Learning transactions representations for information management in banks: Mastering local, global, and external knowledge
In today’s world, banks use artificial intelligence to optimize diverse business processes, aiming to improve customer experience. Most of the customer-related tasks can be categorized into two groups: (1) local ones, which focus on a client’s current state, such as transaction forecasting, and (2)...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | International Journal of Information Management Data Insights |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2667096825000059 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825206844195340288 |
|---|---|
| author | Alexandra Bazarova Maria Kovaleva Ilya Kuleshov Evgenia Romanenkova Alexander Stepikin Aleksandr Yugay Dzhambulat Mollaev Ivan Kireev Andrey Savchenko Alexey Zaytsev |
| author_facet | Alexandra Bazarova Maria Kovaleva Ilya Kuleshov Evgenia Romanenkova Alexander Stepikin Aleksandr Yugay Dzhambulat Mollaev Ivan Kireev Andrey Savchenko Alexey Zaytsev |
| author_sort | Alexandra Bazarova |
| collection | DOAJ |
| description | In today’s world, banks use artificial intelligence to optimize diverse business processes, aiming to improve customer experience. Most of the customer-related tasks can be categorized into two groups: (1) local ones, which focus on a client’s current state, such as transaction forecasting, and (2) global ones, which consider the general customer behaviour, e.g., predicting successful loan repayment. Unfortunately, maintaining separate models for each task is costly. Therefore, to better facilitate information management, we compared eight state-of-the-art unsupervised methods on 11 tasks in search for a one-size-fits-all solution. Contrastive self-supervised learning methods were demonstrated to excel at global problems, while generative techniques were superior at local tasks. We also introduced a novel approach, which enriches the client’s representation by incorporating external information gathered from other clients. Our method outperforms classical models, boosting accuracy by up to 20%. |
| format | Article |
| id | doaj-art-0c241a8f9e7445a7a6b152ccadc7c1a6 |
| institution | Kabale University |
| issn | 2667-0968 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Information Management Data Insights |
| spelling | doaj-art-0c241a8f9e7445a7a6b152ccadc7c1a62025-02-07T04:48:29ZengElsevierInternational Journal of Information Management Data Insights2667-09682025-06-0151100323Learning transactions representations for information management in banks: Mastering local, global, and external knowledgeAlexandra Bazarova0Maria Kovaleva1Ilya Kuleshov2Evgenia Romanenkova3Alexander Stepikin4Aleksandr Yugay5Dzhambulat Mollaev6Ivan Kireev7Andrey Savchenko8Alexey Zaytsev9Skolkovo Institute of Science and Technology (Skoltech), Bolshoy Boulevard, 30 p.1, Moscow, 121205, RussiaSkolkovo Institute of Science and Technology (Skoltech), Bolshoy Boulevard, 30 p.1, Moscow, 121205, RussiaSkolkovo Institute of Science and Technology (Skoltech), Bolshoy Boulevard, 30 p.1, Moscow, 121205, Russia; Corresponding author.Skolkovo Institute of Science and Technology (Skoltech), Bolshoy Boulevard, 30 p.1, Moscow, 121205, RussiaSkolkovo Institute of Science and Technology (Skoltech), Bolshoy Boulevard, 30 p.1, Moscow, 121205, RussiaSkolkovo Institute of Science and Technology (Skoltech), Bolshoy Boulevard, 30 p.1, Moscow, 121205, RussiaSber AI Lab, Kutuzovsky Avenue, 32, Moscow, 121165, RussiaSber AI Lab, Kutuzovsky Avenue, 32, Moscow, 121165, RussiaSber AI Lab, Kutuzovsky Avenue, 32, Moscow, 121165, RussiaSkolkovo Institute of Science and Technology (Skoltech), Bolshoy Boulevard, 30 p.1, Moscow, 121205, RussiaIn today’s world, banks use artificial intelligence to optimize diverse business processes, aiming to improve customer experience. Most of the customer-related tasks can be categorized into two groups: (1) local ones, which focus on a client’s current state, such as transaction forecasting, and (2) global ones, which consider the general customer behaviour, e.g., predicting successful loan repayment. Unfortunately, maintaining separate models for each task is costly. Therefore, to better facilitate information management, we compared eight state-of-the-art unsupervised methods on 11 tasks in search for a one-size-fits-all solution. Contrastive self-supervised learning methods were demonstrated to excel at global problems, while generative techniques were superior at local tasks. We also introduced a novel approach, which enriches the client’s representation by incorporating external information gathered from other clients. Our method outperforms classical models, boosting accuracy by up to 20%.http://www.sciencedirect.com/science/article/pii/S2667096825000059Representation learningDeep learningFinancial transactional dataExternal context |
| spellingShingle | Alexandra Bazarova Maria Kovaleva Ilya Kuleshov Evgenia Romanenkova Alexander Stepikin Aleksandr Yugay Dzhambulat Mollaev Ivan Kireev Andrey Savchenko Alexey Zaytsev Learning transactions representations for information management in banks: Mastering local, global, and external knowledge International Journal of Information Management Data Insights Representation learning Deep learning Financial transactional data External context |
| title | Learning transactions representations for information management in banks: Mastering local, global, and external knowledge |
| title_full | Learning transactions representations for information management in banks: Mastering local, global, and external knowledge |
| title_fullStr | Learning transactions representations for information management in banks: Mastering local, global, and external knowledge |
| title_full_unstemmed | Learning transactions representations for information management in banks: Mastering local, global, and external knowledge |
| title_short | Learning transactions representations for information management in banks: Mastering local, global, and external knowledge |
| title_sort | learning transactions representations for information management in banks mastering local global and external knowledge |
| topic | Representation learning Deep learning Financial transactional data External context |
| url | http://www.sciencedirect.com/science/article/pii/S2667096825000059 |
| work_keys_str_mv | AT alexandrabazarova learningtransactionsrepresentationsforinformationmanagementinbanksmasteringlocalglobalandexternalknowledge AT mariakovaleva learningtransactionsrepresentationsforinformationmanagementinbanksmasteringlocalglobalandexternalknowledge AT ilyakuleshov learningtransactionsrepresentationsforinformationmanagementinbanksmasteringlocalglobalandexternalknowledge AT evgeniaromanenkova learningtransactionsrepresentationsforinformationmanagementinbanksmasteringlocalglobalandexternalknowledge AT alexanderstepikin learningtransactionsrepresentationsforinformationmanagementinbanksmasteringlocalglobalandexternalknowledge AT aleksandryugay learningtransactionsrepresentationsforinformationmanagementinbanksmasteringlocalglobalandexternalknowledge AT dzhambulatmollaev learningtransactionsrepresentationsforinformationmanagementinbanksmasteringlocalglobalandexternalknowledge AT ivankireev learningtransactionsrepresentationsforinformationmanagementinbanksmasteringlocalglobalandexternalknowledge AT andreysavchenko learningtransactionsrepresentationsforinformationmanagementinbanksmasteringlocalglobalandexternalknowledge AT alexeyzaytsev learningtransactionsrepresentationsforinformationmanagementinbanksmasteringlocalglobalandexternalknowledge |