Skip to content

FaridHazratian/Sale-Forecasting

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 

Repository files navigation

Blue Book for Bulldozers

This is a kaggle competition that took place in 2012.

-- NoteBook Status: Updating...

Project Intro/Objective

The purpose of this competition is to predict the sale price of bulldozers sold at auctions.

Methods Used

  • Ensemble Learning
  • Machine Learning
  • Data Visualization
  • Predictive Modeling
  • Data Interpretation
  • Time Series Analysis
  • Model Interpretation

Technologies

  • Python
  • Plotly
  • Numpy
  • SkLearn
  • Pandas, jupyter
  • PDPbox
  • treeinterpreter

Project Description

In this Task Most of my attention was on data visualization and Model interpretation with the tools like treeinterpreter and PDPbox. I came up with 3 models such as Random Forest, XGboost, Extremely randomized tree. Which gave me nearly the same results with all that hyper parameter tuning with the score within top 10%.

Needs of this project

  • Model Evaluation
  • Data Exploration/descriptive statistics
  • Data Pre Processing/Cleaning
  • Exploratory Data Analysis