Deep learning for event-driven stock prediction

TLDR

The study proposes a deep learning approach for event‑driven stock market prediction. The method extracts events from news, encodes them as dense vectors via a neural tensor network, and feeds them into a deep convolutional neural network that captures short‑ and long‑term event effects on stock prices. Experiments demonstrate nearly 6% improvement over state‑of‑the‑art baselines on S&P 500 and individual stock predictions, and simulations show higher profitability than prior systems trained on historical data.

Abstract

We propose a deep learning method for event-driven stock market prediction. First, events are extracted from news text, and represented as dense vectors, trained using a novel neural tensor network. Second, a deep convolutional neural network is used to model both short-term and long-term influences of events on stock price movements. Experimental results show that our model can achieve nearly 6% improvements on S&P 500 index prediction and individual stock prediction, respectively, compared to state-of-the-art baseline methods. In addition, market simulation results show that our system is more capable of making profits than previously reported systems trained on S&P 500 stock historical data.