HF-SCA: Hands-Free Strong Customer Authentication Based on a Memory-Guided Attention Mechanisms

Cosimo Distante, Laura Fineo, Luca Mainetti, Luigi Manco, Benito Taccardi and Roberto Vergallo
Additional contact information
Cosimo Distante: Institute of Applied Sciences and Intelligent Systems (ISASI), National Research Council of Italy, 73100 Lecce, Italy
Laura Fineo: Department of Marketing, Banca Sella S.p.A., 13900 Biella, Italy
Luca Mainetti: Department of Innovation Engineering, University of Salento, 73100 Lecce, Italy
Luigi Manco: Vidyasoft s.r.l., 73047 Monteroni di Lecce, Italy
Benito Taccardi: Faculty of Engineering, University of Salento, 73100 Lecce, Italy
Roberto Vergallo: Department of Innovation Engineering, University of Salento, 73100 Lecce, Italy

JRFM, 2022, vol. 15, issue 8, 1-24

Abstract: Strong customer authentication (SCA) is a requirement of the European Union Revised Directive on Payment Services (PSD2) which ensures that electronic payments are performed with multifactor authentication. While increasing the security of electronic payments, the SCA impacted seriously on the shopping carts abandonment: an Italian bank computed that 22% of online purchases in the first semester of 2021 did not complete because of problems with the SCA. Luckily, the PSD2 allows the use of transaction risk analysis tool to exempt the SCA process. In this paper, we propose an unsupervised novel combination of existing machine learning techniques able to determine if a purchase is typical or not for a specific customer, so that in the case of a typical purchase the SCA could be exempted. We modified a well-known architecture (U-net) by replacing convolutional blocks with squeeze-and-excitation blocks. After that, a memory network was added in a latent space and an attention mechanism was introduced in the decoding side of the network. The proposed solution was able to detect nontypical purchases by creating temporal correlations between transactions. The network achieved 97.7% of AUC score over a well-known dataset retrieved online. By using this approach, we found that 98% of purchases could be executed by securely exempting the SCA, while shortening the customer’s journey and providing an elevated user experience. As an additional validation, we developed an Alexa skill for Amazon smart glasses which allows a user to shop and pay online by merely using vocal interaction, leaving the hands free to perform other activities, for example driving a car.

Keywords: strong customer authentication; transaction risk analysis; risk-based assessment; PSD2; machine learning; user experience; vocal interaction (search for similar items in EconPapers)
JEL-codes: C E F2 F3 G (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/1911-8074/15/8/342/pdf (application/pdf)
https://www.mdpi.com/1911-8074/15/8/342/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jjrfmx:v:15:y:2022:i:8:p:342-:d:879383

Access Statistics for this article

JRFM is currently edited by Ms. Chelthy Cheng

More articles in JRFM from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().