Fraud detection without feature engineering / Pamela Vagata.

Format:

Conference/Event

Video

Author/Creator:

Vagata, Pamela, on-screen presenter.

Conference Name:

O'Reilly Artificial Intelligence Conference (2019 : New York, New York)., issuing body.

Language:

English

Subjects (All):

Computer security.

Machine learning.

Computer crimes--Investigation.

Computer crimes.

Computer networks--Security measures.

Computer networks.

Physical Description:

1 online resource (1 streaming video file (40 min., 11 sec.)) : digital, sound, color

Place of Publication:

[Place of publication not identified] : O'Reilly, 2019.

Summary:

"Pamela Vagata (Stripe) explains how Stripe has applied deep learning techniques to predict fraud from raw behavioral data. Since fraud detection is a critical business problem for Stripe, the company already had a well-tuned feature-engineered model for comparison. Stripe found that the deep learning model outperforms the feature-engineered model both on predictive performance and in the effort spent on data engineering, model construction, tuning, and maintenance. Join in to discover how common industry practice could shift toward deeper models trained end to end and away from labor-intensive feature engineering."--Resource description page.

Participant:

Presenter, Pamela Vagata.

Notes:

Title from title screen (viewed November 14, 2019).

Recorded at the 2019 O'Reilly Artificial Intelligence Conference in New York.

OCLC:

1127651167