MarwanMashra / To-Be_Challenge

Using LGBMClassifier to solve To-Be Challenge, which is a machine learning challenge on CodaLab Platform that aims to adress the problems of medical imbalanced data classification.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

To-Be_Challenge

To-Be is a machine learning challenge on CodaLab Platform about Mortality Prediction. The challenge aims to adress the problems of medical imbalanced data classification.

I worked in a team of 3 to solve the challenge and we were able to achieve a score of 77% and rank in the top 3. We used a LGBMClassifier and a mix of two resampling techniques (RandomUnderSampler and BorderlineSMOTE).


Results

ROC Curve Confusion matrix

About

Using LGBMClassifier to solve To-Be Challenge, which is a machine learning challenge on CodaLab Platform that aims to adress the problems of medical imbalanced data classification.


Languages

Language:Jupyter Notebook 100.0%