Asset Dependence Prediction Utilizing Spatiotemporal Patterns

Abstract Financial assets exhibit dependence structures and knowing the dependencies of the assets can help investors to create a diversified portfolio that can reduce portfolio risk due to the high volatility of the financial market. Since asset dependency changes with time in complex patterns, asset dependency forecasting is an important problem in finance. In this paper, we organize pairwise asset dependencies in an Asset DependencyMatrix (ADM ) and formulate the problem of asset dependency fore-cast as the prediction of future ADM s given a sequence of past ADM s.To exploit the spatiotemporal dependencies between the assets, we propose a novel idea that views ADM sequence as an image sequence, where an ADM corresponds to an image and an entry in the ADM to a pixel. This enables us to apply video prediction methods to capture the spatiotemporal dependencies among the assets. In this paper, we propose a novel Asset Dependency Neural Network (ADNN) to tackle the ADM prediction problem. It adopts ConvLSTM, a highly successful method for video prediction, and the novelty of ADNN is the introduction of a transformation function between ADM and ConvLSTM and an end-to-end approach to learn the transformation function. We conducted extensive experiments to evaluate the performance of ADNN and show that our proposed framework consistently outperforms the baselines on future ADM prediction and portfolio risk reduction tasks.