Kimat: AI-Driven Geospatial and Machine Learning-Based House Price Prediction System

  • Unique Paper ID: 209255
  • Volume: 13
  • Issue: 5
  • PageNo: 2243-2255
  • Abstract:
  • The real estate market is rapidly evolving with complex pricing dynamics, making manual property valuation subjective and prone to human error. The "Kimat" platform is designed as an AI-driven house price prediction system that transforms historical housing data into accurate real-time price predictions. By leveraging a focused regression workflow, the system analyzes structured property and locality attributes to output estimated prices accompanied by confidence-oriented explanations. Utilizing machine learning models such as Random Forest, which evaluate key property features and market trends, Kimat provides fast, reliable, and data-driven preliminary valuations. The platform compares Multiple Linear Regression against ensemble techniques using R2, RMSE, and MAE, explains the strongest price drivers, and exposes the selected model through a simple, pincode-aware prediction interface. This empowers homebuyers, real estate agents, and property investors by democratizing real estate valuation and saving time and appraisal costs through an intuitive web interface.

Copyright & License

Copyright © 2026 Authors retain the copyright of this article. This article 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.

BibTeX

@article{209255,
        author = {Dr. MK Jayanthi Kannan and Aditya Anand and Jasmine Chauhan and Arihant Jain and Atreya Malviya and Krish Pandey and Ayush Shukla},
        title = {Kimat: AI-Driven Geospatial and Machine Learning-Based House Price Prediction System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {5},
        pages = {2243-2255},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=209255},
        abstract = {The real estate market is rapidly evolving with complex pricing dynamics, making manual property valuation subjective and prone to human error. The "Kimat" platform is designed as an AI-driven house price prediction system that transforms historical housing data into accurate real-time price predictions. By leveraging a focused regression workflow, the system analyzes structured property and locality attributes to output estimated prices accompanied by confidence-oriented explanations. Utilizing machine learning models such as Random Forest, which evaluate key property features and market trends, Kimat provides fast, reliable, and data-driven preliminary valuations. The platform compares Multiple Linear Regression against ensemble techniques using R2, RMSE, and MAE, explains the strongest price drivers, and exposes the selected model through a simple, pincode-aware prediction interface. This empowers homebuyers, real estate agents, and property investors by democratizing real estate valuation and saving time and appraisal costs through an intuitive web interface.},
        keywords = {House Price Prediction, PropTech, Machine Learning, Random Forest, Multiple Linear Regression, XGBoost, Real Estate Valuation, Predictive Analytics, Kimat.},
        month = {October},
        }

Cite This Article

Kannan, D. M. J., & Anand, A., & Chauhan, J., & Jain, A., & Malviya, A., & Pandey, K., & Shukla, A. (2026). Kimat: AI-Driven Geospatial and Machine Learning-Based House Price Prediction System. International Journal of Innovative Research in Technology (IJIRT), 13(5), 2243–2255.

Related Articles