CoChat
Sign Up
Cited by 55Sustainable Finance and Green BondsCorporate Social Responsibility ReportingImpact of AI and Big Data on Business and Society

AI-driven sustainable finance: Computational tools, ESG metrics, and global implementation

Open access
Elhady, Abdelghafar M., Shohieb, Samaa·2025·Future Business Journal
DOI 10.1186/s43093-025-00610-x
Open this paper in CoChat — free accountOpen PDF

Abstract

Abstract The integration of artificial intelligence (AI) into sustainable finance has emerged as a pivotal innovation for improving environmental, social, and governance (ESG) evaluation. However, ESG data remain fragmented, inconsistent, and prone to methodological opacity—particularly in climate-related investments. This systematic review analyzes 43 peer-reviewed articles and 23 institutional reports to examine whether machine-learning-based ESG scoring models outperform rule-based systems in predicting sustainable investment performance. Following the PRISMA protocol, we applied thematic coding, regional benchmarking, and methodological evaluation across AI–ESG applications. A comparative framework was used to assess AI’s role in ESG integration, predictive analytics, impact measurement, and risk management, with a focus on the climate domain. We also propose and refine the ESG–AI Maturity Index, evaluating AI adoption capacity across data quality, model transparency, and portfolio integration. Findings reveal that AI-enhanced models—particularly those using ensemble learning and sentiment analysis—demonstrate superior performance in forecasting ESG outcomes. However, challenges such as algorithmic bias, regional data gaps, and lack of interpretability remain persistent. The ESG–AI Maturity Index provides a preliminary diagnostic tool for evaluating institutional readiness to adopt AI in ESG scoring. This review contributes by clarifying the performance advantages and limitations of AI-based ESG systems, proposing a framework for maturity assessment, and highlighting urgent policy and technical needs to advance ethical, scalable AI adoption in sustainable finance.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1186/s43093-025-00610-x

Cites

35 of 36 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Organizations with higher AI maturity demonstrate superior ESG forecasting accuracy but still face challenges related to algorithmic bias, regional data gaps, and interpretability.

    “Results indicate that organizations with higher AI maturity demonstrate superior ESG forecasting accuracy but still face challenges related to algorithmic bias, regional data gaps, and interpretability, highlighting governance as a critical condition for scalable AI-driven sustainability decisions.”

    From Artificial Intelligence in Managerial Decision-Making for Sustainable Business Models: A Systematic Literature Review (2026) · cites this paper as [45]

    The Abstract reports better ESG forecasting by AI-enhanced models and persistent algorithmic bias, regional data gaps, and interpretability problems. The Supplementary frameworks section (page not provided) scores firms’ AI maturity as institutional readiness, but does not show that higher-maturity organizations have more accurate ESG forecasts. The ethical-AI framework links maturity to governance readiness, not to demonstrated forecasting accuracy. (LLM, conf=0.87)

    Experimental — accuracy not yet measured

  • AI-enhanced ESG models, particularly ensemble learning and NLP-based sentiment analysis, outperform rule-based approaches in predicting sustainable investment performance, especially in climate-linked portfolios.

    “Elhady and Shohieb [45] analyze 43 peer-reviewed studies and 23 institutional reports to compare machine-learning-based ESG scoring models with traditional rule-based systems. Their findings show that AI-enhanced ESG models-particularly ensemble learning and NLP-based sentiment analysis-outperform rule-based approaches in predicting sustainable investment performance, especially in climate-linked”

    From Artificial Intelligence in Managerial Decision-Making for Sustainable Business Models: A Systematic Literature Review (2026) · cites this paper as [45]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 17

  1. Andre P (2024) The future of AI in banking: revolutionizing financial ser- vices. J Bank Innov 15(2):123-139. https:// doi. org/ 10. 1234/ jbi. 2024. 0152 · DOI
  2. Carl J, Smith R (2023) AI in ESG data integration. J Sustain Finance Invest 13(1):42-56. https:// doi. org/ 10. 1234/ jsfi. 2023. 0131 · DOI
  3. Eccles RG, Serafeim G (2013) The performance frontier: innovating for a sustainable strategy. Harv Bus Rev 91(5):50-60
  4. Eisfeldt AL, Schubert K (2024) Predictive analytics for sustainable invest- ments. J Financ Econ 148(3):789-810. https:// doi. org/ 10. 1016/j. jfine co. 2024. 01. 015 · DOI
  5. Gaddam BK Explainable AI (XAI) for Transparent financial decision-mak- ing: a technical frame-work. J Financ Technol Innov, 12(3):45-67. https:// doi. org/ 10. 1234/ jfti. 2025. 120345 · DOI
  6. Gao L, Wang T, Yu J (2021) AI in investment management: beyond high- frequency trading. IEEE Access 9:125531-125545. https:// doi. org/ 10. 1109/ ACCESS. 2021. 31097 76 · DOI
  7. García-Murillo M, MacInnes I (2023) Artificial intelligence for sustainability: a systematic literature review. Technol Forecast Soc Chang 188:122366. https:// doi. org/ 10. 1016/j. techf ore. 2022. 122366 · DOI
  8. Global Sustainable Investment Alliance (2021) Global Sustainable Invest- ment Review 2020. Available online: https:// www. gsi-allia nce. org/ wp- conte nt/ uploa ds/ 2021/ 08/ GSIR-20201. pdf (accessed on 19 March 2025).
  9. Gupta S, Mittal N, Krishnan S (2019) Artificial intelligence in the invest- ment process: transforming through information advantage. J Econ Bus 104:101766. https:// doi. org/ 10. 1016/j. jecon bus. 2019. 101766 · DOI
  10. Henisz W, Koller T, Nuttall R (2019) Five ways that ESG creates value. McKinsey Quarterly.
  11. Law M, Letts L (2007) Critical Review Form-Qualitative Studies (Version 2.0). McMaster University. Available online: https:// srs-mcmas ter. ca/ wp- conte nt/ uploa ds/ 2015/ 04/ Criti cal-Review-Form-Quali tative-Studi es-Versi on-2-Engli sh. pdf (accessed on 11 March 2025).
  12. Lee J, Youn HL, Poon J, Han SC (2023) Stockemotions: discover investor emotions for finan-cial sentiment analysis and multivariate time series. arXiv preprint, arXiv: 2301. 09279.
  13. Moses O, Mugo R, Mugo J (2020) Leveraging AI for sustainable develop- ment. AI Soc 35:103-110. https:// doi. org/ 10. 1007/ s00146-019-00923-1 · DOI
  14. Nappi-Choulet I, Labussière C (2019) Sustainable investment strategies: the-ory and practice. J Sustain Finance Invest 9(2):177-192. https:// doi. org/ 10. 1080/ 20430 795. 2019. 15812 62 · DOI
  15. Richardson BJ (2013) Socially responsible investing for sustainability: overcoming its incom-plete and conflicting rationales. Trans Environ Law 2(2):311-338. https:// doi. org/ 10. 1017/ S2047 10251 30001 22 · DOI
  16. Sullivan R, Gouldson A (2017) The governance of corporate sustainability: empirical insights into the development, leadership, and implementation of responsible business practice. J Bus Ethics 144(2):279-296. https:// doi. org/ 10. 1007/ s10551-015-2815-0 · DOI
  17. van Tulder R, van Mil E (2020) Principles of sustainable business: frame- works for corporate action on the SDGs. Routledge, Milton Park. https:// doi. org/ 10. 4324/ 97810 03010 663 · DOI

Cited by

Sorted by citations

Related

Authors
Elhady, A. M., & Shohieb, S.
Affiliations
Mansoura University (EG)
Corresponding author
Shohieb, Samaa
ORCID
Venue
Future Business Journal
Publisher
Springer Science and Business Media LLC
Published
2025-08-25
Volume
11
Issue
1
ISSN
  • 2314-7202 (ISSN-L)
  • 2314-7210
DOI
10.1186/s43093-025-00610-x
OpenAlex
W4413489872
Cited by
55
References
34
Citations by year
2026: 51 · 2025: 4
FWCI
49.51
Type
journal article
Language
en
Open access
Licence
Locations
  • Future Business Journal (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Social Sciences › Economics, Econometrics and Finance › Finance › Sustainable Finance and Green Bonds
  • Social Sciences › Business, Management and Accounting › Strategy and Management › Corporate Social Responsibility Reporting
  • Social Sciences › Decision Sciences › Management Science and Operations Research › Impact of AI and Big Data on Business and Society
Keywords
artificial intelligence, sustainable finance, ESG ratings, machine learning, ESG integration, ensemble learning, sentiment analysis, algorithmic bias, model interpretability, ESG data quality

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review