CoChat
Sign Up
Cited by 29Corporate Social Responsibility ReportingCorporate Governance and Financial ManagementCorporate Identity and Reputation

Explainable artificial intelligence modeling for corporate social responsibility and financial performance

Open access
Lachuer, Julien, Jabeur, Sami Ben·2022·Journal of Asset Management
DOI 10.1057/s41260-022-00291-zPMC PMC9526215
Open this paper in CoChat — free accountOpen PDF

Abstract

In this paper, we examine the relation between corporate social responsibility and corporate financial performance in a bullish market. Previous studies have heterogeneous results, mainly due to differences in the samples and statistical approaches used. To resolve these issues, we use an innovative approach through explainable artificial intelligence (XAI). To reflect the recent expansions of CSR practices, we propose a longitudinal analysis of the US market from 2014–2019. We find that in a bullish market, CSR is negatively related to financial market performance. Through the use of XAI, we show that CSR exclusively improves the financial performance of the most sustainable companies. We also highlight the existence of thresholds that modify the relation between the level of CSR and our financial variables.

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 · 10.1057/s41260-022-00291-z

Cites

47 of 47 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?

  • XAI is especially suitable for regulatory compliance, investor communication, and board-level decision-making.

    “This makes XAI especially suitable for regulatory compliance, investor communication, and board-level decision-making.”

    From Artificial Intelligence in Managerial Decision-Making for Sustainable Business Models: A Systematic Literature Review (2026) · cites this paper as [50]

    The Introduction and the Methodology – explainable artificial intelligence (XAI) section say XAI exposes how black-box models make decisions and helps users understand their predictions. Those passages support the general value of explainability, but they do not establish that XAI is especially suitable for regulatory compliance, investor communication, or board-level decision-making; searches for those applications found no supporting passage. (LLM, conf=0.80)

    Experimental — accuracy not yet measured

  • In ESG decision-making, XAI directly addresses the need for trust, accountability, and auditability.

    “In ESG decision-making, XAI directly addresses the need for trust, accountability, and auditability.”

    From Artificial Intelligence in Managerial Decision-Making for Sustainable Business Models: A Systematic Literature Review (2026) · cites this paper as [50]

    The Introduction and the XAI methodology section (pages unavailable) say XAI exposes black-box models’ behavior and decision-making processes, helping people understand their predictions in a CSR/ESG-related analysis. They do not say that XAI directly meets needs for trust, accountability, or auditability in ESG decision-making. (LLM, conf=0.83)

    Experimental — accuracy not yet measured

  • Explainable models improve interpretability without fully sacrificing analytical rigor, thereby strengthening the governance pillar of ESG.

    “Lachuer and Ben Jabeur [50] also show that explainable models improve interpretability without fully sacrificing analytical rigor, thereby strengthening the governance pillar of ESG.”

    From Artificial Intelligence in Managerial Decision-Making for Sustainable Business Models: A Systematic Literature Review (2026) · cites this paper as [50]

    The Methodology—explainable artificial intelligence (XAI) section (page unavailable) says XAI explains otherwise difficult-to-understand, highly accurate models, supporting the interpretability and analytical-rigor portion of the paraphrase. The Results and discussion section (page unavailable) examines governance as a factor associated with CSR, but does not say that explainable models strengthen the governance pillar of ESG. (LLM, conf=0.85)

    Experimental — accuracy not yet measured

  • XAI enables the identification of threshold effects, non-linearities, and decision rules that govern the relationship between CSR performance and financial outcomes.

    “By integrating explainability techniques with ML models, XAI enables the identification of threshold effects, non-linearities, and decision rules that govern the relationship between CSR performance and financial outcomes.”

    From Artificial Intelligence in Managerial Decision-Making for Sustainable Business Models: A Systematic Literature Review (2026) · cites this paper as [50]

  • The main trade-off of XAI identified in the literature is reduced predictive performance and higher implementation complexity compared to deep learning models.

    “The main trade-off identified in the literature is reduced predictive performance and higher implementation complexity compared to deep learning models.”

    From Artificial Intelligence in Managerial Decision-Making for Sustainable Business Models: A Systematic Literature Review (2026) · cites this paper as [50]

    The Methodology–XAI section says that highly accurate machine-learning models can be difficult to explain and that XAI helps explain them. Searches for predictive-performance and implementation-complexity trade-offs found no passage comparing XAI with deep learning on either measure. (LLM, conf=0.73)

    Experimental — accuracy not yet measured

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: 1

  1. Gentry Richard J Shen Wei The relationship between accounting and market measures of firm financial performance: How strong is it? Journal of Managerial Issues 2010 22 4 514 530

Cited by

Sorted by citations

Related

Authors
Lachuer, J., & Jabeur, S. B.
Affiliations
  • Centre National de la Recherche Scientifique (FR)
  • Université catholique de lyon (FR)
Corresponding author
Lachuer, Julien
ORCID
Venue
Journal of Asset Management
Publisher
Springer Science and Business Media LLC
Published
2022-10-01
Volume
23
Issue
7
Pages
619-630
ISSN
  • 1470-8272 (ISSN-L)
  • 1479-179X
DOI
10.1057/s41260-022-00291-z
PMC
PMC9526215
OpenAlex
W4298620471
Cited by
29
References
46
Citations by year
2026: 12 · 2025: 8 · 2024: 6 · 2023: 3
FWCI
3.17
Type
journal article
Language
en
Open access
Licence
Locations
  • Journal of Asset Management (publishedVersion)
  • PubMed Central (publishedVersion)
  • HAL (submittedVersion)
  • RePEc: Research Papers in Economics (submittedVersion)
Funders
Université de Rennes 1
Topics
  • Social Sciences › Business, Management and Accounting › Strategy and Management › Corporate Social Responsibility Reporting
  • Social Sciences › Business, Management and Accounting › Strategy and Management › Corporate Governance and Financial Management
  • Social Sciences › Business, Management and Accounting › Strategy and Management › Corporate Identity and Reputation
Keywords
corporate social responsibility, corporate financial performance, explainable AI, sustainable companies, stock market performance, US stock market

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