auz-amjad/DataScienceCapstone_Oct2017

This is the winning submission for the Oct. 2017 Data Science Capstone challenge hosted by DrivenData for the Microsoft Professional Data Science curriculum on EdX

Data Science Capstone - October, 2017

This is the winning submission for the Oct. 2017 Data Science Capstone challenge hosted by DrivenData for the Microsoft Professional Data Science curriculum on EdX. Public RMSE: 2.8992

email- cbenge509, 2017

Links

• Competition:
  • Challenge description: DAT102x: Predict Student Earnings
  • Final leaderboard : DAT102x: Leaderboard
• Documentation
  • Analysis of College Graduate Earnings : Analysis of College Graduate Earnings.pdf
• Models used
  • SciKit-Learn:
    • ensemble methods
      • RandomForestRegressor
      • ExtraTreesRegressor
      • AdaBoostRegressor
      • GradientBoostingRegressor
    • tree models
      • DecisionTreeRegressor
      • ExtraTreeRegressor
    • generalized linear models
      • LinearRegression
      • ElasticNet
  • XGBoost
    • XGBoostRegressor
  • Microsoft LightGBM
    • LGBMRegressor
  • MLXTend
    • StackingRegressorCV

License

• This project is released under a permissive MIT open source license (LICENSE-MIT.txt). There is no warranty; not even for merchantability or fitness for a particular solution.

Notes

This project was a lot of fun for me; it was my first time working with Python and my first machine learning experience. I spent a great deal of time researching, experimenting, and learning from many people online who were willing to spend their time sharing with others. In the interest of giving back, I am sharing my submission and write-up. -C