FORECASTING HOUSING PRICES USING RANDOM FOREST ALGORITHM ON STREAMLIT FRAMEWORK

Abstract

In the ever-changing real estate landscape, a comprehensive understanding of house prices is crucial for buyers, sellers, and investors alike. While the traditional evaluation method still serves well, the growing availability of datasets has opened a new way to predict house prices. This paper will explore the use of predictive analysis algorithms to find house prices based on data-driven insight to improve the decision-making process when trying to invest or buy a house.

The study discovered that using a predictive algorithm model, the application managed to predict the house price with a commendable level of accuracy. By processing the vast dataset into moderately usable data and comparing several predictive analysis algorithms to find the best result, the machine learning model was able to find and indicate the correlation between data in a large-scale dataset resulting in a good prediction for the house prices. With accurate house price predictions in hand, now users can approach any house transaction with better clarity and knowledge, ensuring better financial decisions.