Menu
Menu
Maximizing Model Performance and Efficiency Through Intelligent Feature Selection
Data Scientist – Wix
Maximizing Model Performance and Efficiency Through Intelligent Feature Selection
Data Scientist – Wix
Irma is a data scientist at Wix. During her time at Wix, Irma has focused on providing end-to-end solutions for business problems, including building and deploying machine learning models that have had a positive impact on user experience for millions of Wix users every day. Working on those projects helped Irma gain extensive experience in classic ML models, causal inference models, and NLP.
She has a strong background in data analysis, with over 10 years of experience working as an analyst in various industries, including the technological unit at 8200.
Irma is a data scientist at Wix. During her time at Wix, Irma has focused on providing end-to-end solutions for business problems, including building and deploying machine learning models that have had a positive impact on user experience for millions of Wix users every day. Working on those projects helped Irma gain extensive experience in classic ML models, causal inference models, and NLP.
She has a strong background in data analysis, with over 10 years of experience working as an analyst in various industries, including the technological unit at 8200.
Features are an essential part of any data science model. The choice of features can greatly impact the model’s performance but also its efficiency. Therefore, data scientists should consider other factors beyond the predictive power of the feature, such as the cost of generating the feature, the integrity of the data, the potential for data drift over time, and the maintenance required to keep the feature up to date.
This talk shares a practical approach of generating a combined feature selection criteria that uses the quantification of the factors mentioned above. This allows data scientists to make informed decisions about the features, taking into account the tradeoff between performance and efficiency. Applying this approach at Wix reduced the model’s daily cost by 30% and minimized the maintenance needs of the production model.
Features are an essential part of any data science model. The choice of features can greatly impact the model’s performance but also its efficiency. Therefore, data scientists should consider other factors beyond the predictive power of the feature, such as the cost of generating the feature, the integrity of the data, the potential for data drift over time, and the maintenance required to keep the feature up to date.
This talk shares a practical approach of generating a combined feature selection criteria that uses the quantification of the factors mentioned above. This allows data scientists to make informed decisions about the features, taking into account the tradeoff between performance and efficiency. Applying this approach at Wix reduced the model’s daily cost by 30% and minimized the maintenance needs of the production model.
| 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 |
WiDS Tel Aviv is an independent event that is organized by Intuit’s WiDS TLV ambassadors as part of the annual WiDS Worldwide conference, the WiDS Datathon, and an estimated 200 WiDS Regional Events worldwide. Everyone is invited to attend all WiDS conference and WiDS Datathon Workshop events which feature outstanding women doing outstanding work.
© 2018-2023 WiDS TLV – Intuit. All rights reserved.
Scotty – By Nir Azoulay
Design: Sharon Geva
