Deep Learning Stock Volatility with Google Domestic Trends

2015/12/15 by Ruoxuan Xiong, Eric Nichols, Xiong, Ruoxuan +3 · 2 citations
Decision Sciences · Economics, Econometrics and Finance · #Stock Market Forecasting Methods #Complex Systems and Time Series Analysis #Market Dynamics and Volatility

paper · pdf · doi:10.48550/arxiv.1512.04916

Abstract

We have applied a Long Short-Term Memory neural network to model S&P 500 volatility, incorporating Google domestic trends as indicators of the public mood and macroeconomic factors. In a held-out test set, our Long Short-Term Memory model gives a mean absolute percentage error of 24.2%, outperforming linear Ridge/Lasso and autoregressive GARCH benchmarks by at least 31%. This evaluation is based on an optimal observation and normalization scheme which maximizes the mutual information between domestic trends and daily volatility in the training set. Our preliminary investigation shows strong promise for better predicting stock behavior via deep learning and neural network models.

Citations

• Testing for unit roots in autoregressive-moving average models of unknown order
• On the Estimation of Security Price Volatilities from Historical Data

Cited by

• Application of Deep Neural Networks to assess corporate Credit Rating
• Financial Time Series Prediction Using Deep Learning

Related

• Volatility forecasting using Deep Learning and sentiment analysis
• Advanced Stock Market Prediction Using Long Short-Term Memory Networks: A Comprehensive Deep Learning Framework
• Predicting Stock Market Trends Using Machine Learning and Deep Learning Algorithms Via Continuous and Binary Data; a Comparative Analysis
• An Evaluation of Deep Learning Models for Stock Market Trend Prediction
• Multimodal deep learning for short-term stock volatility prediction