RATSF: Empowering Customer Service Volume Management through Retrieval-Augmented Time-Series Forecasting
This work addresses the challenge of non-stationary data in customer service management for businesses, offering a flexible and effective forecasting solution that is incremental in its integration with existing Transformer variants.
The paper tackled the problem of forecasting customer service volume by developing a retrieval-augmented framework that leverages similar historical data, resulting in significant performance enhancements in hotel service volume forecasting with demonstrated generalizability across scenarios.
An efficient customer service management system hinges on precise forecasting of service volume. In this scenario, where data non-stationarity is pronounced, successful forecasting heavily relies on identifying and leveraging similar historical data rather than merely summarizing periodic patterns. Existing models based on RNN or Transformer architectures may struggle with this flexible and effective utilization. To tackle this challenge, we initially developed the Time Series Knowledge Base (TSKB) with an advanced indexing system for efficient historical data retrieval. We also developed the Retrieval Augmented Cross-Attention (RACA) module, a variant of the cross-attention mechanism within Transformer's decoder layers, designed to be seamlessly integrated into the vanilla Transformer architecture to assimilate key historical data segments. The synergy between TSKB and RACA forms the backbone of our Retrieval-Augmented Time Series Forecasting (RATSF) framework. Based on the above two components, RATSF not only significantly enhances performance in the context of Fliggy hotel service volume forecasting but also adapts flexibly to various scenarios and integrates with a multitude of Transformer variants for time-series forecasting. Extensive experimentation has validated the effectiveness and generalizability of this system design across multiple diverse contexts.