It is the information that is delivered immediately after collection.
Published in Chapter:
House Rent Prediction Using Ensemble-Based Regression With Real-Time Data
Kuntal Mukherjee (Haldia Institute of Technology, India), Syed Saif Ahmed (Haldia Institute of Technology, India), Mohammad Aasif (Haldia Institute of Technology, India), Sumana Kundu (Dr. B.C. Roy Engineering College, India), and Soumen Ghosh (Haldia Institute of Technology, India)
Copyright: © 2023
|Pages: 14
DOI: 10.4018/978-1-6684-7524-9.ch014
Abstract
Finding a house for rent in a new city within the budget is a major issue especially for new college students and employees. In this scenario, an effective house rent prediction algorithm will be extremely beneficial. The rent for a house is affected by certain aspects such as number of rooms, distance from the market, region, availability of transport, and many more. With the help of different machine learning algorithms, the authors try to analyze, predict, and visualize the rent of a house. In this chapter, the authors have implemented multiple linear regression models and other ensemble learning methods like Adaboost regressor, random forest regressor, gradient boost regressor, and XGboost regressor to tune the overall model performance. The authors self-surveyed data set contains records of a city in West Bengal, India. So far, almost no work has been done in this context for Haldia. The authors' proposed house rent prediction model predicts rent with an accuracy of 98.20%.