Fraud detection without feature engineering /

"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 l...

Descripción completa

Detalles Bibliográficos
Clasificación:Libro Electrónico
Autor Corporativo: O'Reilly Artificial Intelligence Conference
Formato: Electrónico Congresos, conferencias Video
Idioma:Inglés
Publicado: [Place of publication not identified] : O'Reilly, 2019.
Temas:
Computer security.
Machine learning.
Computer crimes > Investigation.
Computer networks > Security measures.
Computer Security
Sécurité informatique.
Apprentissage automatique.
Criminalité informatique > Enquêtes.
Réseaux d'ordinateurs > Sécurité > Mesures.
Acceso en línea:Texto completo (Requiere registro previo con correo institucional)
Descripción
Sumario:"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
Notas:Title from title screen (viewed November 14, 2019).
Descripción Física:1 online resource (1 streaming video file (40 min., 11 sec.))

Ejemplares similares