Stock Price Prediction Based on XGBoost and LightGBM

Stock trading, as a kind of high frequency generally seeks profits in extremely short market changes. And effective stock price forecasting can help investors obtain higher returns. Based on the data set provided by Jane Street, this paper makes use XGBoost model and LightGBM to realize prediction price. Since given training has large amount includes abnormal such missing value, we first carry out feature engineering processing original take mean value so preprocessed that be used modeling. The experimental results show combined better performance than single neural network.