Free

Setting up an A/B Testing Framework

Actions and Detail Panel

Free

Event Information

Share this event

Date and Time

Location

Location

Online Event

Event description
From page traffic to conclusions - Agnes van Belle

About this Event

In this talk, I'll outline how I and my colleagues build up an A/B-testing framework for an e-commerce company, with a focus on the statistical aspect.

After this talk, you will have a good overview of some common steps - and their possible pitfalls.

The talk will start with a brief introduction of main concepts.

Then it dives with a bit more detail into the following topics:

  1. Deciding what to measure
  2. Data transformation: making your measurements testable
  3. Testing: the t-test versus alternatives
  4. When to stop the experiment, or: minimum sample size calculation

About the speaker:

Agnes van Belle works as a Data Scientist at Berlin-based HeyJobs, a scale-up focused on intelligently targeting talent for jobs and vice versa.

Formerly she was employed at OLX Group (online classifieds), where she build a large part of their internal A/B testing framework. In addition, she was a regular consumer of said framework, when developing and testing solutions regarding search and recommendation.

Further back she worked as Search R&D team lead at Textkernel, an Amsterdam-based company using parsing and ranking for matching CVs and vacancies.

Agnes studied Artificial Intelligence at the University of Amsterdam, and has spoken or be a panel member at Berlin Buzzwords, ECIR, ECML-PKDD, and Haystack Europe. Her main interests are around representation learning, NLP, information retrieval and statistics.

DataTalks.Club is the place to talk about data. Join our slack community!

Share with friends

Date and Time

Location

Online Event

Save This Event

Event Saved