The project aims to predict house prices in Mumbai using machine learning techniques to address the challenges of finding accurate pricing in the real estate market. A dataset comprising 6,338 records and 17 variables, including area and number of bedrooms, was analyzed using models like linear regression, decision tree, and random forest, with random forest achieving the highest accuracy of approximately 46%. The document also includes various data visualization techniques to illustrate the relationships between different parameters and house prices.

1. PATTERN RECOGNITION
HOUSE PRICE PREDICTION
MUMBAI
Presented By :
Shashi Ranjan (20BTCSE0061)
Sandeep Yadav (20BTCSE0056)
Submitted to :
Mr. Shubhashish Goswami

2. Objective
This project is prepared to predict the price of
house in ‘Mumbai’ using the concept of Machine
Learning.

3. Introduction
● It is very difficult to search house at places like Mumbai. Even if
you find a house it is very difficult to get a perfect price for the
same.
● To overcome such problem Machine Learning technique can be
used.
● Using Machine Learning Technique it will be easy to know the
price of house based on the area available, number of bedrooms,
facilities available

4. Dataset Description
Dataset Size : 6338 x 17
• Price
• Area
• Location
• Number of Bedrooms
• New/Resale
• Gymnasium
• Lift Available
• Car Parking
• Maintenance Staff
• 24x7 Security
• Club House
• Intercom
• Landscaped Gardens
• Indoor Games
• Gas Connection
• Jogging Track
• Swimming Pool
Following are the parameters in dataset for house price prediction of ‘Mumbai’ :

5. Dataset Type
Dataset
CONTENTS
CONTENTS
Categorical
Quantitative
Continuous
Binary
Nominal
Ordinal
Descrete
Ordinal
Binary
⮚ Dataset is a collection of related sets of information that is composed of separate elements
but can be manipulated as a unit by a computer.

6. CATEGORICAL
NOMINAL
BINARY
• Location
Categorical Attributes
ORDINAL
• New/Resale
• Gymnasium
• Car Parking
• Maintenance
• 24x7 Security
• Club House
• Intercom
• Landscaped
• Indoor Games
• Gas Connection
• Jogging Track
• Swimming Pool

7. QUANTITATIVE
CONTINUOUS
DISCRETE
• Number of Bedrooms
• Lift Available
• Price
• Area
Quantitative Attributes

8. Snapshot of dataset
The following snapshot shows tail part of data taken from Dataset used in House
price prediction.

9. Data Visualisation (Scatter Plot)
In the given Scatter plot it shows that as the ‘Price’ of house
increases with increase in ‘Area’ of house.

10. Data Visualisation (Pie Chart)
Pie chart shows houses available with how many ‘No.of
Bedrooms’ and their percentage out of 100.

11. Data Visualisation (Histogram)
Histogram verifies the pie chart as is shows the number of
houses having how many ‘No. of Bedrooms’.

12. Data Visualisation (Box-Whisker Plot)
Box and whisker plot here shows how many outliers are
present in each parameter of the Dataset.

13. Data Visualisation (Box-Whisker Plot)
Pie chart shows percentage of No.of Bedrooms

14. Applying Machine Learning Algorithm
1. we set the independent and target variables as X and Y respectively.
2. Split the dataset into training and testing in 70:30 ratio.
3. Fitting the train set to multiple linear regression and getting the score of the
model.
4. Fitting the train set to decision tree and getting the score of the model.
5. Fitting the train set to random forest and getting the score of the model.
6. Calculate the model score to understand how our model performed along
with the explained variance score.

15. Conclusion

16. Conclusion
After applying Linear Regression, Decision tree, and
Random forest Machine Learning algorithm we observe
that random forest gives highest accuracy of almost
46%.

17. Thank you