Clickstream Mining Decision Trees
he project is based on a task posed in KDD Cup 2000. It involves mining click-stream data collected from Gazelle.com, which sells legware products. Your task is to determine: Given a set of page views, will the visitor view another page on the site or will he leave?
The data set given to you is in a different form than the original. In particular it has discretized numerical values obtained by partitioning them into 5 intervals of equal frequency. This way, we get a data set where for each feature, we have a finite set of values. These values are mapped to integers, so that the data is easier for you to handle
Implemented the ID3 decision tree learner on Python using the chi-squared split stopping criterion with the p-value threshold given as a parameter.