EURO-Online login
- New to EURO? Create an account
- I forgot my username and/or my password.
- Help with cookies
(important for IE8 users)
1220. Generative South African ESG indexes and multi-target neural complexity in return prediction
Invited abstract in session TD-18: AI and ESG for the small economy SDG agenda (EWG-ORD Workshop 2), stream OR for Development and Developing Countries.
Tuesday, 14:30-16:00Room: 42 (building: 116)
Authors (first author is the speaker)
| 1. | Gordon Dash
|
| Finance and Decision Sciences, University of Rhode Island | |
| 2. | Nina Kajiji
|
| Computer Science and Statistics, University of Rhode Island, and The NKD Group, Inc. | |
| 3. | Bruno Kamdem
|
| Department of Business Management, SUNY Farmingdale State College, School of Business |
Abstract
A company's dedication to environmental, social, and governance principles (ESG) has led to an interest in developing and evaluating firm-level ESG scores. Despite the considerable interest in assessing firm-level scores, investment analytics lack standardized country-specific ESG indexes to comprehensively represent sustainability while facilitating asset predictability. This deficiency is noticeable in the emerging BRICS capital markets (i.e., Brazil, Russia, India, China, and South Africa (SA)). Focusing on SA, the primary objective of this study is to formulate an innovative algorithmic framework to identify distinct dynamic ESG factors capable of assessing sustainability risk in securities traded on the Johannesburg Stock Exchange (JSE). The proposed alternative data procedure utilizes asset returns in the exploratory factor analysis to generate maximum validity factor scores to formulate JSE-specific sustainability factors. The effectiveness of these factors is assessed through a machine-learning model operating within a complex information space that considers the interconnections of valuation signals. Employing an explainable AI technique (XAI), we determine that the newly created S-factor emerges as the primary feature for explaining next-period returns. Following closely behind is the E factor, the SA volatility index, and a precious metals factor. XAI reveals that these factors excel at discerning the varying emphasis South African firms place on their ESG signals.
Keywords
- Sustainable Development
- Financial Modelling
- Artificial Intelligence
Status: accepted
Back to the list of papers