Forecasting Asset Dependencies to Reduce Portfolio Risk

Financial assets exhibit dependence structures, i.e., movements of their prices or returns show various correlations. Knowledge assets’ price dependencies can help investors to create a diversified portfolio, aiming reduce portfolio risk due the high volatility financial market. Since asset dependency changes with time in complex patterns, forecast is an essential problem finance. In this paper, we organize pairwise Asset Dependency Matrix (ADM) and formulate predict future ADM given sequence past ADMs. We propose novel idea viewing ADMs as images capture spatial temporal among assets. Inspired by video prediction tasks, develop Neural Network (ADNN) tackle problem. Experiments that our proposed framework consistently outperforms baselines on both reduction tasks.