Minimizing False Positives in Anomaly Detection Models

Gali Katz

We at Taboola built our own in-house anomaly detection framework, for detecting issues in critical metrics. Our framework contains hundreds of models, which sometimes become noisy. In order to minimize the number of false positives, we chose different strategies such as specific cutoffs, hyperparameter tuning and integration with internal information.

Interested? Come hear Gali Katz, Senior Software Engineer at the Infrastructure Engineering Group at Taboola

Talk language: Hebrew

October 19, 2021
Hall B
Gali Katz
Gali Katz

For the past 4 years, I worked as a senior, full-stack developer in the Production Engineering team at Taboola. Facing real-life scaling and reliability problems, I worked hard to make our monitoring framework stable and reliable. One major step during this project was the development of an anomaly detection engine, which is now becoming widely used by different teams across the company.

Gali Katz

Become a sponsor:

Leave your email and we will get back to you with our great sponsorship information:

Cancellation Policy

The conference will be in-person and not virtual, and will take place according to the COVID-19 regulation at the time of the conference. If we will not be able to hold an in-person event, we will postpone it and not make it virtual. In case of cancellation of the event or if the event is postponed to another date, we will offer a full refund to all attendees and sponsors.

Attendee cancellations:

Up to 30 days prior to the event – 100% Refund 30-14 days prior to the event – 50% Refund. No refund will be offered later than that.