Abstract
Prior research primarily focuses on traditional financial evaluation, rarely considering the integration of artificial intelligence as a factor affecting decision efficiency. In this study, the Analytical Hierarchy Process and Propensity Score Matching are applied to increase the resolution of financial analysis down to firm-level observations using the matching algorithm. In addition, evidence reporting on the accuracy and the consistency of both methods was included. A systematic literature search was conducted using Scopus and Web of Science for empirical studies published between 2010 and 2024. Furthermore, to allocate the decision-making priorities, we build our financial decision model as an evaluation network, where a valuation node is a representation of the alternatives, and a link between nodes is an efficiency comparison. Second, by analyzing the weighted outcomes, we design a smart and adaptive decision system that can integrate financial indicators, behavioral factors, and market dynamics. Our experimental results on panel dataset analysis demonstrate that our approach is robust enough when matching covariates, which also verifies the validity and reliability of our framework. The estimation results are more consistent with the benchmarks, the predictions from AHP, and the adjustments from PSM than the original outcomes. It is demonstrated that reliable decision rules can be generated by fusing multi-method outputs using artificial intelligence. For both investors and institutions, AI integration may substantially contribute to the improvement of financial decision-making.