Forecasting Live Chat Intent from Browsing History
This addresses a domain-specific problem for online customer service by improving intent prediction from browsing history, though it appears incremental as it builds on existing Transformer and LLM methods.
The paper tackles the problem of predicting user intent from browsing history for online live chat, proposing a two-stage approach that first classifies browsing history into high-level intent categories using fine-tuned Transformers, then uses an LLM to generate fine-grained intents, resulting in significant performance gains compared to generating intents without classification.
Customers reach out to online live chat agents with various intents, such as asking about product details or requesting a return. In this paper, we propose the problem of predicting user intent from browsing history and address it through a two-stage approach. The first stage classifies a user's browsing history into high-level intent categories. Here, we represent each browsing history as a text sequence of page attributes and use the ground-truth class labels to fine-tune pretrained Transformers. The second stage provides a large language model (LLM) with the browsing history and predicted intent class to generate fine-grained intents. For automatic evaluation, we use a separate LLM to judge the similarity between generated and ground-truth intents, which closely aligns with human judgments. Our two-stage approach yields significant performance gains compared to generating intents without the classification stage.