Stock Price Prediction Based on XGBoost and LightGBM

Stock trading, as a kind of high frequency trading, 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 of XGBoost model and LightGBM model to realize the prediction of stock price. Since the given training set has a large amount of data and includes abnormal data such as missing value, we first carry out feature engineering processing on the original data and take the mean value of the missing value, so as to obtain the preprocessed data that can be used in modeling. The experimental results show that the combined model of XGBoost and LightGBM has better prediction performance than the single model and neural network.