Alphanetv4: Alpha Mining Model

TL;DR

This paper introduces AlphaNetV4, an improved deep learning model for stock prediction that enhances feature extraction, stability, and learning ability, resulting in better performance and increased excess returns in quantitative trading.

Contribution

AlphaNetV4 incorporates longer sequences, Spearman correlation-based dropout, Bi-LSTM, and Transformer components to address previous limitations and improve stock prediction accuracy.

Findings

Reduced loss from 0.5 to 0.1 with model improvements.

Increased annual excess return by 7-10%.

Enhanced stability and efficiency of feature extraction.

Abstract

As AI and deep learning have become hot spots in the 21st century , they are widely used in the current quant market. In 2020, Huatai Securities constructed deep-learning-based AlphaNet for stock feature extraction and price prediction. At present, it has developed to the 3rd version and has formed a great influence in the market. However, the AlphaNet has some problems, such as underfitting caused by short sequence length of feature extraction, insufficient diversity of feature extraction, high complexity, instability of random sampling, which lead to the poor performance. So this paper proposes AlphaNetV4 to solve them. The main contributions of this paper are: 1) Increased the length of the sequence and reduced the step size of the extraction layer to improve the fitting effect; 2) Reduced the relevance of original input; 3) Used Spearman correlation coefficient to design dropout layer instead of random sampling to enhance the stability of feature extraction; 4) Applied Bi-LSTM to enrich the extraction layer, and Transformer to enhance the learning ability of the model. In addition, this paper also uses CNE5 Barra to redesign the fitting target, and optimizes the training process by modifying the training weight and using sharp EarlyStopping. This paper compares the performance between AlphaNetV4 and the previous AlphaNets. It verifies that increasing the sequence length can reduce the loss from 0.5 to 0.3, reducing the correlation of input can reduce the loss to 0.25, using Spearman Dropout can cut the computational complexity without damaging the accuracy, and that Transformer can reduce the loss to less than 0.1. Further, this paper conducts the back test to show that AlphaNetV4 has increased the annual excess return by about 7% - 10%. Finally, this paper provides suggestions on the future development of quant trading.