Invoice Subject Line Recommender – When Behavioral Science Meets Machine Learning
Invoice Subject Line Recommender – When Behavioral Science Meets Machine Learning
Sheer is a Data Scientist at Intuit. In the past two years, she worked on fraud prevention models, and now she is a part of an AI invoicing mission team. Before joining Intuit, Sheer worked at the Weizmann Institute of Science as a data scientist, leading on-demand projects, including collaboration with top Israel universities. Sheer holds an M.Sc. in Brain Science from the Weizmann Institute of Science and a B.Sc. in Biology and Cognition with honors from the Hebrew University of Jerusalem.
Sheer is a Data Scientist at Intuit. In the past two years, she worked on fraud prevention models, and now she is a part of an AI invoicing mission team. Before joining Intuit, Sheer worked at the Weizmann Institute of Science as a data scientist, leading on-demand projects, including collaboration with top Israel universities. Sheer holds an M.Sc. in Brain Science from the Weizmann Institute of Science and a B.Sc. in Biology and Cognition with honors from the Hebrew University of Jerusalem.
From Netflix to Spotify, the demand for personalization increases over time and can pay off both for the consumer and the relationship with the brand. One of the reinforcement learning algorithms designed to tackle this problem is Contextual Bandit. Contextual Bandit allows one to find the best strategy for a given user based on historical data and update the strategy overtime when the context changes. On a live field experiment with over 100K users, we explored a few Contextual Bandit applications, an existing library, and our implementation. By evaluating the results both in an off-policy setting, we suggest no single perfect solution.
From Netflix to Spotify, the demand for personalization increases over time and can pay off both for the consumer and the relationship with the brand. One of the reinforcement learning algorithms designed to tackle this problem is Contextual Bandit. Contextual Bandit allows one to find the best strategy for a given user based on historical data and update the strategy overtime when the context changes. On a live field experiment with over 100K users, we explored a few Contextual Bandit applications, an existing library, and our implementation. By evaluating the results both in an off-policy setting, we suggest no single perfect solution.
| 8:45 | Reception |
|---|---|
| 9:30 | Opening words by WiDS TLV ambassadors Or Basson and Noah Eyal Altman |
| 9:40 | Dr. Kira Radinski - Learning to predict the future of healthcare |
| 10:10 | Prof. Yonina Eldar - Model-Based Deep Learning: Applications to Imaging and Communications |
| 10:40 | Break |
| 10:50 | Lightning talks |
| 12:20 | Lunch & Poster session |
|---|---|
| 13:20 | Roundtable session & Poster session |
| 14:05 | Roundtable closure |
| 14:20 | Break |
| 14:30 | Dr. Anna Levant - 3D Metrology: Seeing the Unseen |
| 15:00 | Aviv Ben-Arie - Counterfactual Explanations: The Future of Explainable AI? |
| 15:30 | Closing remarks |
| 15:40 | End |
© 2018-2022 WiDS TLV – Intuit. All rights reserved.
Scotty – By Nir Azoulay
Design: Sharon Geva