Long Short-Term Memory Networks for CSI300 Volatility Prediction with Baidu Search Volume
This work addresses volatility prediction for financial markets, but it is incremental as it applies an existing LSTM method to a new data source (search volume) without major methodological innovation.
The authors tackled the problem of predicting CSI300 volatility by using Baidu search volume data as indicators of public mood and macroeconomic factors, and found that their Long Short-Term Memory neural network model was more accurate than the benchmark GARCH model.
Intense volatility in financial markets affect humans worldwide. Therefore, relatively accurate prediction of volatility is critical. We suggest that massive data sources resulting from human interaction with the Internet may offer a new perspective on the behavior of market participants in periods of large market movements. First we select 28 key words, which are related to finance as indicators of the public mood and macroeconomic factors. Then those 28 words of the daily search volume based on Baidu index are collected manually, from June 1, 2006 to October 29, 2017. We apply a Long Short-Term Memory neural network to forecast CSI300 volatility using those search volume data. Compared to the benchmark GARCH model, our forecast is more accurate, which demonstrates the effectiveness of the LSTM neural network in volatility forecasting.