Stock Trend Prediction Based on ARIMA-LightGBM Hybrid Model

Abstract

As an important part of capital market, stock market is playing an increasingly important role in social and economic development. Stock trend prediction model research has been a popular topic of study among specialists and academics in the fields of economic finance and data analysis. In this paper, Gree Electric Appliance stock is selected as the research object. When the training set and test set are determined, the ARIMA model and LightGBM model, which are commonly used for forecasting, are used to predict the trend of the stock respectively, and then the benefits and drawbacks of these two models in stock trend prediction are analyzed and summarized. On this basis, we propose the ARIMA-LightGBM hybrid model to predict the stock change trend of Gree Electric Appliances stock in six months. In the proposed hybrid model, The ARIMA model was used for the six-month prediction of exogenous variables. Secondly, the LightGBM model is used to model the exogenous variables predicted by the ARIMA model to obtain the predicted stock trend in the next six months. By comparing with the actual Gree Electric Appliances stock price trend, the results show that the prediction accuracy of the proposed ARIMA-LightGBM hybrid model is better than that of the LightGBM model. At the end of the paper, we also put forward some valuable investment strategies based on the forecast results.