Opening the Black Box of Financial AI with CLEAR-Trade: A CLass-Enhanced Attentive Response Approach for Explaining and Visualizing Deep Learning-Driven Stock Market Prediction

Deep learning has been shown to outperform traditional machine learning algorithms across a wide range of problem domains. However, current deep learning algorithms have been criticized as uninterpretable "black-boxes" which cannot explain their decision making processes. This is a major shortcoming that prevents the widespread application of deep learning to domains with regulatory processes such as finance. As such, industries such as finance have to rely on traditional models like decision trees that are much more interpretable but less effective than deep learning for complex problems. In this paper, we propose CLEAR-Trade, a novel financial AI visualization framework for deep learning-driven stock market prediction that mitigates the interpretability issue of deep learning methods. In particular, CLEAR-Trade provides a effective way to visualize and explain decisions made by deep stock market prediction models. We show the efficacy of CLEAR-Trade in enhancing the interpretability of stock market prediction by conducting experiments based on S&P 500 stock index prediction. The results demonstrate that CLEAR-Trade can provide significant insight into the decision-making process of deep learning-driven financial models, particularly for regulatory processes, thus improving their potential uptake in the financial industry.

Products of Hidden Markov Models: It Takes N>1 to Tango

Products of Hidden Markov Models(PoHMMs) are an interesting class of generative models which have received little attention since their introduction. This maybe in part due to their more computationally expensive gradient-based learning algorithm,and the intractability of computing the log likelihood of sequences under the model. In this paper, we demonstrate how the partition function can be estimated reliably via Annealed Importance Sampling. We perform experiments using contrastive divergence learning on rainfall data and data captured from pairs of people dancing. Our results suggest that advances in learning and evaluation for undirected graphical models and recent increases in available computing power make PoHMMs worth considering for complex time-series modeling tasks.