In this chapter, we develop a neural network (NN) model for stock classification using input features derived from widely known momentum factors and apply it to two problems; long-short strategy construction and stock recommendation. Empirical findings suggest that our model can create a long-short portfolio generating a significant profit and high Sharpe ratio (SR). It is also effective in making buy/hold/sell recommendation, although the evidence is less strong. Our model seems to be more powerful for cross-sectional prediction while having a limited ability for time-series prediction. We also find that economic performance of a model can be very different from its statistical performance. This signifies the importance of choosing an objective function that reflects economic performance and evaluating models from both statistical and economic perspectives.

Chapter Contents:

• 19.1 Introduction
• 19.2 Momentum and stock-return predictability
• 19.2.1 Momentum effects
• 19.2.2 Jegadeesh–Titman (JT) momentum strategy
• 19.2.3 52-Week high (52WH) momentum strategy
• 19.3 Machine-learning-based momentum strategy
• 19.3.1 Feature engineering
• 19.3.2 Labelling
• 19.3.3 Training and testing
• 19.3.3.1 Data sample
• 19.3.3.2 Learning the model
• 19.3.4 Portfolio formation
• 19.4 Empirical results
• 19.4.1 Classification accuracy
• 19.4.2 Portfolio performance
• 19.5 Machine-learning-based stock recommendation
• 19.5.1 Design of the model
• 19.5.2 Empirical results
• 19.6 Conclusion
• References

Inspec keywords: investment; time series; pattern classification; stock markets; learning (artificial intelligence); neural nets

Other keywords: long-short portfolio; long-short strategy construction; time-series prediction; evaluating models; input features; stock classification; neural network model; high Sharpe ratio; momentum factors; economic performance; stock recommendation; empirical findings; cross-sectional prediction; significant profit; buy/hold/sell recommendation

Subjects: Financial computing; Neural computing techniques; Other topics in statistics; Knowledge engineering techniques; Data handling techniques