An introductory lecture to XGBoost is scheduled in Big Data Utah meetup. The lecture file (talk.pdf) contains three main parts:
-
Analysis of XGBoost algorithm, with math explained in detail.
-
Introduction to major XGBoost parameters and parameter tuning.
-
A demo file showing how to apply XGBoost to kaggle Allstate Claims Severity dataset.
Demo jupyter notebook: Demo.ipynb
 |
 |
|---|
Given the house price data in Moscow from 2011-2015, the goal of this project is to predict the house prices in Moscow from year 2015-2016. This is a competition currently hosted by kaggle: https://www.kaggle.com/c/sberbank-russian-housing-market
I used XGBoost in this competition and ranked 10th / 3274 teams. The leader board can be found in https://www.kaggle.com/c/sberbank-russian-housing-market/leaderboard
 |
 |
|---|