We're sorry but this page doesn't work properly without JavaScript enabled. Please enable it to continue.
Feedback

Two clicks to cluster and block thousands of spammers

Formal Metadata

Title
Two clicks to cluster and block thousands of spammers
Title of Series
Number of Parts
69
Author
Contributors
License
CC Attribution 3.0 Unported:
You are free to use, adapt and copy, distribute and transmit the work or content in adapted or unchanged form for any legal purpose as long as the work is attributed to the author in the manner specified by the author or licensor.
Identifiers
Publisher
Release Date
Language

Content Metadata

Subject Area
Genre
Abstract
LOVOO's (a social and dating platform) moderation team focuses on keeping the platform free of unwanted users. Our newest solution involves using unsupervised learning to cluster and visualize users' batches within a few clicks to moderate them according to the clustering algorithm's outcome. Behind those clicks, there's a large collection of components supporting the system. These include a machine learning service that creates the model, our whole Antispam platform, Kafka, gRPC, databases, lots of data, and more. This talk is about the complete platform— its intention, motivation, architecture, and results.