Skip to main contentSkip to navigation
MachineHack Gen AI Logo
Predicting House Prices In Bengaluru Logo

PredictingHousePrices
InBengaluru

Expired
Start: March 19, 2018Ends: November 3, 2025
Participants
3,532
Time Left
Ended
Subs/day
10
Challenge Overview

Predicting Property Prices in Bengaluru

What factors influence a potential home buyer's decision?
Home buyers often evaluate several criteria, including:

  • Location and proximity to essential amenities like offices, schools, parks, restaurants, and hospitals.
  • Size and layout of the property.
  • Aesthetic considerations like having a balcony or a "white picket fence."
  • And most importantly—price.

In recent years, the real estate market in India has seen significant changes. The lingering effects of demonetization, the enforcement of the Real Estate (Regulation and Development) Act (RERA), and trust issues with property developers have all contributed to a 7% drop in housing sales across India in 2017.

For example, property prices in Bengaluru alone dropped by nearly 5% in the second half of 2017, according to a study by Knight Frank. A report by Makaan further reveals that:

  • Over 9,000 apartments are available in the ₹42–52 lakh range.
  • Approximately 7,100 apartments fall within the ₹52–62 lakh range.
  • The ₹15–25 lakh budget segment includes 5,000+ projects, followed by projects in the ₹34–43 lakh range.

Buying a Home in Bengaluru: A Unique Challenge

With Bengaluru's millennial workforce, dynamic culture, favorable climate, and booming job market, deciding the right price for a property can be daunting. Understanding property prices in Namma Bengaluru requires analyzing a combination of factors.

Dataset Overview

The dataset contains detailed information about properties in Bengaluru. It has been meticulously curated over months of primary and secondary research by a dedicated team.

Train and Test Data:

  • Each row represents a property with a fixed set of 9 features (categorical and continuous).
  • These features provide insights into the property’s characteristics and pricing.

Features:

  1. Area_type: Type of area (e.g., built-up, super-built-up).
  2. Availability: Indicates possession status or readiness (categorical or time-series).
  3. Location: The property’s location in Bengaluru.
  4. Price: The price of the property (in lakhs, INR).
  5. Size: Number of bedrooms (BHK: 1–10 or more).
  6. Society: The society or community the property belongs to.
  7. Total_sqft: Total area of the property (in sq. ft).
  8. Bath: Number of bathrooms.
  9. Balcony: Number of balconies.

Problem Statement:

Using the given 9 features, build a robust machine learning model to predict the price of houses in Bengaluru. This will help potential home buyers and property developers make informed decisions based on reliable data-driven insights.

Problem Statement

This challenge focuses on building advanced machine learning models to solve real-world problems. Participants will work with carefully curated datasets and compete to achieve the best performance metrics.

Target Column: price
Metric: custom_root_mean_squared_1
Level: Beginner
Submissions: 10/day
Top Submissions

No leaderboard data available

Check back later for updates

Predicting House Prices In Bengaluru

Registration is open

Similar Challenges

Discover similar AI and data science competitions

No sponsored hackathons available at the moment.

Never Miss a Hackathon

Get notified about new AI hackathons, data science competitions, and exclusive opportunities. Join 50,000+ developers staying ahead of the curve.

No spam, unsubscribe at any time. We respect your privacy.