Stock selection for machine learning

Abstract

The application of machine learning for stock prediction is attracting a lot of attention in recent years. A large amount of research has been conducted in this area and multiple existing results have shown that machine learning methods could be successfully used toward stock predicting using stocks’ historical data. Most of these existing approaches have focused on short-term prediction using stocks’ historical price and technical indicators. In this thesis, we prepared 22 years’ worth of stock quarterly financial data and investigated three machine learning algorithms: Feed-forward Neural Network (FNN), Random Forest (RF) and Adaptive Neural Fuzzy Inference System (ANFIS) for stock prediction based on fundamental analysis. In addition, we applied RF-based feature selection and bootstrap aggregation in order to improve model performance and aggregate predictions from different models. Our results show that RF model achieves the best prediction results, and feature selection is able to improve test performance of FNN and ANFIS. Moreover, the aggregated model outperforms all baseline models as well as the benchmark DJIA index by an acceptable margin for the test period. Our findings demonstrate that machine learning models could be used to aid fundamental analysts with decision making regarding to stock investment. In recent years, a variety of research fields, including finance, have begun to place great emphasis on machine learning techniques because they exhibit broad abilities to simulate more complicated problems. In contrast to the traditional linear regression scheme that is usually used to describe the relationship between the stock forward return and company characteristics, the field of finance has experienced the rapid development of tree-based algorithms and neural network paradigms when illustrating complex stock dynamics. These nonlinear methods have proved to be effective in predicting stock prices and selecting stocks that can outperform the general market. This article implements and evaluates the robustness of the random forest (RF) model in the context of the stock selection strategy. The model is trained for stocks in the Chinese stock market, and two types of feature spaces, fundamental/technical feature space and pure momentum feature space, are adopted to forecast the price trend in the long run and the short run, respectively. It is evidenced that both feature paradigms have led to remarkable excess returns during the past five out-of-sample period years, with the Sharpe ratios calculated to be 2.75 and 5 for the portfolio net value of the multi-factor space strategy and momentum space strategy, respectively. Although the excess return has weakened 3 in recent years with respect to the multi-factor strategy, our findings point to a less efficient market that is far from equilibrium