The rapid growth of digital technologies and online real estate services has significantly transformed the rental property market. Nowadays, users prefer online rental platforms for searching apartments, houses, and commercial properties instead of relying on traditional offline methods. However, existing rental platforms mainly provide manual search and filtering options, which often generate irrelevant results and fail to understand the personalized preferences of users. As the number of property listings increases continuously, users face difficulties in identifying suitable rental properties efficiently. Therefore, there is a growing need for intelligent recommendation systems that can provide accurate and personalized property suggestions based on user behavior and preferences. This research paper proposes an AI-Based Property Recommendation System for Smart Rental Platforms that utilizes machine learning techniques to improve the efficiency and accuracy of property recommendations. The proposed system is designed to analyze user preferences such as budget, preferred location, property type, amenities, and previous interactions with the platform. Based on this analysis, the system generates personalized rental property recommendations using recommendation algorithms such as content-based filtering and collaborative filtering. The proposed system is implemented using the MERN stack, including MongoDB for database management, Express.js and Node.js for backend development, and React.js for frontend user interface design. Machine learning libraries and recommendation techniques are integrated into the system to provide intelligent property suggestions. The recommendation engine continuously learns from user interactions to improve recommendation quality over time. The system offers various features including property search, user authentication, smart filtering, wishlist management, recently viewed properties, and AI-driven recommendation sections. Compared to traditional rental platforms, the proposed system significantly reduces the time required for property searching and enhances user experience through personalized recommendations. The results of the proposed model demonstrate that integrating artificial intelligence into rental platforms improves recommendation accuracy, increases user satisfaction, and enhances overall platform efficiency. The proposed system can further be extended with advanced technologies such as deep learning, voice-assisted search, chatbot integration, and real-time property price prediction. This research highlights the importance of AI-driven recommendation systems in the future development of smart rental and real estate platforms.
Bijesh Jangid (Mon,) studied this question.