Myriam Hansel-Lesmy & Maya Cohen

A Journey Toward Creating One Holistic Model to Replace an Entire Ecosystem

Senior Machine Learning Scientist – PayPal

Myriam Hansel-Lesmy & Maya Cohen

A Journey Toward Creating One Holistic Model to Replace an Entire Ecosystem

Senior Machine Learning Scientist – PayPal

Bio

Myriam has been a senior machine learning scientist at PayPal for almost two years. She focuses on developing models in the seller risk domain. Before joining PayPal, Myriam worked as an algorithm engineer in the medical domain. Myriam holds a BSc in Physics and Biology and an MSc and PhD in Neuroscience. Myriam also mentors Haredi women, helping them find jobs in the industry. In her free time, she loves traveling and discovering new places with her family.

Maya has been a machine learning scientist at PayPal for three and a half years, where she has been focused on creating real-time risk models. Prior to joining PayPal, she completed a BSc in Information Systems Engineering at the Technion’s Computer Science faculty. Maya is passionate about constructing data-driven solutions and is constantly seeking to learn about new machine learning methods that can be implemented at

Bio

Myriam has been a senior machine learning scientist at PayPal for almost two years. She focuses on developing models in the seller risk domain. Before joining PayPal, Myriam worked as an algorithm engineer in the medical domain. Myriam holds a BSc in Physics and Biology and an MSc and PhD in Neuroscience. Myriam also mentors Haredi women, helping them find jobs in the industry. In her free time, she loves traveling and discovering new places with her family.

Maya has been a machine learning scientist at PayPal for three and a half years, where she has been focused on creating real-time risk models. Prior to joining PayPal, she completed a BSc in Information Systems Engineering at the Technion’s Computer Science faculty. Maya is passionate about constructing data-driven solutions and is constantly seeking to learn about new machine learning methods that can be implemented at

Abstract

One of the main challenges in managing risk in large companies is maintaining a highly complex strategy composed of thousands of rules and dozens of AI models. This complexity may result in a lack of agility, long time to market, and high maintenance costs. 

In this talk, we will introduce a unique solution we developed at PayPal to face this issue, one that aims to improve and replace the majority of our current strategy ecosystem with one holistic model. 

In addition to the usual challenges of working with imbalance and diverse data, developing such a comprehensive model required us to go on a journey with our partners to redefine the problem, asking the right questions to refine their needs and creating a novel label. This process enabled us to create a model that has achieved a significant improvement over the current benchmark and has the potential to fully replace the current solution. For large companies like PayPal, this novel approach is groundbreaking.

Abstract

One of the main challenges in managing risk in large companies is maintaining a highly complex strategy composed of thousands of rules and dozens of AI models. This complexity may result in a lack of agility, long time to market, and high maintenance costs.
In this talk, we will introduce a unique solution we developed at PayPal to face this issue, one that aims to improve and replace the majority of our current strategy ecosystem with one holistic model.
In addition to the usual challenges of working with imbalance and diverse data, developing such a comprehensive model required us to go on a journey with our partners to redefine the problem, asking the right questions to refine their needs and creating a novel label. This process enabled us to create a model that has achieved a significant improvement over the current benchmark and has the potential to fully replace the current solution. For large companies like PayPal, this novel approach is groundbreaking.

Discussion Points

  • Data scientist role definitions – full stack data scientists vs. specialisations
  • Pure data science teams vs embedded teams
  • Data science reporting lines
  • Professional and personal development in embedded teams

Discussion Points

  • Data scientist role definitions – full stack data scientists vs. specialisations
  • Pure data science teams vs embedded teams
  • Data science reporting lines
  • Professional and personal development in embedded teams

Planned Agenda

8:45 Reception
9:30 Opening words by WiDS TLV ambassador Nitzan Gado and by Lily Ben Ami, CEO of the Michal Sela Forum
9:50 Prof. Bracha Shapira – Data Challenges in Recommender Systems Research: Insights from Bundle Recommendation
10:20 Juan Liu – Accounting Automation: Making Accounting Easier So That People Can Forget About It
10:50 Break
11:00 Lightning talks
12:20 Lunch & poster session
13:20 Roundtable session & poster session
14:05 Roundtable closure
14:20 Break
14:30 Merav Mofaz – “Every Breath You Take and Every Move You Make…I'll Be Watching You:” The Sensitive Side of Smartwatches
14:50 Reut Yaniv – Ad Serving in the Online Geo Space Along Routes
15:10 Rachel Wities - It’s Not Just the Doctor’s Handwriting: Challenges and Opportunities in Healthcare NLP
15:30 Closing remarks
15:40 End