Competitions

I am also a fan of data science competitions.

• 6th place, National Bank of Greece Race 2019, National Bank of Greece (April 2019)
  Training Greek word embeddings from legal texts. You can find more info here.
• 2nd place, Fintech Crowdhackathon 2016, National Bank of Greece (April 2016)
  Our team (RSK project) was the 2nd winner in the Fintech Crowdhackathon organized by the National Bank of Greece. We made a platform to detect fraudulent e-transactions based on deep learning. You can find more info here.
• 2nd place, Dreem challenge 2015, in-class Kaggle competition (January 2015)
  Trying to analyze dreams. During deep sleep, crucial mechanisms occur: memory consolidation, cellular regeneration, growth hormone release or biological clock reset. Lacking deep sleep impairs memory, focus and judgment during work. DREEM introduces a way to increase the duration and quality of deep sleep to ensure optimal performance.
• 6th place, Data Mining Cup 2013, Prudsys (May 2013)
  Our team from the Department of Informatics (AUEB), consisting of undergraduate students G. Papoutsakis, G. Zografos, G. Theofilis, myself, and Ph.D. students M. Karkali and S. Thomaidou, took the 6th place in the Data Mining Cup 2013 competition. The participations reached 99 teams from 77 universities all over the world.
• Top 25%, Employee Access Challenge 2013, Kaggle (April 2013)
  The objective of this competition was to build a model, learned from historical data, that determines an employee’s access needs, such that manual access transactions (grants and revokes) are minimized as the employee’s attributes change over time. The model takes an employee’s role information and a resource code and returns whether or not access should be granted.