Of the utility of the TEST dataset

Of the utility of the TEST dataset Let’s assume that we want to create a ranking (or a “list of candidates”) for a marketing campaign using predictive technique. Let’s give a practical and real example. Let’s assume that we are end of 2009 and you are selling a “GPS device” (like Garmin or TomTom). You

Classification problems: lift curve or classification table?

Classification problems: lift curve or classification table? The common idea of classifying is to look at “small groups” of records, and evaluate if we should put them a 1 or a 0 when it comes to a particular target. For example, if I am interested in figuring out who will get cancer, I can “build”

Not all lifts are born equal

Not all lifts are born equal Let’s return to the same example as for the previous section about “CRM tools”. Let’s assume that you want to do a direct-mail marketing campaign for one of your product. You must find all the customers that are susceptible to buy your product and send them a brochure or

Lift, ROC, AUC and Gini

Lift, ROC, AUC and Gini One good way to compare different predictive modeling platforms is to compare the models that are produced by these platform.Comparing models across platform is not an easy task. Models can be compared using various criteria’s: 1.    Simple predictive Model Quality (i.e. Height of the lift curve / AUC) 2.    Generalization