Alpha Discovery Neural Network, the Special Fountain of Financial Trading Signals

Genetic programming (GP) is the state-of-the-art in financial automated feature construction task. It employs reverse polish expression to represent features and then conducts the evolution process. However, with the development of deep learning, more powerful feature extraction tools are available. This paper proposes Alpha Discovery Neural Network (ADNN), a tailored neural network structure which can automatically construct diversified financial technical indicators based on prior knowledge. We mainly made three contributions. First, we use domain knowledge in quantitative trading to design the sampling rules and object function. Second, pre-training and model pruning has been used to replace genetic programming, because it can conduct more efficient evolution process. Third, the feature extractors in ADNN can be replaced by different feature extractors and produce different functions. The experiment results show that ADNN can construct more informative and diversified features than GP, which can effectively enriches the current factor pool. The fully-connected network and recurrent network are better at extracting information from the financial time series than the convolution neural network. In real practice, features constructed by ADNN can always improve multi-factor strategies' revenue, sharpe ratio, and max draw-down, compared with the investment strategies without these factors.

[1]  Alexandros Karatzoglou,et al.  Parallel Recurrent Neural Network Architectures for Feature-rich Session-based Recommendations , 2016, RecSys.

[2]  Marianthi Markatou,et al.  Text mining for the Vaccine Adverse Event Reporting System: medical text classification using informative feature selection , 2011, J. Am. Medical Informatics Assoc..

[3]  Andreas Radbruch,et al.  Generation of stable monoclonal antibody-producing BCR+ human memory B cells by genetic programming , 2009, Nature Medicine.

[4]  Franklin Allen,et al.  Using genetic algorithms to find technical trading rules , 1999 .

[5]  R.J. Watts,et al.  Mining conference proceedings for corporate technology knowledge management , 2005, A Unifying Discipline for Melting the Boundaries Technology Management:.

[6]  Ferat Sahin,et al.  A survey on feature selection methods , 2014, Comput. Electr. Eng..

[7]  Rongfang Bie,et al.  Automatic facial expression recognition based on a deep convolutional-neural-network structure , 2017, 2017 IEEE 15th International Conference on Software Engineering Research, Management and Applications (SERA).

[8]  Gregory D. Hager,et al.  Temporal Convolutional Networks for Action Segmentation and Detection , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[10]  Hiroshi Motoda,et al.  Feature Extraction, Construction and Selection: A Data Mining Perspective , 1998 .

[11]  T. C. Green,et al.  Crowdsourced Employer Reviews and Stock Returns , 2018, Journal of Financial Economics.

[12]  Maosong Sun,et al.  Enhancing Stock Movement Prediction with Adversarial Training , 2018, IJCAI.

[13]  Krzysztof Krawiec,et al.  Genetic Programming-based Construction of Features for Machine Learning and Knowledge Discovery Tasks , 2002, Genetic Programming and Evolvable Machines.

[14]  Zura Kakushadze,et al.  101 Formulaic Alphas , 2015, 1601.00991.

[15]  Katia Sycara,et al.  The Importance of Simplicity and Validation in Genetic Programming for Data Mining in Financial Data , 1999 .

[16]  Yang Zhong,et al.  Face attribute prediction using off-the-shelf CNN features , 2016, 2016 International Conference on Biometrics (ICB).

[17]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[18]  Michael Carbin,et al.  The Lottery Ticket Hypothesis: Training Pruned Neural Networks , 2018, ArXiv.

[19]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[20]  E. Fama,et al.  Common risk factors in the returns on stocks and bonds , 1993 .

[21]  Sebastián Ventura,et al.  Knowledge Discovery with Genetic Programming for Providing Feedback to Courseware Authors , 2004, User Modeling and User-Adapted Interaction.

[22]  Garrison W. Cottrell,et al.  A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction , 2017, IJCAI.

[23]  Jaydip Sen,et al.  A Robust Predictive Model for Stock Price Prediction Using Deep Learning and Natural Language Processing , 2019, SSRN Electronic Journal.

[24]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Dah-Jye Lee,et al.  A feature construction method for general object recognition , 2013, Pattern Recognit..

[26]  Yong Jiang,et al.  Automatic Financial Feature Construction , 2019 .

[27]  Samuel Marchal,et al.  PRADA: Protecting Against DNN Model Stealing Attacks , 2018, 2019 IEEE European Symposium on Security and Privacy (EuroS&P).

[28]  Jakša Cvitanić,et al.  On portfolio optimization under "drawdown" constraints , 1994 .

[29]  W. Sharpe.  The Sharpe Ratio , 1994 .