Financial statement fraud remains a substantial risk in environments marked by weak regulatory oversight and information asymmetry. This study develops a decision-centric framework that integrates machine learning, explainable artificial intelligence, and decision curve analysis to improve fraud detection under severe class imbalance. Using 969 firm-year observations from 132 Mongolian firms (2013–2024), we evaluate 21 financial ratios with models including Random Forest, XGBoost, LightGBM, MLP, TabNet, and a Stacking Ensemble trained with SMOTE and class-weighted learning. Performance was assessed using PR-AUC, F1-score, Recall, and DeLong-based significance testing. The Stacking Ensemble achieved the strongest results (PR-AUC = 0.93; F1 = 0.83), outperforming both classical and modern baseline models. Interpretability analyses (SHAP, LIME, and counterfactual explanations) consistently identified leverage, profitability, and liquidity indicators as dominant drivers of fraud risk, supported by a SHAP Stability Index of 0.87. Decision curve analysis showed that calibrated thresholds improved decision efficiency by 7–9% and reduced over-audit costs by 3–4%, while an audit cost simulation estimated annual savings of 80–100 million MNT. Overall, the proposed ML–XAI–DCA framework offers a transparent, interpretable, and cost-efficient approach for enhancing fraud detection in emerging-market contexts with limited textual disclosures.

Finding out how financial influences impact investors' decisions when they trade on the Mongolian Stock Exchange is the aim of the study. It also seeks to determine the behavioral characteristics of investors and evaluate the ways in which irrational conduct complicates the process of making investment decisions. We carried out the study in two ways in order to accomplish the aforementioned goals. They are: Questionnaire study: To ascertain how influencers affect investors' choices, the study gathered primary data from 80 investors in total. The findings indicate that investors' well-being is positively impacted by financial influencers, and that stock market participation is positively impacted by influencers and investor well-being. For a total of 3088 days, from 2013.01.01 to 2024.10.31, the price data of "Tavan Tolgoi" JSC, listed on the Mongolian Stock Exchange, as well as 254 tweets from official sources and social influencers that might have an impact on it (positive 61.0%, negative 39.0%), were evaluated using the autoregressive model. According to some of the study's findings, information about the company's earnings, dividends, and financial standing has a greater influence on price than information on the coal markets in China and Mongolia. Additionally, it was discovered that although social influencers' positive information had a favorable effect on the price that day and the day next, their negative information had a significant negative effect. JEL ангилал: E62, C11, C40