Stock Embeddings: Learning Distributed Representations for Financial Assets
This addresses the lag in modeling asset correlations for financial applications, offering a novel approach inspired by NLP techniques.
The paper tackles the problem of modeling relationships between financial assets by proposing a neural model for stock embeddings that learns from historical returns data, and demonstrates its utility in two real-world financial analytics tasks compared to benchmarks.
Identifying meaningful relationships between the price movements of financial assets is a challenging but important problem in a variety of financial applications. However with recent research, particularly those using machine learning and deep learning techniques, focused mostly on price forecasting, the literature investigating the modelling of asset correlations has lagged somewhat. To address this, inspired by recent successes in natural language processing, we propose a neural model for training stock embeddings, which harnesses the dynamics of historical returns data in order to learn the nuanced relationships that exist between financial assets. We describe our approach in detail and discuss a number of ways that it can be used in the financial domain. Furthermore, we present the evaluation results to demonstrate the utility of this approach, compared to several important benchmarks, in two real-world financial analytics tasks.