A Decision Tree Classifier with GA based feature selection.

Machine Learning techniques have been applied to the eld of classification for more than a decade. Machine Learning techniques can learn normal and anomalous patterns from training data and generate classifiers, which can be used to capture characteristics of interest. In general, the input data to classifiers is an extremely large set of features, but not all of features are relevant to the classes to be classified. Hence, the learner must generalize from the given examples in order to produce a useful output in new cases.

Our Project, titled Decision Tree Classifier with Genetic Algorithm-based Feature Selection is aimed at developing a complete program that constructs an optimal decision tree, based on any kind of data set, divided into training and testing examples, by selecting only a subset of features to classify data.

Although our program works with generic data samples, it must be noted that when we started this project, our main intention was to classify ground water samples into two classes, namely Potable and Non-Potable Water.