Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM69179
Volume:
10 |
11 |
Nov 2026
Pages:
1-8
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.
Research Scholor
D.G Ruparel College
Assistant Professor
D.G Ruparel College
Property valuation is an important activity for buyers, sellers, investors, and real-estate professionals. Estimating a property's value can be difficult because price is influenced by several characteristics, including location, property type, floor area, number of bedrooms and bathrooms, floor level, age, furnishing, and parking availability. This paper presents PropVal.ai, a web-based property price prediction and portfolio-management application developed using Python, Flask, SQLite, and Scikit-learn. The system applies a Linear Regression model within a preprocessing pipeline that standardizes numerical attributes and one-hot encodes categorical attributes. It provides authenticated user accounts, user-specific property records, price predictions, prediction history, dashboard summaries, and interactive visual reports. The application can generate synthetic training data during initial setup and stores the trained pipeline for reuse. Model evaluation is designed around the coefficient of determination (R²), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE). Since the documented training process uses generated synthetic data, the resulting metrics should be interpreted as development or internal validation indicators rather than proof of performance on live market transactions. PropVal.ai is therefore presented as an indicative statistical decision-support tool, not as a certified appraisal service.
KEYWORDS
This paper presented PropVal.ai, an AI-based property price prediction and real-estate valuation web application. The system integrates a Flask web application, SQLite relational storage, account authentication, property-record management, a Scikit-learn Linear Regression pipeline, prediction history, and interactive dashboard visualizations. Numerical inputs are standardized and categorical inputs are one-hot encoded through a preprocessing pipeline. The trained pipeline is cached for reuse, while the application records prediction information for later review. The project demonstrates how a machine-learning component can be integrated into a practical web-based decision-support workflow. Its current contribution is the end-to-end application and its connected features, rather than a newly proposed prediction algorithm. Since the documented training data are synthetic and the README does not provide numerical evaluation results, the current system should be treated as a prototype for indicative estimates. Validation using reliable real-world transaction data, transparent experimental reporting, and comparison with alternative models are essential next steps.
[1] S. Rosen, “Hedonic Prices and Implicit Markets: Product Differentiation in Pure Competition,” Journal of Political Economy, vol. 82, no. 1, pp. 34–55, 1974. [2] G. James, D. Witten, T. Hastie, R. Tibshirani, and J. Taylor, An Introduction to Statistical Learning: with Applications in Python. Springer, 2023. [3] F. Pedregosa et al., “Scikit-learn: Machine Learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011. [4] Pallets Projects, “Flask Documentation.” Available: https://flask.palletsprojects.com/
Publication Date
11/18/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
0
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...