Visual Attention Model for Cross-sectional Stock Return Prediction and End-to-End Multimodal Market Representation Learning.

Technical and fundamental analysis are traditional tools used to analyze individual stocks; however, the finance literature has shown that the price movement of each individual stock correlates heavily with other stocks, especially those within the same sector. In this paper we propose a general purpose representation that incorporates fundamental and technical indicators and relationships between individual stocks. We treat the daily stock as a market where rows (grouped by sector) represent individual stocks and columns represent indicators. We apply a convolutional neural network over this image to build features in a hierarchical way. We use a recurrent neural network, with an attention mechanism over the feature maps, to model temporal dynamics in the market. We show that our proposed model outperforms strong baselines in both short-term and long-term stock return prediction tasks. We also show another use for our image: to construct concise and dense embeddings suitable for downstream prediction tasks.