CMU 15-780: Graduate Artificial Intelligence

Stock Forecasting Using Neural Nets

Implemented and compared the performance of 3 machine learning alorithms (logstic regression, support vector machine (SVM), and a neural network or multi-layer perceptron) in forcasting stock market trends. Algorithms used several input metrics for the ML hypothesis funciton: price-to-earnings (P/E) ratio, Price-to-book (P/B) ratio, Debt-Equity, Free cash flow, price/earnings to growth (PEG) ratio, and Google Trends data.

Check out our Final Project Paper