Stock-Price Forecasting Based on XGBoost and LSTM

Using time-series data analysis for stock-price forecasting (SPF) is complex and challenging because many factors can influence stock prices (e.g., inflation, seasonality, economic policy, societal behaviors). Such be analyzed over time SPF. Machine learning deep have been shown to obtain better forecasts of than traditional approaches. This study, therefore, proposed a method enhance the performance an SPF system based on advanced machine First, we applied extreme gradient boosting as feature-selection technique extract important features from high-dimensional remove redundant features. Then, fed selected into long short-term memory (LSTM) network forecast prices. The LSTM was used reflect temporal nature input series fully exploit future contextual information. structure enables this capture more stochasticity within price. does not change when or Forex data. Experimental results dataset covering 2008–2018 showed that our approach outperformed baseline autoregressive integrated moving average with regard mean absolute error, squared root-mean-square error.