FindMyDorm: A Deep Reinforcement Learning Approach for Personalized Recommendation Systems

Authors:
T. S. Abiraami, R. Hari, S. Surya, R. Angeline, Sureshkumar Somayajula

Addresses:
Department of Computer Science and Engineering in AIML, SRM Institute of Science and Technology, Ramapuram, Chennai, Tamil Nadu, India. Department of Computer Science and Technology, Sunlife Canada Financials, Toronto, Ontario, Canada.

Abstract:

The process of finding appropriate hostel accommodation for students is a very important and time-consuming task that students in universities need to undertake, entailing the analysis of a variety of constraints and requirements that need to be met, including affordability, proximity to institutions of learning, security, and availability of basic amenities. There is a primary reliance on a straightforward listings-based strategy that does not provide relevant or legitimate information when used with existing web solutions for searching for college hostels. FindMyDorm is a web-based dormitory recommendation system developed for this research paper. Its purpose is to facilitate efficient, individualized housing searches. To address the problems raised, this approach was designed to overcome them. The system presented aims to create recommendations that are pertinent by enabling the systematic collection and processing of user-specific input on geographical location, financial constraints, required facilities, and proximity to educational institutions. This enables the formulation of relevant recommendations. 

Keywords: Deep Reinforcement Learning; Personalized Recommendation System; Student Accommodation; Sequential Decision-Making; Sentiment Analysis; Popularity Bias Mitigation.

Received on: 07/04/2025, Revised on: 02/08/2025, Accepted on: 23/09/2025, Published on: 05/05/2026

DOI: 10.64091/ATICS.2026.000257

AVE Trends in Intelligent Computing Systems, 2026 Vol. 3 No. 2 , Pages: 77-85

  • 👁 99
  • ⬇ 3
Download PDF