Risk Management via Anomaly Circumvent: Mnemonic Deep Learning for Midterm Stock Prediction
This addresses the problem of cumulative errors in midterm stock predictions for value investors, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles midterm stock price prediction by proposing Mid-LSTM, a deep neural network that avoids anomalies to reduce cumulative errors, achieving 2-4% accuracy improvement and up to 120.16% annual return in portfolio allocation.
Midterm stock price prediction is crucial for value investments in the stock market. However, most deep learning models are essentially short-term and applying them to midterm predictions encounters large cumulative errors because they cannot avoid anomalies. In this paper, we propose a novel deep neural network Mid-LSTM for midterm stock prediction, which incorporates the market trend as hidden states. First, based on the autoregressive moving average model (ARMA), a midterm ARMA is formulated by taking into consideration both hidden states and the capital asset pricing model. Then, a midterm LSTM-based deep neural network is designed, which consists of three components: LSTM, hidden Markov model and linear regression networks. The proposed Mid-LSTM can avoid anomalies to reduce large prediction errors, and has good explanatory effects on the factors affecting stock prices. Extensive experiments on S&P 500 stocks show that (i) the proposed Mid-LSTM achieves 2-4% improvement in prediction accuracy, and (ii) in portfolio allocation investment, we achieve up to 120.16% annual return and 2.99 average Sharpe ratio.