[Kaggle] Project for Machine Learning course at University of Twente (2015)
In collaboration with Kim Beunder
For this competition, we have provided a dataset with 93 features for more than 200,000 products.
The objective is to build a predictive model which is able to distinguish between our main product
categories. The winning models will be open sourced.
- Anaconda
- Pyhton
- scikit-learn
- numpy
- pandas
- matplotlib
Unfortunately I wasn't able to recover the full jupyter notebooks containing all the results presented in the report. However, I include base code which can be extended at will.
The goal was to build and ensemble method containing Logistic Regression, k-Nearest Neighbors, Random Forests and Gradient Boosting classifiers to reduce a multi-class logarithmic loss.