Deep Learning for Recommender Systems – eBay Tech Berlin

Finding a car that fits your preferences can be a very time-consuming task and may drive you crazy. On the other hand, with approximately 1.5 million cars on our platform, vehicle descriptions that are constantly changing and users that are still exploring may also drive us as the solution provider crazy. Under these circumstances, matching cars with users' preferences is challenging and by the time you've found a match, your perfect car might be gone. Even if you haven't searched for a car yet, you've probably faced similar problems in other domains like news, consumer products, or entertainment. On Spotify, you don't like to explicitly outline your music tastes before you start enjoying music. You also don't want to search through the whole IMDB to find your next favorite series on Netflix. The sheer number of possibilities creates a burden of choice.