SETN: Stock Embedding Enhanced with Textual and Network Information

TL;DR

This paper introduces SETN, a novel stock embedding method that combines textual data and network information using advanced neural models, improving performance in financial tasks like fund creation.

Contribution

The study presents a new stock embedding approach integrating textual and network data with transformer and graph neural networks, enhancing application outcomes.

Findings

SETN outperforms baseline methods in company information extraction.

Stock embeddings from SETN better facilitate thematic fund creation.

The approach demonstrates improved performance in wealth management tasks.

Abstract

Stock embedding is a method for vector representation of stocks. There is a growing demand for vector representations of stock, i.e., stock embedding, in wealth management sectors, and the method has been applied to various tasks such as stock price prediction, portfolio optimization, and similar fund identifications. Stock embeddings have the advantage of enabling the quantification of relative relationships between stocks, and they can extract useful information from unstructured data such as text and network data. In this study, we propose stock embedding enhanced with textual and network information (SETN) using a domain-adaptive pre-trained transformer-based model to embed textual information and a graph neural network model to grasp network information. We evaluate the performance of our proposed model on related company information extraction tasks. We also demonstrate that stock embeddings obtained from the proposed model perform better in creating thematic funds than those obtained from baseline methods, providing a promising pathway for various applications in the wealth management industry.