Contests in Signal Processing and Machine Learning

During the last couple of months, a few new Signal Processing and Machine Learning contests were finished and new ones were initiated. A selection of some contests with a strong relation to Signal Processing is provided below:

In a big contest that attracted more than 2100 teams, Home Depot was asking Kagglers to help them improve their customers' shopping experience by developing a model that can accurately predict the relevance of search results. Search relevancy is an implicit measure Home Depot uses to gauge how quickly they can get customers to the right products. High ranking solutions included a combination of sophisticated Natural Language Processing techniques, on top of which a multitude of diverse ensembles were constructed.

In a contest that was just initiated a few days ago, Draper provides a unique dataset of satellite images taken at the same locations over 5 days. Kagglers are challenged to predict the chronological order of the photos taken at each location. Accurately doing so could uncover approaches that have a global impact on commerce, science, and humanitarian works.

Also from the domain of image recognition, the State Farm Distracted Driver Detection contest sets the question if computer vision can be used to detect distracted drivers. According to the CDC motor vehicle safety division, one in five car accidents is caused by a distracted driver. Sadly, this translates to 425,000 people injured and 3,000 people killed by distracted driving every year. State Farm hopes to improve these alarming statistics, and better insure their customers, by testing whether dashboard cameras can automatically detect drivers engaging in distracted behaviors. Given a dataset of 2D dashboard camera images, State Farm is challenging Kagglers to classify each driver's behavior. Are they driving attentively, wearing their seatbelt, or taking a selfie with their friends in the backseat?