SellTrend: Visualizing Multi-Attribute Temporal Transactions for Anomaly Detection

Team Members: Zhicheng Liu, John Stasko

    Video - System Overview and Usage Scenario (18.2 MB mov)

    SellTrend: Inter-Attribute Visual Analysis of Temporal Transaction Data - InfoVis 2009, (Honorable Mention Best Paper)

SellTrend is a visualization system for analyzing airline travel purchase requests. Such transaction data can be characterized as multi-variate temporal and categorical event sequences, and the chief problem addressed is how to help analysts identify complex combinations of transaction attributes that contribute to failed purchase requests.

SellTrend combines a diverse set of techniques ranging from time series visualization to faceted browsing and historical trend analysis. Analysts are able to achieve a high-level real-time awareness of the transaction processes, and they can conduct more in-depth interactive visual analyses whenever something interesting calls for detailed attention.

This research is supported in part by a funding from Travelport Corp.