Automatic Financial Feature Construction
This work addresses the need for better feature construction in finance, but it is incremental as it builds upon existing genetic programming methods.
The paper tackles the problem of automatic financial feature construction by proposing a neural network-based framework called alpha discovery neural network (ADNN), which replaces genetic programming with pre-training to produce more diversified and higher informative features, and it further improves the performance of features constructed by GP.
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.