Key points are not available for this paper at this time.
The house rental price prediction project utilizes data science techniques to forecast rental prices based on various property attributes. The dataset encompasses factors such as the number of bedrooms (BHK), property size, location, and furnishing status. Through extensive data preprocessing, feature engineering, and exploratory data analysis, insights were gained into the influential factors affecting rental prices. The temporal trends in rental prices were also investigated, providing valuable information on market dynamics. In building the predictive model, a Random Forest Regressor was selected as the algorithm of choice1. This decision was grounded in the algorithm's ability to handle non-linear relationships and interactions among features, making it particularly suitable for the complexity of real estate pricing. The choice of Random Forest Regression over other algorithms is justified by its robustness in handling a diverse range of features and capturing intricate patterns within the dataset. Unlike simpler models that may struggle with the complexity of real estate data, the ensemble nature of Random Forest enables it to provide more accurate predictions. The abstract concludes with an acknowledgment of the model's potential real-world applications for property owners, real estate agents, and tenants, while highlighting areas for future improvements and research.
JS et al. (Fri,) studied this question.