Anzeige
Erschienen in:
2018 | OriginalPaper | Buchkapitel
Machine Learning Applied to Point-of-Sale Fraud Detection
verfasst von : Christine Hines, Abdou Youssef
Erschienen in: Machine Learning and Data Mining in Pattern Recognition
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
This paper applies machine learning (ML) techniques including neural networks, support vector machines Random Forest, and Adaboost to detecting insider fraud in restaurant point-of-sales data. With considerable engineering of the features, and by applying under-sampling techniques we show that ML techniques deliver very high fraud-detection performance. In particular, RandomForest can achieve 91% or better across all metrics when using a model trained on one restaurant to detect fraud in a separate restaurant. However, there must be sufficient fraud samples in the model for this to occur. Knowledge and techniques from this research could be used to develop a low-cost product to automate fraud detection for restaurant owners.