Bridging Data‐Driven Intelligence and Expert‐Driven Knowledge: A Systematic Review of the RF ‐ AHP Hybrid Paradigm

As decision‐making environments become increasingly complex, the development of human–machine collaborative systems that integrate data‐driven intelligence with expert knowledge has attracted considerable scholarly interest. Although the hybrid paradigm combining Random Forest (RF) and Analytic Hierarchy Process (AHP) presents a robust solution, a systematic review utilizing knowledge mapping remains absent in the literature. To address this deficiency, this study employs a combined bibliometric and content analysis to provide a comprehensive review of the RF‐AHP hybrid paradigm. At the macro level, the analysis reveals the distributional characteristics of global collaboration networks and identifies core research hotspots. Theoretically, the study elucidates the synergistic mechanisms between RF and AHP in terms of cognitive logic, decision robustness, and system adaptability. In practical terms, the integration of RF and AHP is categorized into five distinct approaches: result‐level fusion, mutual verification and supplementation, procedural relay, model‐level embedding, and meta‐decision selection. Each approach is analyzed with respect to specific decision‐making scenarios. The review concludes by summarizing current core challenges and outlining future research directions. This work ultimately provides a reusable technical framework and practical reference for addressing scientific problems that require integrating multi‐source data and expert experience, thereby promoting further exploration and development of this paradigm.