Predicting Companies' ESG Ratings from News Articles Using Multivariate Timeseries Analysis

TL;DR

This paper introduces a deep learning model that predicts companies' ESG ratings from news articles by leveraging multivariate timeseries analysis, providing a practical tool that outperforms existing methods.

Contribution

The study develops a novel approach combining multivariate timeseries and deep learning to forecast ESG ratings from news data, and releases a new dataset of US companies and ratings.

Findings

The approach outperforms state-of-the-art methods in accuracy.

The model effectively supports manual ESG rating analysis.

A new dataset of 3,000 US companies and ratings is provided.

Abstract

Environmental, social and governance (ESG) engagement of companies moved into the focus of public attention over recent years. With the requirements of compulsory reporting being implemented and investors incorporating sustainability in their investment decisions, the demand for transparent and reliable ESG ratings is increasing. However, automatic approaches for forecasting ESG ratings have been quite scarce despite the increasing importance of the topic. In this paper, we build a model to predict ESG ratings from news articles using the combination of multivariate timeseries construction and deep learning techniques. A news dataset for about 3,000 US companies together with their ratings is also created and released for training. Through the experimental evaluation we find out that our approach provides accurate results outperforming the state-of-the-art, and can be used in practice to support a manual determination or analysis of ESG ratings.