Answers are grounded in this paper and cite their sources.
Demonstrates improved financial forecasting in economic decision-making, suggesting enhanced accuracy.
Effective economic decision needs accurate financial forecasting and risk assessment, which is crucial to ensure economic stability. The objective of this paper is to combine Explainable Artificial Intelligence (XAI) with Statistical Process Control (SPS) in order to improve financial modeling. Precise analysis of financial time series data is performed via Linear Regression, Random Forest Regressor, and eXtreme Gradient Boosting Regressor, wherein the various measures of accuracy of all three techniques are assessed by evaluating Mean Absolute Error, Mean Squared Error, Root Mean Squared Error, and R² Score. In an effort to enhance explainability, SHapley Additive exPlanations and Local Interpretable Model Agnostic Explanation algorithms are adopted to interpret model results and assess the fundamental determinants of the financial outcome. SPS charts, including Shewhart, Cumulative Sum, and Exponentially Weighted Moving Average, are employed to track financial trends and identify anomalies in risk fluctuations. Additionally, hypothesis testing is performed to compare model predictions with actual financial indices. A calculus-based analysis explores derivative-based rate changes and integral-based cumulative trends in financial risk prediction. A comparative analysis of XAI techniques is presented, providing insights into model performance. The results indicate that collaborative methods such as Random Forest and eXtreme Gradient Boosting surpass traditional regression approaches, while SPC and XAI enhance financial risk detection and improve the transparency of decision-making. This study highlights the importance of integrating XAI and SPC to achieve effective, interpretable, and data-driven financial forecasting.
No takes yet. Share an insight, caveat, or question.
Puranik et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: