The Enron scandal was an accounting scandal involving Enron Corporation, an American energy company based in Houston, Texas. Upon being publicized in October 2001, the company declared bankruptcy and its accounting firm, Arthur Andersen – then one of the five largest audit and accountancy partnerships in the world – was effectively dissolved. In addition to being the largest bankruptcy reorganization in U.S. history at that time, Enron was cited as the biggest audit failure.
To develop a fraud detection machine learning model using information that is common among many companies, which may be useful to identify person of interests in similar situations.
- Original email dataset: Latest version was released by CMU in 2015, containing over 600,000 emails from 158 employees of the Enron corporation
- For simplicity, we picked an open source person of interest (POI) dataset, which has been combined with the email dataset, to help develop fraud detection models
- POI dataset: Contained 145 records consisting of 14 financial attributes, 7 email attributes and a class label (POI)
- Data source: https://github.com/missmariss31/enron/blob/master/enron.csv
- Understood the background and the case profile of the financial fraud case
- Identified the data sources that need to be collected for building the fraud detection model
- Performed EDA (Exploratory Data Analysis) to have a preliminary understanding of the dataset
- Sampling
- Data pre-processing
- Developed a new financial fraud detection model
- Evaluated the performance of the newly developed model
- Identified non-data analytic elements
- Risks and red flags of the case, with the objective to prevent similar financial frauds in future
- Corporate governance and controls
- Suggestions on how to prevent similar financial fraud in future
- Me
- Janus
- Johnathan
- Ricky