House Price Prediction (ML model & Webapp)

The Problem Definition

   

The problem we are going to solve in this project is the house price prediction problem. Based on certain features of the house, such as the location, area in square feet, number of bedrooms, number of bathrooms, we have to predict the estimated price of the house.

Purpose of this Model & Website

Our project is a Machine learning model/app, which will guess the accurate price of your future house on basis of the some certain specification of your future house.

Prediction house prices are expected to help people who plan to buy a  house so they can know the price range in the future, then they can plan their finance well. In addition, house price predictions are also beneficial for property investors to know the trend of housing prices in a certain location.

In real estate, so many real-estate companies are hiring some experts to predict the price of a House and suggest that the company invest in that house but sometimes they are not 100% correct. Sometimes they are failed to give accurate predictions about the price of the house.

So we want to create one ml model that can use to predict the price of this house. it gives 90% right prediction but accurate prediction about the price of the house because we train that model with all the previous year data which predict the approx but accurate price of that house using this ML model.

In this project, we use one ML model to predict the price of one specific city’s houses using a data set that provides on the Kaggle app.

How it's Work

1.) Collecting the data

The first step is data science work where we take a data set from Kaggle called ‘Bengaluru_House_price.csv’.We will perform some extensive data cleaning work on it to ensure that it gives accurate results during prediction.

This jupyter notebook entitled ‘House_Price_Predictions.ipynb’ is where we perform all the data science-related work. Our dataset requires a lot of work in terms of data cleaning. In fact, 70% of the notebook is all about data cleaning where we drop empty rows and remove unnecessary columns that won’t help in prediction which is also called an outlier.

2.) Model Creation

Outliers are anomalies that cause an enormous amount of damage to data and prediction. There is a lot of things to understand from the dataset logically to detect and remove these outliers.

after that, Turns out the Ridge model gives the best results for our data with a score above 80% which is not bad. we extracting useful and important information from the dataset and dumped it in "RidgeModel.pk1" which will help us to predict the price successfully.

Using this ridge model's pickle file we convert python objects into a character stream. Also, we need to export the locations(columns) into a json(columns.json) file to be able to interact with it from the frontend.

3.) Server

We will use a Flask server as our backend to host the application locally. In the server folder.

4.) Frontend

The front end is made up of simple HTML, CSS, and JavaScript. The user can select the number of square feet area, BHK, bathrooms, and location in the form and hit on the ‘ESTIMATE’ button to get the estimated price. The JavaScript file is responsible for interacting with both the backend flask server routes and the frontend HTML.

Architecture of Application

Features We use in Our model

• Location of the house
• Number of Bedroom 
• Number Bathroom
• Square Feet 

Technologies 

• Model creation
• Python libraries : numpy, pandas, Scikit-Learn,pickle-mixin
• Model creation editor : jupyter notebook   
• Website creation
• Editor : VScode, Pycharm
• Language : HTML, CSS, JS 
• Serve Side
• Flask Server

Screenshots Of Model and Webapp

• Bengaluru_House_price.csv

        

Uncleaned & With outlier dataset

• Cleaned_Data.csv

cleaned & Without outlier dataset
    

• Website

     

                                                                            

     

               

THANK YOU !