House Price Forecast

A house value is simply more than location and square footage. Like the features that make up a person, an educated party would want to know all aspects that give a house its value. The client wants to take advantage of the features that influence a house price the most. They typically want to buy a house at a low price and invest on the features that will give the highest return. For example, buying a house at a good location but small square footage. The client will invest on making rooms at a small cost to get a large return.


Numpy & Pandas
Scikit Learn

Key Challenges

  • Identifying the housing markets’ leading indicators.
  • Clean up and preparation of huge amount of Data.
  • Identification of neighbourhood sale trends and assessment sale trends.

Our Solutions

  • High-performance python toolkits an Exploratory Data Analysis (EDA) was performed on the dataset. With over 40 different parameters, a correlation study helped to identify the market indicators.
  • EDA helped in gathering insights about data. Features are categorised into Categorical and Continuous. This helped in data filtering and cleanup.
  • Clustering helped in grouping similar properties based on location. A complex pipeline of filtering addresses, reverse geocoding and custom clustering helped to get neighbourhood sale trends.
  • Advanced Regression and Deep learning techniques applied on strongest market indicators helped to forecast sale prices of the properties. Accuracy of 95% with error of 10K price.