rodolfolermacontreras / bookish-octo-barnacle

Machine Learning Analysis for King County Home Prices

bookish-octo-barnacle

Machine Learning Analysis for King County Home Prices

Problem

Is there a feature or set of features that would yield to a higher home price for the King County Region?

Abstract

The purpose of this analysis is to provide insights on what home features (if any) could/would yield to higher home prices in the King County Region (Washington, US). This analysis was done by using the King County House Sales data set containing data from 2014 to 2015. The data was obtain from the following website: King County House Sales from UW Website

This exploration analysis is divided in the following way:

First look at the data:

• Data Cleaning
• Data Exploration
  • Price Distribution
  • Price Time Distribution
  • Location
  • Size and Condition

Analysis:

• Summary from previous analysis/milestones
• Features
  • Binning Variables
  • Normalized Variables
  • One-hot encode
• Split Data Set
• Train & Test Model
• Evaluate Model Performance

Summary/Conclusion:

• From the Data Exploration (Milestone 01)
• From Analysis (Milestone 02 & 03)
• Regarding Model & Predictions (Milestone 04)