Forecasting Multan estate prices using optimized regression techniques
Abstract
Purchasing a house or plot has become a complicated task for an average person due to budget constraints and market situations. An individual does not know the prices of the plots and gets trapped by a middle man. This paper proposes a solution for this problem by predicting the plot prices using a machine learning approach, leveraging Multiple Linear Regression, Gradient Boosting Regression, and Random Forest regression techniques. This work compares the performance of these three algorithms by hyper-parameter tuning using gird search, and random search for checking which one is adequate in terms of scores and error rates. Factors that influence the prices of the plots include plot covered area, physical condition of the plot, area, and population. Gradient boosting regression has surpassed all other machine learning methods, achieving the lowest error rates and highest R-squared score of 0.987 with grid search. The resultant predictive systems can help the folk in three ways. 1) safety from deception 2) budget oriented instant information, and 3) time saving.
Copyright (c) 2021 University of Sindh Journal of Information and Communication Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
University of Sindh Journal of Information and Communication Technology (USJICT) follows an Open Access Policy under Attribution-NonCommercial CC-BY-NC license. Researchers can copy and redistribute the material in any medium or format, for any purpose. Authors can self-archive publisher's version of the accepted article in digital repositories and archives.
Upon acceptance, the author must transfer the copyright of this manuscript to the Journal for publication on paper, on data storage media and online with distribution rights to USJICT, University of sindh, Jamshoro, Pakistan. Kindly download the copyright for below and attach as a supplimentry file during article submission