MACHINE LEARNING WITH THE HEART

The aim of the competition is to create a predictive model using heart data provided by Driven Data to predict the probability of a person suffereing from a heart disease.

This is the code I used when I participated in the Machine learning with the heart competition. You can find a detailed description of the competition here. This submission scored 0.369 (in the top 16%) against the winning score of 0.000(Judged on Log loss)

ZINDI TRANSPORT PROBLEM

The aim of the competition is to create a predictive model using traffic data provided from Uber Movement and historic bus ticket sales data from Mobiticket to predict the number of tickets that will be sold for buses into Nairobi from cities in "up country" Kenya.

This is the code I used when I participated in the Zindi transport competition. You can find a detailed description of the competition here This submission scored 4.425 against the winning score of 3.302(Judged on Mean Absolute Error)

DAKAR AIR POLLUTION

This problem is a supervised regression machine learning task. The objective is to use historical waether data and PM2.5 sensor data to predict the air quality in Dakar Senegal.
This is a standard supervised regression task:

Supervised: The labels are included in the training data and the goal is to train a model to learn to predict the labels from the features

Regression: The label is a positive continuous variable

You can find the code here