Adversarial Learning Networks for FinTech Applications Using Heterogeneous Data Sources

The dynamic property and increasing complexity are the key challenges for modeling financial technology (FinTech) -related applications such as stock markets. Over the years, a lot of inflexible predictive strategies have been proposed for predicting stock price movements that failed to achieve satisfactory results especially when a market crash occurs. To cope with this challenge, we propose a prediction framework based on an adversarial training strategy using reinforcement learning for the said FinTech application. The framework uses a heterogeneous knowledge base, including stock prices, tweets, and global indicators. We propose a modified newton-divided difference polynomial (NDDP) for missing data imputation. The informative patterns representing the intrinsic characteristics of financial markets were extracted using long short-term memory networks (LSTM). The two adversarial networks are heterogeneous data fusion representing market crash (HDFM) Q -learning and confrontational Q -learning network. Both networks are trained in an adversarial fashion to increase the effectiveness of prediction even when the financial market is volatile. The experimental results show the importance of global indicators and the proposed adversarial learning network (ALN) for improving the predictive performance in comparison with the existing state-of-the-art works.