Rental Price Prediction of Boarding Houses in Batam City Using Linear Regression and Random Forest Algorithms

Abstract

Boarding houses, commonly known as "kost," are residential places typically rented by individuals, serving a function similar to hotels, but with more affordable pricing. With the proliferation of boarding house businesses, residents and newcomers in Batam city face challenges in selecting suitable accommodation based on both price and amenities. Leveraging machine learning, a branch of artificial intelligence (AI), and incorporating various algorithms, a system can be developed to predict the rental prices of boarding houses. This helps individuals make informed decisions regarding the suitability of a boarding house based on their preferences and budget. The algorithms utilized in this study are Linear Regression and Random Forest. The modeling process resulted in R2 Scores, with Linear Regression achieving a score of 64%, while Random Forest outperformed with an impressive 99% R2 Score. Due to the higher R2 Score of Random Forest, this model was selected for the development of a website using the Scrum framework. The outcome of this research is a predictive pricing website for boarding houses, offering a valuable tool for residents and visitors in Batam when seeking to rent or lease a boarding house.

Keywords

• price prediction
• boarding houses
• random forest
• linear regression
• scrum