A Comparative Research on Stock Selection Strategy based on Machine Learning Models

This paper aims to develop efficient prediction techniques using machine learning models. In this paper, We have extensive access to market trading and technical indicator data, and a sliding window method is used to better capture more time series information. To identify the precise forecasting approach, we employed multiple algorithms like Linear Regression, Random Forest and XGBoost, etc,. After the daily rotation stock selection models were constructed, we use the investing performance indicators such as annualized return, sharpe ratio, and maximum drawdown to evaluate and compare the efficiency of difference models.