Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{204251,
        author = {Subramanya G M and Dr. Merin Meelet},
        title = {A Hybrid Recommendation Framework for Item Proposal in Enterprise Service Management Systems: A Survey},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {1542-1551},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204251},
        abstract = {Intelligent item proposal is becoming an indispensi- ble capability in modern Enterprise Service Management (ESM) platforms. When agents create service orders, they must rapidly select the right parts, labor units, or service bundles from large and frequently evolving catalogs while simultaniously accounting for customer context, asset history, and organisational policy. This decision is consequential: an incorrect or incomplete selection leads to rework, customer dissatisfaction, and increased resolu- tion time. Despite growing interest in recommendation systems for enterprise use, existing approaches remain fragmented, ad- dressing individual signals such as historical order data, curated product lists, and machine learning inference in isolation. Very few works offer a unified view of how these signals can be combined in a governance-aware, explainable, and operationally robust manner.
This paper presents a structured survey and synthesis of recommendation methods relevant to item proposal in enterprise service workflows. We examine four core proposal source families – AI-based contextual inference, historical order retreival, prod- uct list constraints, and quotation memory signals – alongside a fifth extension channel for external rule or partner hooks. We introduce a generalized hybrid reference architecture that fuses outputs from all signal sources and evaluate the trade-offs across recommendation accuracy, latency, interpretability, and policy compliance. Our comparative analysis of representative studies reveals consistent gaps in confidence calibration, benchmark standardisation, and user-centric evaluation methodology. The survey concludes with a research agenda that adresses these open problems and positions the hybrid model as a practical default for enterprise deployment.},
        keywords = {enterprise service management, hybrid recom- mendation, item proposal, decision support systems, case-based reasoning, explainable AI, collaborative filtering, survey},
        month = {June},
        }