Financial Analysis using Machine Learning Methods

Machine Learning methods have long been applied to financial data. We explore the correlation (or the lack thereof) of financial data, such as the BIST 100 index or individual stock prices, to features extracted from financial news and past data. We intend to use the advancements in text classification and Natural Language Processing capabilities in general, and machine learning models to extract the features of Turkish news documents and stock price series using statistical methods and to analyze the correlation of the extracted features with the financial data. For now, we use basic report features, past price data and moving averages as our feature set, and Linear Regression, Logistic Regression, and HMM as our models. We show that using HMM, we can get an average precision of 60% in predicting the non-increase of stock prices across 40 stocks.