Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM62055
Volume:
10 |
4 |
April 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 computer science with specialisation in Artificial Intelligence
IIMT College of Engineering
Department of computer science with specialisation in Artificial Intelligence
IIMT College of Engineering
Department of computer science with specialisation in Artificial Intelligence
IIMT College of Engineering
The rapid growth of digital technologies has significantly transformed the real estate sector; however, traditional property search platforms still rely on rigid, filter-based systems that often fail to meet user expectations for personalization and efficiency. This paper presents an AI-Powered Flat Finder, a smart real estate search system that leverages conversational artificial intelligence (AI) to provide an intuitive and user-friendly property discovery experience. The proposed system integrates Natural Language Processing (NLP) with a modern web architecture to enable users to search for flats using simple, human-like queries such as “2BHK near metro under ₹15,000.” The system interprets user intent, extracts key parameters like location, budget, and amenities, and retrieves relevant listings from a real-time cloud database. The frontend is developed using React, ensuring a responsive and interactive user interface, while Firebase is used as the backend for real-time data synchronization, secure authentication, and scalable storage. Unlike conventional platforms, the system supports context-aware interactions, allowing users to refine their search through follow-up queries. The integration of AI enhances recommendation accuracy, reduces search time, and improves overall user engagement. Experimental observations indicate improved efficiency, faster response time, and higher user satisfaction compared to traditional search methods. The proposed solution demonstrates how AI-driven conversational systems can revolutionize real estate search by making it more intelligent, personalized, and accessible. Future enhancements may include voice-based interaction, image-based search, and predictive analytics for property pricing trends.
KEYWORDS
The AI-Powered Flat Finder system presents an innovative approach to modern real estate search by integrating Artificial Intelligence, Natural Language Processing, and cloud-based technologies. Unlike traditional platforms that rely on rigid filter-based mechanisms, this system enables users to interact through natural language, making the search process more intuitive, efficient, and user-friendly. The implementation of an AI chatbot allows users to describe their requirements in a conversational manner, which are then processed to extract meaningful parameters such as location, budget, and property type. The integration of Firebase ensures real-time data synchronization, secure authentication, and scalable database management. Together, these technologies create a seamless and responsive system capable of delivering accurate and personalized property recommendations. The results demonstrate that the system achieves high efficiency, fast response time, and improved user engagement. The conversational interface reduces the complexity of traditional search methods, while the recommendation system enhances the relevance of search results. Additionally, the system’s scalability and performance indicate its potential for handling large datasets and multiple concurrent users without significant degradation. This research highlights the potential of AI-driven systems in transforming traditional industries such as real estate. By combining intelligent query processing with real-time data handling, the AI-Powered Flat Finder provides a more accessible and effective solution for property discovery. The system not only improves user experience but also lays the foundation for future advancements in smart real estate applications. In conclusion, the proposed system successfully achieves its objective of simplifying and enhancing the flat search process. With further enhancements such as voice-based interaction, predictive analytics, and multi-language support, the system can evolve into a comprehensive and intelligent real estate platform suitable for large-scale deployment.
[1] Meta, “React – A JavaScript Library for Building User Interfaces.” [Online]. Available: https://react.dev/ [2] Node.js Foundation, “Node.js Documentation.” [Online]. Available: https://nodejs.org/en/docs/ [3] Express.js, “Express – Fast, Unopinionated, Minimalist Web Framework for Node.js.” [Online]. Available: https://expressjs.com/ [4] MongoDB Inc., “MongoDB Documentation.” [Online]. Available: https://www.mongodb.com/docs/ [5] S. T. Kulkarni et al., “A Comprehensive Review of MERN Stack Development: Trends, Challenges, and Future Directions.” [Online]. Available: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5837262 [6] S. A. Bafna et al., “Review on Study and Usage of MERN Stack for Web Development.” [Online]. Available: https://www.ijraset.com/research-paper/study-and-usage-of-mern-stack-for-web-development [7] N. Bhat et al., “MERN Stack Unveiled: A Research Study on the Technology’s Architecture and Benefits.” [Online]. Available: https://propulsiontechjournal.com/index.php/journal/article/view/2215 [8] S. Nagarathinam et al., “Building the Modern Web: A Comparative Study of MERN and FERN Technology Stacks.” [Online]. Available: https://www.researchgate.net/publication/385704717 [9] A. S. Patil et al., “Harnessing the MERN Stack for Scalable E-commerce Website Design.” [Online]. Available: https://www.researchgate.net/publication/390647948 [10] V. Sahni et al., “MERN Stack Web-Based Platform for Placement Preparation.” [Online]. Available: https://kuey.net/index.php/kuey/article/view/3035
Publication Date
4/30/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
3
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...