Hierarchical Fallback Architecture for High Risk Online Machine Learning Inference
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929691012628480 |
|---|---|
| author | Polleti, Gustavo Santana, Marlesson Del Sant, Felipe Sassi Fontes, Eduardo |
| author_facet | Polleti, Gustavo Santana, Marlesson Del Sant, Felipe Sassi Fontes, Eduardo |
| contents | Open Banking powered machine learning applications require novel robustness approaches to deal with challenging stress and failure scenarios. In this paper we propose an hierarchical fallback architecture for improving robustness in high risk machine learning applications with a focus in the financial domain. We define generic failure scenarios often found in online inference that depend on external data providers and we describe in detail how to apply the hierarchical fallback architecture to address them. Finally, we offer a real world example of its applicability in the industry for near-real time transactional fraud risk evaluation using Open Banking data and under extreme stress scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_17834 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hierarchical Fallback Architecture for High Risk Online Machine Learning Inference Polleti, Gustavo Santana, Marlesson Del Sant, Felipe Sassi Fontes, Eduardo Machine Learning Computational Engineering, Finance, and Science Software Engineering I.2.m Open Banking powered machine learning applications require novel robustness approaches to deal with challenging stress and failure scenarios. In this paper we propose an hierarchical fallback architecture for improving robustness in high risk machine learning applications with a focus in the financial domain. We define generic failure scenarios often found in online inference that depend on external data providers and we describe in detail how to apply the hierarchical fallback architecture to address them. Finally, we offer a real world example of its applicability in the industry for near-real time transactional fraud risk evaluation using Open Banking data and under extreme stress scenarios. |
| title | Hierarchical Fallback Architecture for High Risk Online Machine Learning Inference |
| topic | Machine Learning Computational Engineering, Finance, and Science Software Engineering I.2.m |
| url | https://arxiv.org/abs/2501.17834 |