AI - Powered Local Worker & Service Marketplace

Abstract

The rapid expansion of the digital economy has created an urgent demand for platforms that bridge the gap between local service providers and users who need skilled labour on demand. Existing solutions either lack intelligent personalization or fail to provide a truly unified experience covering discovery, communication, and payment in a single interface. This paper presents an AI-powered local worker and service marketplace a full-stack web platform that connects users with verified local workers across a wide range of service categories. The system’s defining innovation is an embedded AI chatbot that functions simultaneously as a query-answering assistant, a rule-based recommendation engine, and a semi-automated booking facilitator. Built on a hybrid architecture combining React.js, Node.js, Supabase (PostgreSQL), Redis, Socket.IO, and Razorpay, the platform delivers real-time communication, location-aware search, and secure payment processing in a cohesive experience. The chatbot extracts user intent service type, location, and preference signals—and maps them to relevant worker profiles through a structured filtering pipeline. Experimental evaluation demonstrates improved booking efficiency, reduced search time, and higher user satisfaction compared to conventional service directories. The proposed system establishes a scalable and extensible foundation for next-generation intelligent service marketplaces.

Introduction

The system addresses inefficiencies in the informal labor market for local services such as plumbing, electrical work, and domestic help, where users struggle to find reliable workers and workers lack stable income and visibility. Existing platforms like Urban Company and TaskRabbit improve access but still rely on keyword-based search and manual browsing, lacking intelligent conversational support.

To solve this, the proposed platform introduces an AI-powered conversational service marketplace that enables users to describe their needs in natural language. The system uses a chatbot with intent classification, entity extraction, and recommendation logic to identify suitable workers, automate booking, and streamline communication within a single interface.

The architecture combines a React-based frontend, Node.js backend, and Supabase for authentication, database, and storage, along with Redis for caching, Socket.IO for real-time communication, Razorpay for payments, and Google Maps for location services. The chatbot processes user queries, retrieves relevant worker data, and generates structured recommendations in real time.

Key features include worker registration and verification, AI-driven recommendations, real-time chat, secure authentication, and integrated payments. The booking system supports end-to-end workflows from selection to payment confirmation with real-time updates.

Testing results show high accuracy in intent detection, fast response times due to caching, reliable payment processing, and successful real-time notifications, demonstrating improved efficiency and usability compared to traditional service platforms.

Conclusion

This paper has presented the design, architecture, and implementation of an AI-powered local worker and service marketplace. The system addresses a well-documented gap in the existing landscape of service platforms by combining intelligent conversational assistance with a unified discovery, communication, and payment experience. The AI chatbot operating as a query assistant, recommendation engine, and booking facilitator demonstrated measurable improvements in booking efficiency and user satisfaction during evaluation. The hybrid architecture, combining Supabase’s scalable BaaS infrastructure with a dedicated Node.js bridge server, proved effective in balancing operational simplicity with the requirements of real-time, stateful interactions. The rule-based recommendation approach delivered fast, interpretable, and reliable worker suggestions suited to the platform’s early stage. The proposed system establishes a technically sound and practically viable foundation for intelligent local service marketplaces.

References

[1] M. Singh and A. Gupta, “Digital Transformation of Local Service Markets: A Case Study of Urban Company,” Journal of Business Research, vol. 98, pp. 245–256, 2019. [2] D. Sutherland and B. Naïb, “Gig Economy Platforms and Worker Welfare: Evidence from Fiverr,” International Journal of Electronic Commerce, vol. 25, no. 2, pp. 112–134, 2021. [3] A. Sundararajan, The Sharing Economy: The End of Employment and the Rise of Crowd-Based Capitalism. Cambridge, MA: MIT Press, 2016. [4] R. Adamopoulou and L. Moussiades, “An Overview of Chatbot Technology,” in Artificial Intelligence Applications and Innovations, Springer, 2020, pp. 373–383. [5] T. Pham, L. Nguyen, and B. Le, “Rule-Based Chatbot for Customer Support in Service Industries,” Procedia Computer Science, vol. 177, pp. 468–475, 2020. [6] F. Xu, J. Uszkoreit, Y. Du, W. Fan, D. Zhao, and J. Zhu, “Chatbot for E-Commerce: Design and Effectiveness,” in Proc. ACL Workshop on NLP for Conversational AI, 2020, pp. 1–12. [7] F. Ricci, L. Rokach, and B. Shapira, Recommender Systems Handbook, 2nd ed. New York: Springer, 2015. [8] M. D. Ekstrand, J. T. Riedl, and J. A. Konstan, “Collaborative Filtering Recommender Systems,” Foundations and Trends in Human–Computer Interaction, vol. 4, no. 2, pp. 81–173, 2011. [9] S. Zhang, L. Yao, A. Sun, and Y. Tay, “Deep Learning Based Recommender System: A Survey and New Perspectives,” ACM Computing Surveys, vol. 52, no. 1, pp. 1–38, 2019. [10] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA: MIT Press, 2016. [11] C. Pautasso, O. Zimmermann, and F. Leymann, “Restful Web Services vs. ‘Big’ Web Services: Making the Right Architectural Decision,” in Proc. WWW, 2008, pp. 805–814. [12] L. Richardson and S. Ruby, RESTful Web Services. Sebastopol, CA: O’Reilly Media, 2007.

Copyright

Copyright © 2026 Yogesh A. Palode, Vishal V. Farpat, Kartik B. Nagose, Shantanu D. Shejol, Sakshi J. Pandit, Priyanka V. Narkhede. This 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.