Hello! We publish a report from the Avito Data Science Meetup: Personalization mitap, which took place in our office. Participants discussed modeling user preferences in multimodal data and clustering volatile ads using the EM algorithm. Under the cut - videos, presentations, a link to a photo report.

Modeling user preferences in multimodal data. Hady W. Lauw, Maxim Tkachenko (Singapore Management University)

The key to good recommendations is modeling huge amounts of behavioral data that arise as a result of user interactions with online systems. These interactions are multimodal, that is, composed of various types of data, such as user ratings, reviews, photos, or their social interactions. This complicates the task. Speakers talk about data mining and machine learning methods for modeling user preferences in multimodal data and their use in creating a complete recommendation system.

The report was delivered in English, we translated it and added subtitles in Russian:

Presentation

Clustering volatile ads using the EM algorithm. Vasily Leksin (Avito)

Working on the development of recommendations on Avito, colleagues decided to cluster short-lived ads: this will help users see more relevant recommendations, and we will be less likely to retrain models and do it faster. Vasily presents an optimized EM algorithm that is capable of efficiently processing huge amounts of data and talks about methods for assessing the quality of clustering and application applications of the algorithm.

Presentation

Thanks to everyone who came to the meeting, watched the videos. We posted the photo report from the meeting on Facebook . To be the first to know about events for technicians at Avito, sign up for our Timepad . And be sure to tell us in the comments on what topics you would like to listen to the reports.

See you soon!