Or Levi – VP Data Science, Founder AdVerif.AI (Acquired)

Or Levi is an AI Researcher specializing in Natural Language Processing and Computational Advertising. His work has been presented in leading AI conferences and covered by international media.

Or’s strongest passion is using AI for social impact, which led him to found AI startup AdCVerif.AI with the purpose of fighting the spread of misinformation and hate speech online. AdVerif.ai is a member of Microsoft’s AI for Good initiative and was named among CB Insights’ International Game Changers – startups with potential to transform society and economies for the better.

CB Insights game changers

Or holds a M.Sc. (Magna Cum Laude) in Information Retrieval from the Technion, the Israel Institute of Technology. In his spare time, he enjoys playing sports and teaching deep recurrent neural networks to generate humor 😊

Research

PUBLICATIONS:

Organic Ponies and Sponsored Batteries: A Category-Based CTR Optimization Model
O Levi
Proceedings of the SIGIR 2019 Workshop on eCommerce, co-located with the 42nd International ACM SIGIR Conference

Selective cluster-based document retrieval
O Levi, F Raiber, O Kurland, I Guy
Proceedings of the 25th ACM International on Conference on Information and Knowledge Management

Selective Cluster Presentation on the Search Results Page
O Levi, I Guy, F Raiber, O Kurland
ACM Transactions on Information Systems (TOIS) 36 (3), 28

Online Learning of a Ranking Formula for Revenue and Advertiser ROI Optimization
O Levi
ICTIR 2017, LEARNER – 1st International Workshop on Learning Next Generation Rankers

PATENTS:

SOCIAL NETWORK INITIATED LISTINGS – Application No. 15/705,913
Or Levi et al.
Invented and developed a patented technology for selling on ecommerce sites via social networks.
Winner of the Excellence in Innovation Award out of 219 hackthon demos worldwide

FUN PROJECTS:

FunnyBot – Can Machines Tell Jokes? A Deep Recurrent Neural Network in TensorFlow
Taking up on Open-AI requests for research: an implementation of word-level LSTM in TensorFlow trained on a 200k English jokes dataset.
Work in progress – (hopefully) funny jokes to follow!

Playing Pac-man with Artificial Intelligence / Reinforcement Learning
Solving the Pac-man game as a Markov Decision Process problem with the aim of learning an optimal policy using a value-iteration approach.

Contact

I’D LOVE TO HEAR FROM YOU