Automatic Financial Feature Construction

TL;DR

This paper introduces ADNN, a neural network-based framework for automatic financial feature construction that outperforms genetic programming by producing more diverse, informative features and serving as a data augmentation tool.

Contribution

The paper proposes a novel neural network framework, ADNN, replacing genetic programming for financial feature construction, leveraging domain knowledge and pre-training for improved results.

Findings

ADNN produces more diversified features than GP.

ADNN generates higher informative features.

ADNN enhances GP performance as a data augmentation method.

Abstract

In automatic financial feature construction task, the state-of-the-art technic leverages reverse polish expression to represent the features, then use genetic programming (GP) to conduct its evolution process. In this paper, we propose a new framework based on neural network, alpha discovery neural network (ADNN). In this work, we made several contributions. Firstly, in this task, we make full use of neural network overwhelming advantage in feature extraction to construct highly informative features. Secondly, we use domain knowledge to design the object function, batch size, and sampling rules. Thirdly, we use pre-training to replace the GP evolution process. According to neural network universal approximation theorem, pre-training can conduct a more effective and explainable evolution process. Experiment shows that ADNN can remarkably produce more diversified and higher informative features than GP. Besides, ADNN can serve as a data augmentation algorithm. It further improves the the performance of financial features constructed by GP.