Explainable Artificial Intelligence in Financial Markets: The Roles of Interpretability and Trust in Shaping Investment Performance

Abstract

This study examined the role of explainable artificial intelligence (XAI) in financial markets by investigating how interpretability and investor trust influenced investment performance. The increasing adoption of artificial intelligence in portfolio management, algorithmic trading, and financial forecasting created concerns regarding transparency, accountability, and user confidence in black-box AI systems. The study employed a quantitative research design using survey data collected from 320 financial analysts, fintech professionals, portfolio managers, institutional investors, and banking experts. A structured questionnaire measured interpretability, investor trust, explainable AI transparency, and investment performance using a five-point Likert scale. Statistical analysis was conducted through SPSS using descriptive statistics, correlation analysis, and regression analysis. The findings revealed strong positive relationships between interpretability and investor trust (r = .742, p < 0.01), explainable AI transparency and investment performance (r = .768, p < 0.01), and investor trust and investment performance (r = .731, p < 0.01). Regression analysis demonstrated that interpretability significantly influenced investment performance (β = 0.41, p = 0.000), while investor trust also exerted a significant positive effect on investment performance (β = 0.46, p = 0.000). The model explained 67.9% of the variation in investment performance (R² = 0.679). The study concluded that explainable artificial intelligence improved transparency, strengthened investor confidence, enhanced financial decision-making, and supported sustainable investment performance within modern financial markets.