Property Price Estimation Using Machine learning and implementing a website using HTML, CSS, and JavaScript

Property price estimation uses various kinds of algorithms in Machine Learning like linear regression, lasso, and decision tree that best predict the house prices with the highest accuracy. In this paper, we use various machine learning algorithms to build a model that predicts the house prices based on the requirements like location, area, number of bedrooms, and no of bathrooms. A Huge set of data on housing prices is trained for various attributes to create an algorithmic model. To better understand the links between the several housing qualities and the selling prices, we will do exploratory data analysis (EDA), which entails visualizing the data and discovering patterns and trends that help to develop the prediction model. Data pre-processing and data cleaning is done before creating the model. We build a linear regression model, and we compare it with the other machine learning algorithms like lasso regression and classification and regression tree algorithms and use the one that yields high accuracy. The tested model is imported through a pickle file and a Flask server is used for developing the website using HTML, CSS, and JavaScript.