Identified which Enron employees are more likely to have committed fraud using machine learning and public Enron financial and email data.
The poi_id_notebook file contains a jupyter notebook illustrating the whole process of this project, including testing different classifiers, selecting features and tuning classifier parameters. The poi_id.py file represents the classifier, features and parameters that returned the best results for me. The classifier, dataset and feature list is dumped into 3 .pkl files. I also included .pkl from using PCA in combination with a decision tree classifier.