How to stay statistically significant in Data Science

Dear members - important message*

Due to the limitation of our space, we have already filled all seats for the evening. However, for those that have reserved a spot but are no longer able to attend, please remove your subscription to allow those on the waiting list to join

***************************************************************

SCHEDULE

18:30-19:00 - Gathering food, drinks and networking
19:00-19:30 - First talk: “How Data Scientists Survive Agile?” by Dima Goldenberg
19:30-20:00 - Second talk: “Experimentation at Booking.com” by Kostia Kofman
20:00-20:30 - Q&A with the Booking.com TLV R&D team
20:30-21:00- More time for networking and mingling

Collaboration with Machine & Deep Learning Israel. All the talks will be held in English!

How Data Scientists Survive Agile? by Dima Goldenberg

There is a conflict of interest: data science field is often based on long-term cycles of research, data collection and labeling, on the other hand, product development requires fast execution, flexible decision making and constant deliverables of new machine learning models to production.

In this talk, we’ll share how agile product development principles work in harmony with machine learning development at Booking.com. We will explain how embedded data scientists in cross-functional team structure and data-driven culture can contribute to daily standups and constant deliverables.

Experimentation at Booking.com by Kostia Kofman

Data science & product development must rely on a solid and scientific method to assess impact on the user experience. The scale of traffic and work at Booking.com pushed us to build a scalable, reliable and versatile experimentation platform which is constantly improved upon.

In this talk, we will share how we formulate a hypothesis, select the right metrics and appropriate statistical tests and finally how we interpret the results and refine our hypothesis.

Some of the topics we’ll cover: RCT (randomized controlled trial) and causal inference, comparative tests vs non-inferiority tests, bias - sources and ways to overcome it, and more if time permits.
________________________

SPEAKER INFORMATION

Dima Goldenberg| Data Scientist ML & Team Leader, Booking.com

Dima Goldenberg is a Data Scientist and Team Lead in the Personalization track at Booking.com. He joined Booking.com in 2017 with the establishment of the Machine Learning Development Center in Tel Aviv and worked on different customer-facing machine learning based projects such as customer retention and destinations recommendations.

Dima has a master’s in Industrial Engineering from the Tel Aviv University where he specialized in Big Data and Data Science, conducting his thesis research on "Influence Maximization in Social Networks". He started his data science path as a data specialist in the IDF and expanded his professional experience in internet, intelligence and semi-conductors industries together with a vast teaching experience of data-topics within the army, academia and private initiatives.

Kostia Kofman| Data Scientist ML, Booking.com

Holding a degree in math, a master’s in economics and pursuing another master’s in statistics, Kostia Kofman joined Booking.com as a Data Scientist in late 2017 as one of the first hires in their new Tel Aviv office. At Booking.com his primary focus is about bringing greater personalization of our website to our most frequent users. While prior to joining Booking.com Kostia worked for various web-related companies.