Nos derniers articles

4 résultats pour « frauddetection »

Deep Semi‑Supervised Anomaly Detection for Finding Fraud in the Futures Market

4 sept. 2023 Autre, fraud, frauddetection, anomalydetection, financialdata, supervisedlearning

"#frauddetection is overwhelmingly associated with the greater field of #anomalydetection, which is usually performed via unsupervised learning techniques because of the lack of labeled data needed for #supervisedlearning. However, a small quantity of labeled data does often exist. This research article aims to evaluate the efficacy of a deep semi-supervised anomaly detection technique, called Deep SAD, for detecting #fraud in high-frequency #financialdata."

Need for Artificial Intelligence (Ai) to Be Explainable in Banking and Finance

29 août 2023 Autre, ai, riskassessment, banking, decisionmaking, ethical, transparency, frauddetection, xai, fairness, algorithm, accountability

The essential role of #ai in #banking holds promise for efficiency, but faces challenges like the opaque "black box" issue, hindering #fairness and #transparency in #decisionmaking #algorithms. Substituting AI with Explainable AI (#xai) can mitigate this problem, ensuring #accountability and #ethical standards. Research on XAI in finance is extensive but often limited to specific cases like #frauddetection and credit #riskassessment.

A Primer on Anomaly and Fraud Detection in Blockchain Networks

9 janv. 2023 Autre, machinelearning, frauddetection, gametheory, blockchain, anomalydetection

"... blockchain networks are vulnerable to anomalies and frauds that can have serious consequences for the integrity and security of these networks. In this primer, we provide an overview of the definition and properties of blockchain technology, and discuss the types and examples of anomalies and frauds that occur in these networks."

A Time Series Approach to Explainability for Neural Nets with Applications to Risk‑Management

7 déc. 2022 Autre, riskmanagement, artificialintelligence, deeplearning, frauddetection, xai

"We here propose a novel XAI [eXplainable AI] technique for deep learning methods (DL) which preserves and exploits the natural time ordering of the data. Simple applications to financial data illustrate the potential of the new approach in the context of risk-management and fraud-detection."

Une question ? Une collaboration ?
Contactez‑nous dès aujourd'hui

Nom

Téléphone

E-Mail

Message

Votre message a bien été envoyé

Metametris
6 rue d’Armaillé
75017 - Paris

du lundi au vendredi
de 8h à 18h

06 07 91 04 29