Larysa Sergiienko

In today’s fast-paced business environment, integrating sustainability into financial decision-making has been a key driver of change. As stakeholders increasingly demand greater corporate transparency and accountability, regulatory bodies have stepped in to ensure that sustainability reporting is standardized and robust. This paper aims to establish the relationship between the sustainability-related disclosure rules and the dynamic indicators of the financial market. The object of the study is 74 countries of the world, which are grouped into developed and developing countries. The time period is 2021, for the stock market capitalization indicators – 2020, as the most recent years with available data. The research methods are normality tests (Shapiro-Wilk and Shapiro-Francia test), comparison methods (Student’s t-test and Mann-Whitney U test, regression analysis with dummy variables), linear and non-linear correlation and regression analysis (logarithmic, polynomial). The results obtained confirmed that the sustainability-related disclosure rules are higher in developed countries than in developing ones. At the same time, in developed countries, the growth of such requirements affects the increase in stock price volatility, stock market capitalization, foreign direct and portfolio investments. For developing countries, there is also an increase in the stock market capitalization, portfolio investments and the volume of stock trading. Recognizing these trends can benefit both financial market regulators and participants to encourage the formation of a transparent and efficient financial market, thereby mitigating the problems associated with information asymmetry.

Type of the article: Research Article

Abstract
This study evaluates whether explainable machine-learning models can provide reliable and operationally interpretable short-horizon delinquency monitoring in U.S. auto lease securitization panels. Six public SEC ABS-EE trust-family panels were harmonized at the contract-month level. The primary outcome is one-month-ahead incident escalation to 30 or more days past due among contracts below 30 days past due at the feature month. Fully tuned penalized logistic regression (M1), unconstrained gradient boosting (M2), and governance-constrained gradient boosting (M3/X-LEASE) were assessed through chronological development, calibration, locked out-of-time testing, contract-held-out validation, six leave-one-issuer-out experiments, and later temporal evaluation. The locked test comprised 198,301 observations and 768 events. M2 produced the strongest discrimination (AUC-ROC 0.8151; PR-AUC 0.0269), while M3 exceeded the logistic benchmark by PR-AUC but did not outperform M2. At an exact 1% review capacity, each model generated 1,984 alerts; M2 detected 104 events, compared with 61 for M3, so the hypothesized recall advantage of X-LEASE was not supported. Full-sample TreeSHAP analysis showed stable feature rankings across tested issuers, later periods, and contract-level resampling. M3 relied more heavily on credit score and issuer controls and had a more concentrated explanation structure, but this does not establish superior auditability or fairness. The results support human-reviewed early-warning monitoring within the tested securitization panels, not lifetime default prediction, automated adverse decisions, or universal transferability.

Acknowledgments
The authors acknowledge the public availability of SEC EDGAR Form ABS-EE, Exhibit 102 asset-level data. No individuals or institutions outside the author team provided paid analytical, editorial, or funding support for this manuscript.