Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM69292
Volume:
10 |
11 |
Nov 2026
Pages:
1-9
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.

Department of Artificial Intelligence and Data Science
East West Institute of Technology

Department of Artificial Intelligence and Data Science
East West Institute of Technology

Department of Artificial Intelligence and Data Science
East West Institute of Technology

Department of Artificial Intelligence and Data Science
East West Institute of Technology

Department of Artificial Intelligence and Data Science
East West Institute of Technology
Online shoppers frequently encounter the same product listed at different prices across multiple e-commerce platforms, making it difficult to identify the best purchasing option. Traditional price-comparison websites provide only tabular price information and lack intelligent decision support, while large language models may generate inaccurate or unverified recommendations. This paper presents PriceHunt, an AI-powered product comparison and recommendation system that integrates Retrieval-Augmented Generation (RAG) with a multi-retailer product database to deliver accurate, explainable, and data-driven shopping recommendations. The proposed system employs PostgreSQL-based full-text retrieval to identify relevant products and grounds AI-generated responses using retrieved catalogue information. An explainable scoring mechanism evaluates products based on factors such as price competitiveness, customer ratings, discount benefits, and historical pricing trends. The architecture consists of a presentation layer, retrieval layer, data layer, and generation layer, enabling efficient product comparison and natural language interaction. Experimental results demonstrate that the system successfully provides grounded recommendations, reduces the risk of hallucinated product information, and improves user decision-making through transparent explanations and visual comparison dashboards. The proposed framework offers a practical and scalable solution for intelligent e-commerce assistance and serves as a foundation for future enhancements such as live price tracking, hybrid retrieval, and personalized recommendations.
KEYWORDS
This paper presented PriceHunt, an AI-powered product comparison and recommendation framework that integrates Retrieval-Augmented Generation (RAG), multi-retailer price comparison, and explainable recommendation techniques. The proposed system addresses the limitations of traditional price-comparison platforms by combining intelligent product retrieval, grounded recommendation generation, and transparent decision support within a single platform. The system utilizes PostgreSQL-based full-text search to retrieve relevant products from a structured multi-retailer product database and employs a Gemini- based Large Language Model to generate context-aware recommendations. An explainable scoring mechanism evaluates products based on factors such as price competitiveness, customer ratings, discount benefits, and historical pricing trends, enabling users to understand the reasoning behind each recommendation. The integration of conversational AI with interactive comparison dashboards further enhances the user experience and simplifies the decision-making process. Experimental evaluation demonstrated that the proposed framework successfully provides accurate product comparisons, reliable recommendations, and transparent ranking explanations. By grounding AI responses in retrieved product information, the system reduces the risk of hallucinated outputs and improves recommendation trustworthiness. The retrieval mechanism, combined with fallback search strategies, ensures consistent product discovery and robust system performance. Overall, PriceHunt demonstrates the effectiveness of combining Retrieval-Augmented Generation, explainable AI, and multi-retailer price comparison to support informed purchasing decisions. The proposed framework provides a scalable foundation for future intelligent e-commerce applications and highlights the potential of retrieval-grounded AI systems in enhancing online shopping experiences.
[1] P. Lewis, E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal,H. Küttler, M. Lewis, W. Yih, T. Rocktäschel, S. Riedel, and D. Kiela, “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks,” Advances in Neural Information Processing Systems (NeurIPS), vol. 33, pp. 9459–9474, 2020. [2] Z. Ji, N. Lee, R. Frieske, T. Yu, D. Su, Y. Xu, E. Ishii, Y. Bang,A. Madotto, and P. Fung, “Survey of Hallucination in Natural Language Generation,” ACM Computing Surveys, vol. 55, no. 12, pp. 1–38, 2023. [3] V. Karpukhin, B. Oguz, S. Min, P. Lewis, L. Wu, S. Edunov, D. Chen, and W. Yih, “Dense Passage Retrieval for Open-Domain Question Answering,” Proceedings of EMNLP, pp. 6769–6781, 2020. [4] S. Robertson and H. Zaragoza, “The Probabilistic Relevance Framework: BM25 and Beyond,” Foundations and Trends in Information Retrieval, vol. 3, no. 4, pp. 333–389, 2009. [5] PostgreSQL Global Development Group, “PostgreSQL Documentation: Full Text Search,” Available: https://www.postgresql.org/docs/current/textsearch.html [6] R. Doorenbos, O. Etzioni, and D. Weld, “A Scalable Comparison-Shopping Agent for the World Wide Web,” Proceedings of the FirstInternational Conference on Autonomous Agents, pp. 39–48, 1997. [7] Y. Zhang and X. Chen, “Explainable Recommendation: A Survey and New Perspectives,” Foundations and Trends in Information Retrieval, vol. 14, no. 1, pp. 1–101, 2020. [8] Supabase Inc., “Supabase Documentation,” Available: https://supabase.com/docs [9] Google, “Gemini API Documentation,” Available: https://ai.google.dev [10] React Team, “React Documentation,” Available: https://react.dev
Publication Date
11/20/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
0
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...