Cortana Intelligence Competitions

The Cortana Intelligence team has launched a data science challenge site. Currently there are two introductory challenges posted.

Decoding Brain Signals

Each year, millions of people suffer brain-related disorders and injuries and as a result, many face a lifetime of impairment with limited treatment options. This competition is based on one of the greatest challenges in neuroscience today – how to interpret brain signals.

Building on the work of Dr. Kai J. Miller and other neuroscientists, the competition is designed to further our understanding of how our brain interprets electric signals. The medical community and ultimately, patients will benefit from your expertise in machine learning and data science to help decode these signals.

Through this competition, you will play a key role in bringing the next generation of care to patients through advancing neuroscience research. Build the most intelligent model and accurately predict the image shown to a person based on electric signals in the brain. The Grand Prize winner will get $3,000 cash, followed by a 2nd prize of $1,500 cash, and a 3rd prize of $500 cash.

Contest Ends July 1, 2016

Iris Multiclass Classification

The primary goal of this tutorial competition is to help you get familiar with Cortana Intelligence Competition platform and build your first solution for Azure Machine Learning (AzureML) Competition using the well-known iris data. Participants’ performance is ranked by the overall accuracy of the model (higher accuracy, higher rank). As this is a tutorial competition, there is no award provided


The challenges have been up since 3/30 and already have 120 submissions! These are great competitions for all devs with an interest in data science. Students can try the Iris data set and more advanced can tackle the brain signal data.

The site has some interesting features.

  • auto-scoring of models
  • no need to download the data to your local box, then upload to wherever modeling is to be done. The data resides natively in Azure.

Stay tuned for more developments and challenges!