Optimization of investment strategies through machine learning

Abstract

The main objective of this research is to develop a sustainable stock quantitative investing model based on Machine Learning and Economic Value-Added techniques for optimizing investment strategies. Quantitative stock selection and algorithmic trading are the two features of the model. Principal component analysis and economic value-added criteria are used in quantitative stock model for efficiently stocks selection, which may repeatedly select valuable stocks. Machine learning techniques such as Moving Average Convergence, Stochastic Indicators and Long-Short Term Memory are used in algorithmic trading. One of the first attempts, the Economic Value-Added indicators are used to appraise stocks in this study. Furthermore, the application of EVA in stock selection is exposed. Illustration of the proposed model has been done on United States stock market and finding shows that Long-Short Term Memory (LSTM) networks can more accurately forecast future stock values. The proposed strategy is feasible in all market situations, with a return that is significantly larger than the market return. As a result, the proposed approach can not only assist the market in returning to rational investing, but also assist investors in obtaining significant returns that are both realistic and valuable.

Keywords

• Algorithmic trading
• Economic value-added strategy
• Long-short term memory
• Machine learning
• Moving average convergence
• Quantitative stock investment