Hospitality service in numbers
Key Performance Indicators (KPI) for Hospitality industry help remove the guesswork from managing the business by checking the numbers that tell what’s really happening.
There’s a business saying: ‘If you can’t measure it, you can’t manage it!’ Real, responsive management needs reliable and truthful figures on which decisions can be based. If there are problems, you can take corrective action quickly. If you are having success, you’ll know to do more of what you’re doing! Good figures also give you a wider understanding of your success – sometimes if it’s a quiet month (when your suppliers are telling you that ‘everyone’s quiet!’) you’ll see that some of your KPIs are actually improving (ex. sales per head).
KPIs in Hospitality industry can be categorized for functions like Reception, Housekeeping, Maintenance, Kitchen, Restaurant, Sales, Store, Purchasing, etc.
Staff KPI:
- Wage Cost %: wage costs as a percentage of sales
- Total Labour Cost %: not just wages but also the other work cover insurance, retirement and superannuation charges and other taxes that apply on your payroll
- Total Labour Hours: how many hours worked in each section. This is useful to compare against sales to measure productivity
- Event Labour charge-out: Hotels usually charge-out service staff at a markup on the cost of the wages paid. Are you achieving a consistent mark-up?
- Labour turnover: number of new staff in any one week or month
- Average length of employment: another way to look at your success in keeping staff. Add up the total number of weeks all your people have worked for you and divide this by the total number of staff
- Average hourly pay: divide the total payroll by the number of hours worked by all staff
Kitchen Management KPI:
- Food Cost %: measured by adding up food purchases for the week and measuring them against your food sales
- Total Food Costs: how much was total food bill? Sometimes a useful figure to show staff who think you are made of money
- Food Costs per head: see every week how much it costs to feed an average customer
- Kitchen Labour %: measure kitchen productivity by comparing kitchen labour against food sales
- Kitchen Labour hours: how many hours worked in this section? Compare against sales to measure productivity
- Stock value: food stock holding- It should be less than a week’s use, but can slip out if you are storing frozen food
- Main selling items: weekly sales from POS or dockets & know the best sellers and map these on the Menu Profitability
- Kitchen linen costs: cost of uniforms, aprons & tea-towels can be a shock! How many tea-towels are being used each day?
Front House Management KPI:
- Total Sales Per Head: total sales divided by number of customers. This may vary between different times of the day
- Number of customers: simple! A good measure of popularity
- Food, Dessert, Beverage Sales per head: how much your menu appeals to your customers (do you have all the choices they want), & how well your staff are selling.
- Seating Efficiency: how well are tables being turned over while still offering high quality customer service
- Basket Analysis: how many items do lunch customers buy? What else do morning coffee drinkers order? Grab a pile of dockets and look for ordering patterns
- Linen costs: uniforms, aprons etc.
- Front of House Labour %: how many hours worked in this section? Compare against sales to measure productivity
- FOH Labour hours: how many hours worked in this section? Compare against sales to measure productivity
- Customer satisfaction: Feedback forms, complaints and other methods that are hard to quantify sometimes but worth making an attempt.
- Strike rate: if 500 people came to hotel last night & only 100 ate at the bistro, your ’strike rate’ would be 1 in 5, or 20%
- RevPASH Revenue per Available Seat Hour: take the total number of ’seat hours’ and divide total revenue for a period by this number
Bar & Restaurant Management KPI:
- Sales per head: how much your beverage and wine appeals to your customers and how well your staff are selling
- Gross Profit on sales: difference between what you sold and what it cost you. The sales mix can influence this heavily
- Average Profit % on sales: useful to see if your sales are holding steady, although ultimately the actual Gross Profit (real money) will matter the most
- Stock value: It’s worth checking with your suppliers and seeing how much you can order ‘just in time’
- Stock turnover: how fast is your cellar stock selling?
- Carrying cost of stock: what is the cost of financing the stock?
- Sales / stock-take discrepancies: Alcohol is security problem, & keeping an eye on ’shrinkage’, staff drinks and stealing a constant problem
Banquet Sales Management KPI:
- Number of customers: simple! A good measure of popularity.
- Visits by your top 100 or 200 customers: they provide a huge proportion of your sales! Track their frequency and spending – these people are gold!
- Sales per head: across all areas
- Marketing and advertising costs: total value of spend, always trying to measure it against response
- Response rates: how many people responded to different campaigns and what effect did this have on profit?
- Press mentions: keeping your eyes open for favourable mentions
- Bookings: in the current week and month and coming up. Also in peak times, eg Christmas.
- Event inquiries: No. of inquiries about large bookings & functions, especially if a campaign to promote them is on
- Sales inquiry conversion rate: No. of inquiries that turn into actual sales. why so few people were ‘converted’ – was it the quality of the promotional material, skill of the sales staff, pricing or make-up of your function menus and facilities?
Finance & Admin Management KPI:
- Cash position at bank: how much do you have available after reconciling your cheque book?
- Stock-take discrepancies: measure of efficiency of each department, but also of administrative systems in place
- Total accounts due: how much do you owe?
- Total accounts payable: needs careful management if you have accounts, eg large restaurants
- Return on Investment: profit business makes can be measured as a percentage return on the amount invested in it
- Taxes owed: to know how much is owed at any one time so it is not ’spent’
- Sales & costs: actual figures compared to what budgeted for a period
- Administration labour costs: strong and skilful administrative support will be essential to manage the KPIs listed above!
- IT efficiency: how much down-time for IT systems? How accurate is the POS system?
Other KPIs:
- Revenue per available room
- Average daily rate of rooms
- % of occupancy of rooms
- Average cleaning costs per room
- % of reservation requests cancelled with / without penalty
- % of rooms with maintenance issues
- % of cancelled reservation requests
- Average number of guests per room
- Average length of stay of guests
- % of non-room revenue
- % of cancelled rooms occupied
- Kilowatt-hours (kwh) per room
- Number of hotel guests per employee
- Gross operating profits per available room
- % of guests who would rank stay as exceeding expectations
- Waste per night per occupied bed space
Data Science blog
mandag 23. mai 2016
søndag 22. mai 2016
Another approach to Time Intelligence
Best Parctices for Time Scale solution
This is an original method that I use when I build SSAS Cubes and it is time to share it with you
Time Intelligence is a common issue for every OLAP structure because Time as dimension apperars in every OLAP project, in every Cube you build, despite business model or type. To handle Time Intelligence good in calculations, aggregations and optimization, you need to use Timescale as well. With Timescale I mean: MonthToDate (MTD), YearToDate (YTD), LastYear(LY) etc..., all these very important to everyday use of Business Intelligence solutions.
Now I will take to technical steps to implement this genius way of handling with Timescale and Time calculations.
First you create a Table for Timescale in the source (in you DB, DWH or Data Mart), with 3-4 columns and 3-4 records for example. Here is a sample for that:
Based on this table you create a Dimension Timescale where Columns are Attributes and Records are Members of that Dimension.
After that, I go to DSV of our Cube, on every Fact Table that needs Timescale (usually all need Timescale) I add Named Calculation FK_Timescale with value 'PE', as in the image above:
I create a relationship FK_Timescale of the Fact Table to Timescale table in Data Source View (DSV) and after I build the Cube I do the same in Dimension Usage, where I create Regular relation between Fact Table and Timescale Dimension as shown above:
I create 2 name sets for MTD and YTD right after Calculate; and the MDX for that is shown above :
CALCULATE;
-- Period to date
-- Month to Date
[Timescale].[Timescale].[MTD] = Sum(MTD([Time Dim].[Hierarchy].CurrentMember),[Timescale].[Timescale].[PE]);
-- Year to Date
[Timescale].[Timescale].[YTD] = Sum(YTD([Time Dim].[Hierarchy].CurrentMember),[Timescale].[Timescale].[PE]);
Now, you have ready implemmented Timescale in the Cube for all your Measures, so you do not need to calculate Timescales for each Measure. Instead of having MTD(YTD) Revenue, you just use Revenue measure and change Timescale from PE to MTD(YTD). Test this with Excel, through Data Connection to OLAP Cube and enjoy possibilities. This way is proven more dynamic, flexible and optimized for query performance.
I would be very pleased and that will help me keeping posting good things about BI, if you find time from your busy schedule to suggest, critic or to share with love this blog or this particular content.
This is an original method that I use when I build SSAS Cubes and it is time to share it with you
Time Intelligence is a common issue for every OLAP structure because Time as dimension apperars in every OLAP project, in every Cube you build, despite business model or type. To handle Time Intelligence good in calculations, aggregations and optimization, you need to use Timescale as well. With Timescale I mean: MonthToDate (MTD), YearToDate (YTD), LastYear(LY) etc..., all these very important to everyday use of Business Intelligence solutions.
Now I will take to technical steps to implement this genius way of handling with Timescale and Time calculations.
First you create a Table for Timescale in the source (in you DB, DWH or Data Mart), with 3-4 columns and 3-4 records for example. Here is a sample for that:
Based on this table you create a Dimension Timescale where Columns are Attributes and Records are Members of that Dimension.
After that, I go to DSV of our Cube, on every Fact Table that needs Timescale (usually all need Timescale) I add Named Calculation FK_Timescale with value 'PE', as in the image above:
I create a relationship FK_Timescale of the Fact Table to Timescale table in Data Source View (DSV) and after I build the Cube I do the same in Dimension Usage, where I create Regular relation between Fact Table and Timescale Dimension as shown above:
I create 2 name sets for MTD and YTD right after Calculate; and the MDX for that is shown above :
CALCULATE;
-- Period to date
-- Month to Date
[Timescale].[Timescale].[MTD] = Sum(MTD([Time Dim].[Hierarchy].CurrentMember),[Timescale].[Timescale].[PE]);
-- Year to Date
[Timescale].[Timescale].[YTD] = Sum(YTD([Time Dim].[Hierarchy].CurrentMember),[Timescale].[Timescale].[PE]);
Now, you have ready implemmented Timescale in the Cube for all your Measures, so you do not need to calculate Timescales for each Measure. Instead of having MTD(YTD) Revenue, you just use Revenue measure and change Timescale from PE to MTD(YTD). Test this with Excel, through Data Connection to OLAP Cube and enjoy possibilities. This way is proven more dynamic, flexible and optimized for query performance.
I would be very pleased and that will help me keeping posting good things about BI, if you find time from your busy schedule to suggest, critic or to share with love this blog or this particular content.
Predictive Analytics
Predictive analytics encompasses a variety of techniques from statistics, data mining and game theory that analyze current and historical facts to make predictions about future events.
In business, predictive models exploit patterns found in historical and transactional data to identify risks and opportunities. Models capture relationships among many factors to allow assessment of risk or potential associated with a particular set of conditions, guiding decision making for candidate transactions.
Predictive analytics is used in actuarial science, financial services, insurance, telecommunications, retail, travel, healthcare, pharmaceuticals and other fields.
One of the most well-known applications is credit scoring, which is used throughout financial services. Scoring models process a customer’s credit history, loan application, customer data, etc., in order to rank-order individuals by their likelihood of making future credit payments on time. A well-known example would be the FICO score.
Definition Predictive analytics is an area of statistical analysis that deals with extracting information from data and using it to predict future trends and behavior patterns. The core of predictive analytics relies on capturing relationships between explanatory variables and the predicted variables from past occurrences, and exploiting it to predict future outcomes. It is important to note, however, that the accuracy and usability of results will depend greatly on the level of data analysis and the quality of assumptions.
Types: Generally, the term predictive analytics is used to mean predictive modeling, "scoring" data with predictive models, and forecasting. However, people are increasingly using the term to describe related analytical disciplines, such as descriptive modeling and decision modeling or optimization. These disciplines also involve rigorous data analysis, and are widely used in business for segmentation and decision making, but have different purposes and the statistical techniques underlying them vary.
Predictive models: Predictive models analyze past performance to assess how likely a customer is to exhibit a specific behavior in the future in order to improve marketing effectiveness. This category also encompasses models that seek out subtle data patterns to answer questions about customer performance, such as fraud detection models. Predictive models often perform calculations during live transactions, for example, to evaluate the risk or opportunity of a given customer or transaction, in order to guide a decision. With advancement in computing speed, individual agent modeling systems can simulate human behavior or reaction to given stimuli or scenarios. The new term for animating data specifically linked to an individual in a simulated environment is avatar analytics.
Descriptive models: Descriptive models quantify relationships in data in a way that is often used to classify customers or prospects into groups. Unlike predictive models that focus on predicting a single customer behavior (such as credit risk), descriptive models identify many different relationships between customers or products. Descriptive models do not rank-order customers by their likelihood of taking a particular action the way predictive models do. Descriptive models can be used, for example, to categorize customers by their product preferences and life stage. Descriptive modeling tools can be utilized to develop further models that can simulate large number of individualized agents and make predictions.
Decision models: Decision models describe the relationship between all the elements of a decision — the known data (including results of predictive models), the decision and the forecast results of the decision — in order to predict the results of decisions involving many variables. These models can be used in optimization, maximizing certain outcomes while minimizing others. Decision models are generally used to develop decision logic or a set of business rules that will produce the desired action for every customer or circumstance.
Applications: Although predictive analytics can be put to use in many applications, we outline a few examples where predictive analytics has shown positive impact in recent years.
Analytical customer relationship management (CRM): Analytical Customer Relationship Management is a frequent commercial application of Predictive Analysis. Methods of predictive analysis are applied to customer data to pursue CRM objectives.
Clinical decision support systems: Experts use predictive analysis in health care primarily to determine which patients are at risk of developing certain conditions, like diabetes, asthma, heart disease and other lifetime illnesses. Additionally, sophisticated clinical decision support systems incorporate predictive analytics to support medical decision making at the point of care. A working definition has been proposed by Dr. Robert Hayward of the Centre for Health Evidence: "Clinical Decision Support systems link health observations with health knowledge to influence health choices by clinicians for improved health care."
Collection analytics: Every portfolio has a set of delinquent customers who do not make their payments on time. The financial institution has to undertake collection activities on these customers to recover the amounts due. A lot of collection resources are wasted on customers who are difficult or impossible to recover. Predictive analytics can help optimize the allocation of collection resources by identifying the most effective collection agencies, contact strategies, legal actions and other strategies to each customer, thus significantly increasing recovery at the same time reducing collection costs.
Cross-sell: Often corporate organizations collect and maintain abundant data (e.g. customer records, sale transactions) and exploiting hidden relationships in the data can provide a competitive advantage to the organization. For an organization that offers multiple products, an analysis of existing customer behavior can lead to efficient cross sell of products. This directly leads to higher profitability per customer and strengthening of the customer relationship. Predictive analytics can help analyze customers’ spending, usage and other behavior, and help cross-sell the right product at the right time.
Customer retention: With the number of competing services available, businesses need to focus efforts on maintaining continuous consumer satisfaction. In such a competitive scenario, consumer loyalty needs to be rewarded and customer attrition needs to be minimized. Businesses tend to respond to customer attrition on a reactive basis, acting only after the customer has initiated the process to terminate service. At this stage, the chance of changing the customer’s decision is almost impossible. Proper application of predictive analytics can lead to a more proactive retention strategy. By a frequent examination of a customer’s past service usage, service performance, spending and other behavior patterns, predictive models can determine the likelihood of a customer wanting to terminate service sometime in the near future. An intervention with lucrative offers can increase the chance of retaining the customer. Silent attrition is the behavior of a customer to slowly but steadily reduce usage and is another problem faced by many companies. Predictive analytics can also predict this behavior accurately and before it occurs, so that the company can take proper actions to increase customer activity.
Direct marketing: When marketing consumer products and services there is the challenge of keeping up with competing products and consumer behavior. Apart from identifying prospects, predictive analytics can also help to identify the most effective combination of product versions, marketing material, communication channels and timing that should be used to target a given consumer. The goal of predictive analytics is typically to lower the cost per order or cost per action.
Fraud detection: Fraud is a big problem for many businesses and can be of various types. Inaccurate credit applications, fraudulent transactions (both offline and online), identity thefts and false insurance claims are some examples of this problem. These problems plague firms all across the spectrum and some examples of likely victims are credit card issuers, insurance companies, retail merchants, manufacturers, business to business suppliers and even services providers. This is an area where a predictive model is often used to help weed out the “bads” and reduce a business's exposure to fraud.
Predictive modeling can also be used to detect financial statement fraud in companies, allowing auditors to gauge a company's relative risk, and to increase substantive audit procedures as needed.
The Internal Revenue Service (IRS) of the United States also uses predictive analytics to try to locate tax fraud.
Portfolio, product or economy level prediction: Often the focus of analysis is not the consumer but the product, portfolio, firm, industry or even the economy. For example a retailer might be interested in predicting store level demand for inventory management purposes. Or the Federal Reserve Board might be interested in predicting the unemployment rate for the next year. These type of problems can be addressed by predictive analytics using Time Series techniques (see below).
Underwriting: Many businesses have to account for risk exposure due to their different services and determine the cost needed to cover the risk. For example, auto insurance providers need to accurately determine the amount of premium to charge to cover each automobile and driver. A financial company needs to assess a borrower’s potential and ability to pay before granting a loan. For a health insurance provider, predictive analytics can analyze a few years of past medical claims data, as well as lab, pharmacy and other records where available, to predict how expensive an enrollee is likely to be in the future. Predictive analytics can help underwriting of these quantities by predicting the chances of illness, default, bankruptcy, etc. Predictive analytics can streamline the process of customer acquisition, by predicting the future risk behavior of a customer using application level data. Predictive analytics in the form of credit scores have reduced the amount of time it takes for loan approvals, especially in the mortgage market where lending decisions are now made in a matter of hours rather than days or even weeks. Proper predictive analytics can lead to proper pricing decisions, which can help mitigate future risk of default.
Statistical techniques: The approaches and techniques used to conduct predictive analytics can broadly be grouped into regression techniques and machine learning techniques.
Regression techniques: Regression models are the mainstay of predictive analytics. The focus lies on establishing a mathematical equation as a model to represent the interactions between the different variables in consideration. Depending on the situation, there is a wide variety of models that can be applied while performing predictive analytics. Some of them are briefly discussed below.
Linear regression model: The linear regression model analyzes the relationship between the response or dependent variable and a set of independent or predictor variables. This relationship is expressed as an equation that predicts the response variable as a linear function of the parameters. These parameters are adjusted so that a measure of fit is optimized. Much of the effort in model fitting is focused on minimizing the size of the residual, as well as ensuring that it is randomly distributed with respect to the model predictions.
The goal of regression is to select the parameters of the model so as to minimize the sum of the squared residuals. This is referred to as ordinary least squares (OLS) estimation and results in best linear unbiased estimates (BLUE) of the parameters if and only if the Gauss-Markov assumptions are satisfied.
Once the model has been estimated we would be interested to know if the predictor variables belong in the model – i.e. is the estimate of each variable’s contribution reliable? To do this we can check the statistical significance of the model’s coefficients which can be measured using the t-statistic. This amounts to testing whether the coefficient is significantly different from zero. How well the model predicts the dependent variable based on the value of the independent variables can be assessed by using the R² statistic. It measures predictive power of the model i.e. the proportion of the total variation in the dependent variable that is “explained” (accounted for) by variation in the independent variables.
Discrete choice models: Multivariate regression (above) is generally used when the response variable is continuous and has an unbounded range. Often the response variable may not be continuous but rather discrete. While mathematically it is feasible to apply multivariate regression to discrete ordered dependent variables, some of the assumptions behind the theory of multivariate linear regression no longer hold, and there are other techniques such as discrete choice models which are better suited for this type of analysis. If the dependent variable is discrete, some of those superior methods are logistic regression, multinomial logit and probit models. Logistic regression and probit models are used when the dependent variable is binary.
Logistic regression: For more details on this topic, see logistic regression.
In a classification setting, assigning outcome probabilities to observations can be achieved through the use of a logistic model, which is basically a method which transforms information about the binary dependent variable into an unbounded continuous variable and estimates a regular multivariate model (See Allison’s Logistic Regression for more information on the theory of Logistic Regression).
The Wald and likelihood-ratio test are used to test the statistical significance of each coefficient b in the model (analogous to the t tests used in OLS regression; see above). A test assessing the goodness-of-fit of a classification model is the –.
Multinomial logistic regression: An extension of the binary logit model to cases where the dependent variable has more than 2 categories is the multinomial logit model. In such cases collapsing the data into two categories might not make good sense or may lead to loss in the richness of the data. The multinomial logit model is the appropriate technique in these cases, especially when the dependent variable categories are not ordered (for examples colors like red, blue, green). Some authors have extended multinomial regression to include feature selection/importance methods such as Random multinomial logit.
Probit regressionProbit models offer an alternative to logistic regression for modeling categorical dependent variables. Even though the outcomes tend to be similar, the underlying distributions are different. Probit models are popular in social sciences like economics.
A good way to understand the key difference between probit and logit models, is to assume that there is a latent variable z.
We do not observe z but instead observe y which takes the value 0 or 1. In the logit model we assume that y follows a logistic distribution. In the probit model we assume that y follows a standard normal distribution. Note that in social sciences (example economics), probit is often used to model situations where the observed variable y is continuous but takes values between 0 and 1.
Logit versus probit: The Probit model has been around longer than the logit model. They look identical, except that the logistic distribution tends to be a little flat tailed. One of the reasons the logit model was formulated was that the probit model was difficult to compute because it involved calculating difficult integrals. Modern computing however has made this computation fairly simple. The coefficients obtained from the logit and probit model are also fairly close. However, the odds ratio makes the logit model easier to interpret.
For practical purposes the only reasons for choosing the probit model over the logistic model would be:
There is a strong belief that the underlying distribution is normal
The actual event is not a binary outcome (e.g. Bankrupt/not bankrupt) but a proportion (e.g. Proportion of population at different debt levels).
Time series models: Time series models are used for predicting or forecasting the future behavior of variables. These models account for the fact that data points taken over time may have an internal structure (such as autocorrelation, trend or seasonal variation) that should be accounted for. As a result standard regression techniques cannot be applied to time series data and methodology has been developed to decompose the trend, seasonal and cyclical component of the series. Modeling the dynamic path of a variable can improve forecasts since the predictable component of the series can be projected into the future.
Time series models estimate difference equations containing stochastic components. Two commonly used forms of these models are autoregressive models (AR) and moving average (MA) models. The Box-Jenkins methodology (1976) developed by George Box and G.M. Jenkins combines the AR and MA models to produce the ARMA (autoregressive moving average) model which is the cornerstone of stationary time series analysis. ARIMA (autoregressive integrated moving average models) on the other hand are used to describe non-stationary time series. Box and Jenkins suggest differencing a non stationary time series to obtain a stationary series to which an ARMA model can be applied. Non stationary time series have a pronounced trend and do not have a constant long-run mean or variance.
Box and Jenkins proposed a three stage methodology which includes: model identification, estimation and validation. The identification stage involves identifying if the series is stationary or not and the presence of seasonality by examining plots of the series, autocorrelation and partial autocorrelation functions. In the estimation stage, models are estimated using non-linear time series or maximum likelihood estimation procedures. Finally the validation stage involves diagnostic checking such as plotting the residuals to detect outliers and evidence of model fit.
In recent years time series models have become more sophisticated and attempt to model conditional heteroskedasticity with models such as ARCH (autoregressive conditional heteroskedasticity) and GARCH (generalized autoregressive conditional heteroskedasticity) models frequently used for financial time series. In addition time series models are also used to understand inter-relationships among economic variables represented by systems of equations using VAR (vector autoregression) and structural VAR models.
Survival or duration analysis: Survival analysis is another name for time to event analysis. These techniques were primarily developed in the medical and biological sciences, but they are also widely used in the social sciences like economics, as well as in engineering (reliability and failure time analysis).
Censoring and non-normality, which are characteristic of survival data, generate difficulty when trying to analyze the data using conventional statistical models such as multiple linear regression. The normal distribution, being a symmetric distribution, takes positive as well as negative values, but duration by its very nature cannot be negative and therefore normality cannot be assumed when dealing with duration/survival data. Hence the normality assumption of regression models is violated.
The assumption is that if the data were not censored it would be representative of the population of interest. In survival analysis, censored observations arise whenever the dependent variable of interest represents the time to a terminal event, and the duration of the study is limited in time.
An important concept in survival analysis is the hazard rate, defined as the probability that the event will occur at time t conditional on surviving until time t. Another concept related to the hazard rate is the survival function which can be defined as the probability of surviving to time t.
Most models try to model the hazard rate by choosing the underlying distribution depending on the shape of the hazard function. A distribution whose hazard function slopes upward is said to have positive duration dependence, a decreasing hazard shows negative duration dependence whereas constant hazard is a process with no memory usually characterized by the exponential distribution. Some of the distributional choices in survival models are: F, gamma, Weibull, log normal, inverse normal, exponential etc. All these distributions are for a non-negative random variable.
Duration models can be parametric, non-parametric or semi-parametric. Some of the models commonly used are Kaplan-Meier and Cox proportional hazard model (non parametric).
Classification and regression trees: Main article: decision tree learning
Classification and regression trees (CART) is a non-parametric decision tree learning technique that produces either classification or regression trees, depending on whether the dependent variable is categorical or numeric, respectively.
Decision trees are formed by a collection of rules based on variables in the modeling data set:
Rules based on variables’ values are selected to get the best split to differentiate observations based on the dependent variable
Once a rule is selected and splits a node into two, the same process is applied to each “child” node (i.e. it is a recursive procedure)
Splitting stops when CART detects no further gain can be made, or some pre-set stopping rules are met. (Alternatively, the data is split as much as possible and then the tree is later pruned.)
Each branch of the tree ends in a terminal node. Each observation falls into one and exactly one terminal node, and each terminal node is uniquely defined by a set of rules.
A very popular method for predictive analytics is Leo Breiman's Random forests or derived versions of this technique like Random multinomial logit.
Multivariate adaptive regression splines: Multivariate adaptive regression splines (MARS) is a non-parametric technique that builds flexible models by fitting piecewise linear regressions.
An important concept associated with regression splines is that of a knot. Knot is where one local regression model gives way to another and thus is the point of intersection between two splines.
In multivariate and adaptive regression splines, basis functions are the tool used for generalizing the search for knots. Basis functions are a set of functions used to represent the information contained in one or more variables. Multivariate and Adaptive Regression Splines model almost always creates the basis functions in pairs.
Multivariate and adaptive regression spline approach deliberately overfits the model and then prunes to get to the optimal model. The algorithm is computationally very intensive and in practice we are required to specify an upper limit on the number of basis functions.
Machine learning techniques. Machine learning, a branch of artificial intelligence, was originally employed to develop techniques to enable computers to learn. Today, since it includes a number of advanced statistical methods for regression and classification, it finds application in a wide variety of fields including medical diagnostics, credit card fraud detection, face and speech recognition and analysis of the stock market. In certain applications it is sufficient to directly predict the dependent variable without focusing on the underlying relationships between variables. In other cases, the underlying relationships can be very complex and the mathematical form of the dependencies unknown. For such cases, machine learning techniques emulate human cognition and learn from training examples to predict future events.
A brief discussion of some of these methods used commonly for predictive analytics is provided below. A detailed study of machine learning can be found in Mitchell (1997).
Neural networks. Neural networks are nonlinear sophisticated modeling techniques that are able to model complex functions. They can be applied to problems of prediction, classification or control in a wide spectrum of fields such as finance, cognitive psychology/neuroscience, medicine, engineering, and physics.
Neural networks are used when the exact nature of the relationship between inputs and output is not known. A key feature of neural networks is that they learn the relationship between inputs and output through training. There are two types of training in neural networks used by different networks, supervised and unsupervised training, with supervised being the most common one.
Some examples of neural network training techniques are backpropagation, quick propagation, conjugate gradient descent, projection operator, Delta-Bar-Delta etc. Some unsupervised network architectures are multilayer perceptrons, Kohonen networks, Hopfield networks, etc.
Radial basis functions: A radial basis function (RBF) is a function which has built into it a distance criterion with respect to a center. Such functions can be used very efficiently for interpolation and for smoothing of data. Radial basis functions have been applied in the area of neural networks where they are used as a replacement for the sigmoidal transfer function. Such networks have 3 layers, the input layer, the hidden layer with the RBF non-linearity and a linear output layer. The most popular choice for the non-linearity is the Gaussian. RBF networks have the advantage of not being locked into local minima as do the feed-forward networks such as the multilayer perceptron.
Support vector machines: Support Vector Machines (SVM) are used to detect and exploit complex patterns in data by clustering, classifying and ranking the data. They are learning machines that are used to perform binary classifications and regression estimations. They commonly use kernel based methods to apply linear classification techniques to non-linear classification problems. There are a number of types of SVM such as linear, polynomial, sigmoid etc.
Naïve Bayes: Naïve Bayes based on Bayes conditional probability rule is used for performing classification tasks. Naïve Bayes assumes the predictors are statistically independent which makes it an effective classification tool that is easy to interpret. It is best employed when faced with the problem of ‘curse of dimensionality’ i.e. when the number of predictors is very high.
K-nearest neighbours: The nearest neighbour algorithm (KNN) belongs to the class of pattern recognition statistical methods. The method does not impose a priori any assumptions about the distribution from which the modeling sample is drawn. It involves a training set with both positive and negative values. A new sample is classified by calculating the distance to the nearest neighbouring training case. The sign of that point will determine the classification of the sample. In the k-nearest neighbour classifier, the k nearest points are considered and the sign of the majority is used to classify the sample. The performance of the kNN algorithm is influenced by three main factors: (1) the distance measure used to locate the nearest neighbours; (2) the decision rule used to derive a classification from the k-nearest neighbours; and (3) the number of neighbours used to classify the new sample. It can be proved that, unlike other methods, this method is universally asymptotically convergent, i.e.: as the size of the training set increases, if the observations are independent and identically distributed (i.i.d.), regardless of the distribution from which the sample is drawn, the predicted class will converge to the class assignment that minimizes misclassification error.
Geospatial predictive modeling: Conceptually, geospatial predictive modeling is rooted in the principle that the occurrences of events being modeled are limited in distribution. Occurrences of events are neither uniform nor random in distribution – there are spatial environment factors (infrastructure, sociocultural, topographic, etc.) that constrain and influence where the locations of events occur. Geospatial predictive modeling attempts to describe those constraints and influences by spatially correlating occurrences of historical geospatial locations with environmental factors that represent those constraints and influences. Geospatial predictive modeling is a process for analyzing events through a geographic filter in order to make statements of likelihood for event occurrence or emergence.
Tools: There are numerous tools available in the marketplace which help with the execution of predictive analytics. These range from those which need very little user sophistication to those that are designed for the expert practitioner. The difference between these tools is often in the level of customization and heavy data lifting allowed.
In an attempt to provide a standard language for expressing predictive models, the Predictive Model Markup Language (PMML) has been proposed. Such an XML-based language provides a way for the different tools to define predictive models and to share these between PMML compliant applications. PMML 4.0 was released in June, 2009.
In business, predictive models exploit patterns found in historical and transactional data to identify risks and opportunities. Models capture relationships among many factors to allow assessment of risk or potential associated with a particular set of conditions, guiding decision making for candidate transactions.
Predictive analytics is used in actuarial science, financial services, insurance, telecommunications, retail, travel, healthcare, pharmaceuticals and other fields.
One of the most well-known applications is credit scoring, which is used throughout financial services. Scoring models process a customer’s credit history, loan application, customer data, etc., in order to rank-order individuals by their likelihood of making future credit payments on time. A well-known example would be the FICO score.
Definition Predictive analytics is an area of statistical analysis that deals with extracting information from data and using it to predict future trends and behavior patterns. The core of predictive analytics relies on capturing relationships between explanatory variables and the predicted variables from past occurrences, and exploiting it to predict future outcomes. It is important to note, however, that the accuracy and usability of results will depend greatly on the level of data analysis and the quality of assumptions.
Types: Generally, the term predictive analytics is used to mean predictive modeling, "scoring" data with predictive models, and forecasting. However, people are increasingly using the term to describe related analytical disciplines, such as descriptive modeling and decision modeling or optimization. These disciplines also involve rigorous data analysis, and are widely used in business for segmentation and decision making, but have different purposes and the statistical techniques underlying them vary.
Predictive models: Predictive models analyze past performance to assess how likely a customer is to exhibit a specific behavior in the future in order to improve marketing effectiveness. This category also encompasses models that seek out subtle data patterns to answer questions about customer performance, such as fraud detection models. Predictive models often perform calculations during live transactions, for example, to evaluate the risk or opportunity of a given customer or transaction, in order to guide a decision. With advancement in computing speed, individual agent modeling systems can simulate human behavior or reaction to given stimuli or scenarios. The new term for animating data specifically linked to an individual in a simulated environment is avatar analytics.
Descriptive models: Descriptive models quantify relationships in data in a way that is often used to classify customers or prospects into groups. Unlike predictive models that focus on predicting a single customer behavior (such as credit risk), descriptive models identify many different relationships between customers or products. Descriptive models do not rank-order customers by their likelihood of taking a particular action the way predictive models do. Descriptive models can be used, for example, to categorize customers by their product preferences and life stage. Descriptive modeling tools can be utilized to develop further models that can simulate large number of individualized agents and make predictions.
Decision models: Decision models describe the relationship between all the elements of a decision — the known data (including results of predictive models), the decision and the forecast results of the decision — in order to predict the results of decisions involving many variables. These models can be used in optimization, maximizing certain outcomes while minimizing others. Decision models are generally used to develop decision logic or a set of business rules that will produce the desired action for every customer or circumstance.
Applications: Although predictive analytics can be put to use in many applications, we outline a few examples where predictive analytics has shown positive impact in recent years.
Analytical customer relationship management (CRM): Analytical Customer Relationship Management is a frequent commercial application of Predictive Analysis. Methods of predictive analysis are applied to customer data to pursue CRM objectives.
Clinical decision support systems: Experts use predictive analysis in health care primarily to determine which patients are at risk of developing certain conditions, like diabetes, asthma, heart disease and other lifetime illnesses. Additionally, sophisticated clinical decision support systems incorporate predictive analytics to support medical decision making at the point of care. A working definition has been proposed by Dr. Robert Hayward of the Centre for Health Evidence: "Clinical Decision Support systems link health observations with health knowledge to influence health choices by clinicians for improved health care."
Collection analytics: Every portfolio has a set of delinquent customers who do not make their payments on time. The financial institution has to undertake collection activities on these customers to recover the amounts due. A lot of collection resources are wasted on customers who are difficult or impossible to recover. Predictive analytics can help optimize the allocation of collection resources by identifying the most effective collection agencies, contact strategies, legal actions and other strategies to each customer, thus significantly increasing recovery at the same time reducing collection costs.
Cross-sell: Often corporate organizations collect and maintain abundant data (e.g. customer records, sale transactions) and exploiting hidden relationships in the data can provide a competitive advantage to the organization. For an organization that offers multiple products, an analysis of existing customer behavior can lead to efficient cross sell of products. This directly leads to higher profitability per customer and strengthening of the customer relationship. Predictive analytics can help analyze customers’ spending, usage and other behavior, and help cross-sell the right product at the right time.
Customer retention: With the number of competing services available, businesses need to focus efforts on maintaining continuous consumer satisfaction. In such a competitive scenario, consumer loyalty needs to be rewarded and customer attrition needs to be minimized. Businesses tend to respond to customer attrition on a reactive basis, acting only after the customer has initiated the process to terminate service. At this stage, the chance of changing the customer’s decision is almost impossible. Proper application of predictive analytics can lead to a more proactive retention strategy. By a frequent examination of a customer’s past service usage, service performance, spending and other behavior patterns, predictive models can determine the likelihood of a customer wanting to terminate service sometime in the near future. An intervention with lucrative offers can increase the chance of retaining the customer. Silent attrition is the behavior of a customer to slowly but steadily reduce usage and is another problem faced by many companies. Predictive analytics can also predict this behavior accurately and before it occurs, so that the company can take proper actions to increase customer activity.
Direct marketing: When marketing consumer products and services there is the challenge of keeping up with competing products and consumer behavior. Apart from identifying prospects, predictive analytics can also help to identify the most effective combination of product versions, marketing material, communication channels and timing that should be used to target a given consumer. The goal of predictive analytics is typically to lower the cost per order or cost per action.
Fraud detection: Fraud is a big problem for many businesses and can be of various types. Inaccurate credit applications, fraudulent transactions (both offline and online), identity thefts and false insurance claims are some examples of this problem. These problems plague firms all across the spectrum and some examples of likely victims are credit card issuers, insurance companies, retail merchants, manufacturers, business to business suppliers and even services providers. This is an area where a predictive model is often used to help weed out the “bads” and reduce a business's exposure to fraud.
Predictive modeling can also be used to detect financial statement fraud in companies, allowing auditors to gauge a company's relative risk, and to increase substantive audit procedures as needed.
The Internal Revenue Service (IRS) of the United States also uses predictive analytics to try to locate tax fraud.
Portfolio, product or economy level prediction: Often the focus of analysis is not the consumer but the product, portfolio, firm, industry or even the economy. For example a retailer might be interested in predicting store level demand for inventory management purposes. Or the Federal Reserve Board might be interested in predicting the unemployment rate for the next year. These type of problems can be addressed by predictive analytics using Time Series techniques (see below).
Underwriting: Many businesses have to account for risk exposure due to their different services and determine the cost needed to cover the risk. For example, auto insurance providers need to accurately determine the amount of premium to charge to cover each automobile and driver. A financial company needs to assess a borrower’s potential and ability to pay before granting a loan. For a health insurance provider, predictive analytics can analyze a few years of past medical claims data, as well as lab, pharmacy and other records where available, to predict how expensive an enrollee is likely to be in the future. Predictive analytics can help underwriting of these quantities by predicting the chances of illness, default, bankruptcy, etc. Predictive analytics can streamline the process of customer acquisition, by predicting the future risk behavior of a customer using application level data. Predictive analytics in the form of credit scores have reduced the amount of time it takes for loan approvals, especially in the mortgage market where lending decisions are now made in a matter of hours rather than days or even weeks. Proper predictive analytics can lead to proper pricing decisions, which can help mitigate future risk of default.
Statistical techniques: The approaches and techniques used to conduct predictive analytics can broadly be grouped into regression techniques and machine learning techniques.
Regression techniques: Regression models are the mainstay of predictive analytics. The focus lies on establishing a mathematical equation as a model to represent the interactions between the different variables in consideration. Depending on the situation, there is a wide variety of models that can be applied while performing predictive analytics. Some of them are briefly discussed below.
Linear regression model: The linear regression model analyzes the relationship between the response or dependent variable and a set of independent or predictor variables. This relationship is expressed as an equation that predicts the response variable as a linear function of the parameters. These parameters are adjusted so that a measure of fit is optimized. Much of the effort in model fitting is focused on minimizing the size of the residual, as well as ensuring that it is randomly distributed with respect to the model predictions.
The goal of regression is to select the parameters of the model so as to minimize the sum of the squared residuals. This is referred to as ordinary least squares (OLS) estimation and results in best linear unbiased estimates (BLUE) of the parameters if and only if the Gauss-Markov assumptions are satisfied.
Once the model has been estimated we would be interested to know if the predictor variables belong in the model – i.e. is the estimate of each variable’s contribution reliable? To do this we can check the statistical significance of the model’s coefficients which can be measured using the t-statistic. This amounts to testing whether the coefficient is significantly different from zero. How well the model predicts the dependent variable based on the value of the independent variables can be assessed by using the R² statistic. It measures predictive power of the model i.e. the proportion of the total variation in the dependent variable that is “explained” (accounted for) by variation in the independent variables.
Discrete choice models: Multivariate regression (above) is generally used when the response variable is continuous and has an unbounded range. Often the response variable may not be continuous but rather discrete. While mathematically it is feasible to apply multivariate regression to discrete ordered dependent variables, some of the assumptions behind the theory of multivariate linear regression no longer hold, and there are other techniques such as discrete choice models which are better suited for this type of analysis. If the dependent variable is discrete, some of those superior methods are logistic regression, multinomial logit and probit models. Logistic regression and probit models are used when the dependent variable is binary.
Logistic regression: For more details on this topic, see logistic regression.
In a classification setting, assigning outcome probabilities to observations can be achieved through the use of a logistic model, which is basically a method which transforms information about the binary dependent variable into an unbounded continuous variable and estimates a regular multivariate model (See Allison’s Logistic Regression for more information on the theory of Logistic Regression).
The Wald and likelihood-ratio test are used to test the statistical significance of each coefficient b in the model (analogous to the t tests used in OLS regression; see above). A test assessing the goodness-of-fit of a classification model is the –.
Multinomial logistic regression: An extension of the binary logit model to cases where the dependent variable has more than 2 categories is the multinomial logit model. In such cases collapsing the data into two categories might not make good sense or may lead to loss in the richness of the data. The multinomial logit model is the appropriate technique in these cases, especially when the dependent variable categories are not ordered (for examples colors like red, blue, green). Some authors have extended multinomial regression to include feature selection/importance methods such as Random multinomial logit.
Probit regressionProbit models offer an alternative to logistic regression for modeling categorical dependent variables. Even though the outcomes tend to be similar, the underlying distributions are different. Probit models are popular in social sciences like economics.
A good way to understand the key difference between probit and logit models, is to assume that there is a latent variable z.
We do not observe z but instead observe y which takes the value 0 or 1. In the logit model we assume that y follows a logistic distribution. In the probit model we assume that y follows a standard normal distribution. Note that in social sciences (example economics), probit is often used to model situations where the observed variable y is continuous but takes values between 0 and 1.
Logit versus probit: The Probit model has been around longer than the logit model. They look identical, except that the logistic distribution tends to be a little flat tailed. One of the reasons the logit model was formulated was that the probit model was difficult to compute because it involved calculating difficult integrals. Modern computing however has made this computation fairly simple. The coefficients obtained from the logit and probit model are also fairly close. However, the odds ratio makes the logit model easier to interpret.
For practical purposes the only reasons for choosing the probit model over the logistic model would be:
There is a strong belief that the underlying distribution is normal
The actual event is not a binary outcome (e.g. Bankrupt/not bankrupt) but a proportion (e.g. Proportion of population at different debt levels).
Time series models: Time series models are used for predicting or forecasting the future behavior of variables. These models account for the fact that data points taken over time may have an internal structure (such as autocorrelation, trend or seasonal variation) that should be accounted for. As a result standard regression techniques cannot be applied to time series data and methodology has been developed to decompose the trend, seasonal and cyclical component of the series. Modeling the dynamic path of a variable can improve forecasts since the predictable component of the series can be projected into the future.
Time series models estimate difference equations containing stochastic components. Two commonly used forms of these models are autoregressive models (AR) and moving average (MA) models. The Box-Jenkins methodology (1976) developed by George Box and G.M. Jenkins combines the AR and MA models to produce the ARMA (autoregressive moving average) model which is the cornerstone of stationary time series analysis. ARIMA (autoregressive integrated moving average models) on the other hand are used to describe non-stationary time series. Box and Jenkins suggest differencing a non stationary time series to obtain a stationary series to which an ARMA model can be applied. Non stationary time series have a pronounced trend and do not have a constant long-run mean or variance.
Box and Jenkins proposed a three stage methodology which includes: model identification, estimation and validation. The identification stage involves identifying if the series is stationary or not and the presence of seasonality by examining plots of the series, autocorrelation and partial autocorrelation functions. In the estimation stage, models are estimated using non-linear time series or maximum likelihood estimation procedures. Finally the validation stage involves diagnostic checking such as plotting the residuals to detect outliers and evidence of model fit.
In recent years time series models have become more sophisticated and attempt to model conditional heteroskedasticity with models such as ARCH (autoregressive conditional heteroskedasticity) and GARCH (generalized autoregressive conditional heteroskedasticity) models frequently used for financial time series. In addition time series models are also used to understand inter-relationships among economic variables represented by systems of equations using VAR (vector autoregression) and structural VAR models.
Survival or duration analysis: Survival analysis is another name for time to event analysis. These techniques were primarily developed in the medical and biological sciences, but they are also widely used in the social sciences like economics, as well as in engineering (reliability and failure time analysis).
Censoring and non-normality, which are characteristic of survival data, generate difficulty when trying to analyze the data using conventional statistical models such as multiple linear regression. The normal distribution, being a symmetric distribution, takes positive as well as negative values, but duration by its very nature cannot be negative and therefore normality cannot be assumed when dealing with duration/survival data. Hence the normality assumption of regression models is violated.
The assumption is that if the data were not censored it would be representative of the population of interest. In survival analysis, censored observations arise whenever the dependent variable of interest represents the time to a terminal event, and the duration of the study is limited in time.
An important concept in survival analysis is the hazard rate, defined as the probability that the event will occur at time t conditional on surviving until time t. Another concept related to the hazard rate is the survival function which can be defined as the probability of surviving to time t.
Most models try to model the hazard rate by choosing the underlying distribution depending on the shape of the hazard function. A distribution whose hazard function slopes upward is said to have positive duration dependence, a decreasing hazard shows negative duration dependence whereas constant hazard is a process with no memory usually characterized by the exponential distribution. Some of the distributional choices in survival models are: F, gamma, Weibull, log normal, inverse normal, exponential etc. All these distributions are for a non-negative random variable.
Duration models can be parametric, non-parametric or semi-parametric. Some of the models commonly used are Kaplan-Meier and Cox proportional hazard model (non parametric).
Classification and regression trees: Main article: decision tree learning
Classification and regression trees (CART) is a non-parametric decision tree learning technique that produces either classification or regression trees, depending on whether the dependent variable is categorical or numeric, respectively.
Decision trees are formed by a collection of rules based on variables in the modeling data set:
Rules based on variables’ values are selected to get the best split to differentiate observations based on the dependent variable
Once a rule is selected and splits a node into two, the same process is applied to each “child” node (i.e. it is a recursive procedure)
Splitting stops when CART detects no further gain can be made, or some pre-set stopping rules are met. (Alternatively, the data is split as much as possible and then the tree is later pruned.)
Each branch of the tree ends in a terminal node. Each observation falls into one and exactly one terminal node, and each terminal node is uniquely defined by a set of rules.
A very popular method for predictive analytics is Leo Breiman's Random forests or derived versions of this technique like Random multinomial logit.
Multivariate adaptive regression splines: Multivariate adaptive regression splines (MARS) is a non-parametric technique that builds flexible models by fitting piecewise linear regressions.
An important concept associated with regression splines is that of a knot. Knot is where one local regression model gives way to another and thus is the point of intersection between two splines.
In multivariate and adaptive regression splines, basis functions are the tool used for generalizing the search for knots. Basis functions are a set of functions used to represent the information contained in one or more variables. Multivariate and Adaptive Regression Splines model almost always creates the basis functions in pairs.
Multivariate and adaptive regression spline approach deliberately overfits the model and then prunes to get to the optimal model. The algorithm is computationally very intensive and in practice we are required to specify an upper limit on the number of basis functions.
Machine learning techniques. Machine learning, a branch of artificial intelligence, was originally employed to develop techniques to enable computers to learn. Today, since it includes a number of advanced statistical methods for regression and classification, it finds application in a wide variety of fields including medical diagnostics, credit card fraud detection, face and speech recognition and analysis of the stock market. In certain applications it is sufficient to directly predict the dependent variable without focusing on the underlying relationships between variables. In other cases, the underlying relationships can be very complex and the mathematical form of the dependencies unknown. For such cases, machine learning techniques emulate human cognition and learn from training examples to predict future events.
A brief discussion of some of these methods used commonly for predictive analytics is provided below. A detailed study of machine learning can be found in Mitchell (1997).
Neural networks. Neural networks are nonlinear sophisticated modeling techniques that are able to model complex functions. They can be applied to problems of prediction, classification or control in a wide spectrum of fields such as finance, cognitive psychology/neuroscience, medicine, engineering, and physics.
Neural networks are used when the exact nature of the relationship between inputs and output is not known. A key feature of neural networks is that they learn the relationship between inputs and output through training. There are two types of training in neural networks used by different networks, supervised and unsupervised training, with supervised being the most common one.
Some examples of neural network training techniques are backpropagation, quick propagation, conjugate gradient descent, projection operator, Delta-Bar-Delta etc. Some unsupervised network architectures are multilayer perceptrons, Kohonen networks, Hopfield networks, etc.
Radial basis functions: A radial basis function (RBF) is a function which has built into it a distance criterion with respect to a center. Such functions can be used very efficiently for interpolation and for smoothing of data. Radial basis functions have been applied in the area of neural networks where they are used as a replacement for the sigmoidal transfer function. Such networks have 3 layers, the input layer, the hidden layer with the RBF non-linearity and a linear output layer. The most popular choice for the non-linearity is the Gaussian. RBF networks have the advantage of not being locked into local minima as do the feed-forward networks such as the multilayer perceptron.
Support vector machines: Support Vector Machines (SVM) are used to detect and exploit complex patterns in data by clustering, classifying and ranking the data. They are learning machines that are used to perform binary classifications and regression estimations. They commonly use kernel based methods to apply linear classification techniques to non-linear classification problems. There are a number of types of SVM such as linear, polynomial, sigmoid etc.
Naïve Bayes: Naïve Bayes based on Bayes conditional probability rule is used for performing classification tasks. Naïve Bayes assumes the predictors are statistically independent which makes it an effective classification tool that is easy to interpret. It is best employed when faced with the problem of ‘curse of dimensionality’ i.e. when the number of predictors is very high.
K-nearest neighbours: The nearest neighbour algorithm (KNN) belongs to the class of pattern recognition statistical methods. The method does not impose a priori any assumptions about the distribution from which the modeling sample is drawn. It involves a training set with both positive and negative values. A new sample is classified by calculating the distance to the nearest neighbouring training case. The sign of that point will determine the classification of the sample. In the k-nearest neighbour classifier, the k nearest points are considered and the sign of the majority is used to classify the sample. The performance of the kNN algorithm is influenced by three main factors: (1) the distance measure used to locate the nearest neighbours; (2) the decision rule used to derive a classification from the k-nearest neighbours; and (3) the number of neighbours used to classify the new sample. It can be proved that, unlike other methods, this method is universally asymptotically convergent, i.e.: as the size of the training set increases, if the observations are independent and identically distributed (i.i.d.), regardless of the distribution from which the sample is drawn, the predicted class will converge to the class assignment that minimizes misclassification error.
Geospatial predictive modeling: Conceptually, geospatial predictive modeling is rooted in the principle that the occurrences of events being modeled are limited in distribution. Occurrences of events are neither uniform nor random in distribution – there are spatial environment factors (infrastructure, sociocultural, topographic, etc.) that constrain and influence where the locations of events occur. Geospatial predictive modeling attempts to describe those constraints and influences by spatially correlating occurrences of historical geospatial locations with environmental factors that represent those constraints and influences. Geospatial predictive modeling is a process for analyzing events through a geographic filter in order to make statements of likelihood for event occurrence or emergence.
Tools: There are numerous tools available in the marketplace which help with the execution of predictive analytics. These range from those which need very little user sophistication to those that are designed for the expert practitioner. The difference between these tools is often in the level of customization and heavy data lifting allowed.
In an attempt to provide a standard language for expressing predictive models, the Predictive Model Markup Language (PMML) has been proposed. Such an XML-based language provides a way for the different tools to define predictive models and to share these between PMML compliant applications. PMML 4.0 was released in June, 2009.
søndag 8. mai 2016
Which Of The Five Types Of Data Science Does Your Startup Need?
by TOMASZ TUNGUZ
Credit: O'Reilly
Startups, you are doing data science wrong. That’s the title of a post penned by Ryan Weald in GigaOm this week. Weald echoes DJ Patil’s idea: “product-focused data science is different than the current business intelligence style of data science.”
Weald points to a different model of data scientist, an engineer, not a statistician, who can perform queries and based upon some insights, improve the product with a few code changes and a push to git.
I like Weald’s post but disagree on one point. I don’t think there is one type of data scientist, but five.
- Quantitative, exploratory data scientists tend to have PhDs and use theory to understand behavior. I count Hal Varian, Chief Economist at Google, and Redpoint’s own Jamie Davidson, among them. Varian’s team researches the advertiser dynamics within the ads auction and compares those dynamics to theoretical auction models like the Vickery auction. By combining theory and exploratory research, these data scientists improve products.
- Operational data scientists often work in the finance, sales or operations teams at Google. In the AdSense ops team where I started, we had a star data analyst who each week would discuss our team’s performance: our email response times, the satisfaction scores of our publishers, and changes in publisher behavior by segment. His work provided a feedback loop to improve the team’s tactics and efficiency. Only infrequently were these insights used to influence product.
- Product data scientists tend to belong to product management or engineering. This is the group of data scientists Weald writes about. PMs and engineers sift through logs and analysis tools to understand the way users interact a product and leverage that knowledge to refine the product. At Google, the ads quality team analyzed user clicks data to improve ad targeting.
- Marketing data scientists segment the user base, evaluate the performance of advertising campaigns, match product features to customer segments, and design content marketing campaigns. The marketing data scientist creates awareness and leads for the sales team, helping generate revenue.
- Research data scientists create insights as a product. Nate Silver is arguably the most famous of them. Silver’s work doesn’t influence a product; the analysis is the product itself. Sometimes the data science leads to a thought leadership whitepaper, or a blog post, or a financial report. It’s rarer for startups to employ research scientists because the output isn’t tied to revenue. But larger companies like Google do, think tanks do, financial institutions do.
These five types of data scientists span almost every department of knowledge work. Sometime in the past thirty years, data science became inextricable from the day-to-day operation of these teams. Product, marketing, eng, sales all use data to make decisions. These teams use data to identify, understand and implement feedback loops and to reinforce the behavior a company desires.
To talk about data scientists might be too myopic. Your startup may need a research data scientist or one with a PhD. Or it may need an engineer with an understanding of basic statistics who can work up and down the Rails stack. Or another type all together.
Like any role, when hiring or recruiting a data scientist it’s important to identify what the key problems facing the business and the relevant skills the right candidate will need to solve those challenges.
Tableau explain why FC Barcelona is still the best team in Spain (and the whole World)
Introduction
Futbol Club Barcelona, also known as Barça is a professional football club, based in Barcelona, Catalonia, Spain. Founded in 1899 by a group of Swiss, English and Catalan footballers led by Joan Gamper, the club has become a symbol of Catalan culture and Catalanism, hence the motto "Més que un club" (More than a club). Unlike many other football clubs, the supporters own and operate Barcelona. It is the world's second-richest football club in terms of revenue, with an annual turnover of $613 million and the third most valuable sports team, worth $2.6 billion.The official Barcelona anthem is the "Cant del Barça" and it is knows to all 480 000 000 fans around the World.
Team Philosophy
Johan Cruyff and Charly Rexach returned to Barcelona in 1988 and began to install a philosophy that would change the way people play and view football forever. Both Cruyff and Rexach admit that it wasn't a completely new philosophy. Admitting that it was one adapted from ideas given to them by Michels, and one which many believe had been given to Europe by the Hungarian side of the early 1950s. The foundation of this philosophy was, and still is, built upon the basic template of touch, technique, maintaining possession, and stretching the pitch with continuous circulation of the ball (Tiqui-Taka). Elements that, at the time, were not valued by many Barcelona supporters (Hunter, 2012)
The chart down (OptaPro) shows the power of Barcelona over other La Liga teams, its play philosophy of short passes and ball possession.
Team Discipline and attractivness (support by fans)
Why FC Barcelona is better than any team, this season also?!
Conclusion
Futbol Club Barcelona, also known as Barça is a professional football club, based in Barcelona, Catalonia, Spain. Founded in 1899 by a group of Swiss, English and Catalan footballers led by Joan Gamper, the club has become a symbol of Catalan culture and Catalanism, hence the motto "Més que un club" (More than a club). Unlike many other football clubs, the supporters own and operate Barcelona. It is the world's second-richest football club in terms of revenue, with an annual turnover of $613 million and the third most valuable sports team, worth $2.6 billion.The official Barcelona anthem is the "Cant del Barça" and it is knows to all 480 000 000 fans around the World.
Team Philosophy
Johan Cruyff and Charly Rexach returned to Barcelona in 1988 and began to install a philosophy that would change the way people play and view football forever. Both Cruyff and Rexach admit that it wasn't a completely new philosophy. Admitting that it was one adapted from ideas given to them by Michels, and one which many believe had been given to Europe by the Hungarian side of the early 1950s. The foundation of this philosophy was, and still is, built upon the basic template of touch, technique, maintaining possession, and stretching the pitch with continuous circulation of the ball (Tiqui-Taka). Elements that, at the time, were not valued by many Barcelona supporters (Hunter, 2012)
The chart down (OptaPro) shows the power of Barcelona over other La Liga teams, its play philosophy of short passes and ball possession.
Team Discipline and attractivness (support by fans)
Conclusion
With this in mind, it seems that a lot of clubs steal ideas from Barcelona that they see on the surface, such as tactics, and implement them in the short term, but fail to intertwine them into their own specifically moulded model. It is one thing to use Barcelona as inspiration, but it must be remembered that Barcelona's philosophy is tailored to THEIR own needs, no one else's, and the coaching and playing staff have grown together surrounded by it. They have lived by it and through it. Due to Barcelona's on field success, many are using various aspects of the Barcelona model to shape their own coaching methods, training programmes, and playing style etc. Often missing the point that a club philosophy needs to be self defined and fully committed to by all. There are many different styles of playing football, Barcelona have their own unique style of playing, but it should be remembered that this playing style is born out of wider and deeper beliefs in the cultural values of their personal, independent philosophy.
Abonner på:
Innlegg (Atom)