Stock Embeddings: Learning Distributed Representations for Financial Assets

TL;DR

This paper introduces a neural model for learning stock embeddings from historical returns, capturing nuanced asset relationships to improve financial analytics tasks, inspired by natural language processing techniques.

Contribution

It presents a novel neural approach for training stock embeddings that effectively model asset correlations, filling a gap in financial relationship modeling.

Findings

Outperforms key benchmarks in asset relationship tasks

Demonstrates utility in real-world financial analytics

Provides a detailed methodology for embedding training

Abstract

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.