Production and Operations Management· 2026Q1
EXPRESS: Let Clickstream Talk: A Graph Neural Network Approach to Sales Forecasting
- 0citations
- Q1SCImago
- 2026year
Short summary
A new deep learning framework, ForecastClickGraph, uses clickstream data to forecast sales by modeling consumer journeys as a dynamic graph, outperforming benchmarks by 10-28% in accuracy.
AI-generated from the title and abstract; the full text is not read.
Key points
- ForecastClickGraph models consumer shopping journeys as dynamic graphs of product-stage interactions.
- It uses a graph neural network to learn product representations incorporating temporal patterns and cross-product associations.
- The framework predicts sales distributions using quantile regression, improving probabilistic forecasts.
- Experiments show 10-28% higher accuracy than benchmarks, especially for promotional sales.
AI-generated from the title and abstract; the full text is not read.
Abstract
Abstract This paper proposes ForecastClickGraph, a deep learning framework that extracts cross-product relationships and demand information from clickstream data for probabilistic sales forecasting. ForecastClickGraph models stages in consumer shopping journeys as a dynamic graph, where nodes represent individual product-stage combinations, such as product A viewed or added to cart, and directed edges capture the transitions between stages. A customized graph neural network learns product representations that incorporate both product-level temporal patterns and cross-product associations. Another graph-based module further detects demand spikes using early signals from related products. ForecastClickGraph cross-learns demand patterns across large-scale products and estimates demand distributions through quantile regression. Extensive experiments on a real-world dataset show that ForecastClickGraph outperforms state-of-the-art benchmark models by 10-28% in forecast accuracy, with particularly strong performance in predicting promotional sales bursts. It also yields superior probabilistic forecasts with substantially lower quantile loss and improved calibration relative to benchmarks.
The authors' abstract, as published at the source. Production and Operations Management, 2026 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Management Science and Operations Research
Management Science and Operations ResearchDecision Sciences