securities-fraud-predict

Using machine learning to predict securities fraud

Hypothesis: Market cap and industry are reliable predictors of securities fraud

• Previous literature: https://www.sciencedirect.com/science/article/pii/S0165410111000681

Technique: Download datasets:

• Publicly traded company data: market cap, ticker, industry
  • https://www.kaggle.com/camnugent/sandp500
• Securities fraud class action data: stanford.securities.edu
  • http://www.kaikaichen.com/?p=1032
• S&P500 companies with sector column
  • https://datahub.io/core/s-and-p-500-companies#resource-constituents