Melbourne Housing Data Analysis

Description

The obective of the project is to analyse the Melbourne’s Housing data and build a model to make predict the price of the house. The dataset includes data for the 21 mentioned paramters for the houses in the Melbourne city.

• Suburb,Address,Rooms,Price,Method,Type,SellerG,Date,Distance,Regionname,Propertycount,Bedroom2, Bathroom,Car,Landsize,BuildingArea,YearBuilt,CouncilArea,Lattitude,Longtitude

Technology Used

• Predictive Modeling
  
• Regression
  
• Descriptive Statistics
  

Environment

• R Studio , R (ggplot2,dplyr,randomForest,corrplot),Tableau

Analysis

• Data cleaning with variable research to ensure meaningful and analysable data for modelling.
  
• Exploratory Data Analysis to analyse trends in the housing data : Dashboard
  
• Implemented Linear regression, Decision tree and Random forest regressor models to predict the target feature price.
  
• Efficient features selection using stepwise selection and lasso regression.
  
• Random Forest regressor was the best fit model with efficient R square score.