HOUSE RENT PREDICTION OF MAIJDEE TOWNNOAKHALI, BANGLADESH, A STUDY OF SUPERVISED MACHINE LEARNING

Abstract

In this article, we proposed a machine learning-based approach to predict house rent prices. We use a
dataset of real estate listings containing various features such as main-road, area, number of rooms,
gas-line and other advantage to train our model. We first pre-process the data to remove missing
values, handle outliers, and convert categorical variables to numerical ones. We then explore and
analyze the data using various visualization techniques. We use multiple linear regression, random
forest regression models and decision tree to predict house rents based on the available features. We
evaluate the performance of the models using various metrics such as mean squared error, root mean
squared error, and R-squared. Our results show that the linear regression model outperforms the
random forest regression model and decision tree in terms of prediction accuracy. Overall, this article
demonstrates the effectiveness of machine learning techniques in predicting house rent prices. The
proposed approach can help landowners and renters make informed decisions on pricing and rental
contracts, as well as assist real estate, agents and property managers in setting the right rent prices for
their properties.