Effective processing of financial transactions is essential for banking data analysis. However, in this domain, most methods focus on specialized solutions to stand-alone problems instead of constructing universal representations suitable for many problems. We present a representation learning framework that addresses diverse business challenges. We also suggest novel generative models that account for data specifics, and a way to integrate external information into a client's representation, leveraging insights from other customers' actions. Finally, we offer a benchmark, describing representation quality globally, concerning the entire transaction history; locally, reflecting the client's current state; and dynamically, capturing representation evolution over time. Our generative approach demonstrates superior performance in local tasks, with an increase in ROC-AUC of up to 14\% for the next MCC prediction task and up to 46\% for downstream tasks from existing contrastive baselines. Incorporating external information improves the scores by an additional 20\%.

翻译：金融交易的有效处理对银行数据分析至关重要。然而在该领域，多数方法专注于解决独立问题的专用方案，而非构建适用于多类问题的通用表示。我们提出一种表示学习框架，可应对多样化的业务挑战。同时提出考虑数据特性的新型生成模型，以及将外部信息整合至客户表示的方法——通过利用其他客户行为的洞察。最后，我们构建基准测试，从三个维度描述表示质量：全局层面（关联完整交易历史）、局部层面（反映客户当前状态）及动态层面（捕捉表示随时间的演化）。在局部任务中，我们的生成方法表现优异，相比现有对比基线，下一MCC预测任务的ROC-AUC提升最高达14%，下游任务提升最高达46%；整合外部信息可使分数额外提升20%。