Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2604.08649 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917398166110208 |
|---|---|
| author | Ostroukhov, Maxim Mikhailov, Ruslan Iashin, Vladimir Sokolov, Artem Akshonov, Andrei Protasov, Vitaly Beloborodov, Dmitrii Mullin, Vince Enzmann, Roman Yokunda Kolovos, Georgios Renders, Jason Nesterov, Pavel Repushko, Anton |
| author_facet | Ostroukhov, Maxim Mikhailov, Ruslan Iashin, Vladimir Sokolov, Artem Akshonov, Andrei Protasov, Vitaly Beloborodov, Dmitrii Mullin, Vince Enzmann, Roman Yokunda Kolovos, Georgios Renders, Jason Nesterov, Pavel Repushko, Anton |
| contents | Modern financial systems generate vast quantities of transactional and event-level data that encode rich economic signals. This paper presents PRAGMA, a family of foundation models for multi-source banking event sequences. Our approach pre-trains a Transformer-based architecture with masked modelling on a large-scale, heterogeneous banking event corpus using a self-supervised objective tailored to the discrete, variable-length nature of financial records. The resulting model supports a wide range of downstream tasks such as credit scoring, fraud detection, and lifetime value prediction: strong performance can be achieved by training a simple linear model on top of the extracted embeddings and can be further improved with lightweight fine-tuning. Through extensive evaluation on downstream tasks, we demonstrate that PRAGMA achieves superior performance across multiple domains directly from raw event sequences, providing a general-purpose representation layer for financial applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_08649 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PRAGMA: Revolut Foundation Model Ostroukhov, Maxim Mikhailov, Ruslan Iashin, Vladimir Sokolov, Artem Akshonov, Andrei Protasov, Vitaly Beloborodov, Dmitrii Mullin, Vince Enzmann, Roman Yokunda Kolovos, Georgios Renders, Jason Nesterov, Pavel Repushko, Anton Machine Learning Computational Engineering, Finance, and Science Computation and Language Information Retrieval Computational Finance Modern financial systems generate vast quantities of transactional and event-level data that encode rich economic signals. This paper presents PRAGMA, a family of foundation models for multi-source banking event sequences. Our approach pre-trains a Transformer-based architecture with masked modelling on a large-scale, heterogeneous banking event corpus using a self-supervised objective tailored to the discrete, variable-length nature of financial records. The resulting model supports a wide range of downstream tasks such as credit scoring, fraud detection, and lifetime value prediction: strong performance can be achieved by training a simple linear model on top of the extracted embeddings and can be further improved with lightweight fine-tuning. Through extensive evaluation on downstream tasks, we demonstrate that PRAGMA achieves superior performance across multiple domains directly from raw event sequences, providing a general-purpose representation layer for financial applications. |
| title | PRAGMA: Revolut Foundation Model |
| topic | Machine Learning Computational Engineering, Finance, and Science Computation and Language Information Retrieval Computational Finance |
| url | https://arxiv.org/abs/2604.08649 |