Contests in Signal Processing and Machine Learning

During the last couple of months, a number of machine learning and signal processing contests have recently finished and the final rankings have been announced. Some of those recently concluded ones include:

The CrowdFlower Search Results Relevance challenge: The idea was to predict the relevance of search results from eCommerce sites and in the process create a set of algorithms that will enable small business owners to match the experience provided by more resource rich competitors while also providing established businesses a model to test against.

The 2015 ECML/PKDD contest: The goal in this cotest was to build a predictive framework able to infer the trip time of taxi rides in Porto, Portugal based on their (initial) partial trajectories. The output of such a framework should be the travel time of a particular taxi trip. The business idea behind this problem is that if a dispatcher knew approximately when a taxi driver would be ending their current ride, they would be better able to identify which driver to assign to each pickup request.