EventAction is a prescriptive analytics interface designed to present and explain recommendations of temporal event sequences. EventAction provides a visual analytics approach to (1) identify similar records, (2) explore potential outcomes, (3) review recommended temporal event sequences that might help achieve the users’ goals, and (4) interactively assist users as they define a personalized action plan associated with a probability of success. EventAction’s usage scenarios include student advising, treatment formulating, customer retention, and sports coaching.
- Fan Du, Ph.D. Candidate, Computer Science
- Catherine Plaisant, Research Scientist, UMIACS
- Ben Shneiderman, Professor, Computer Science
- Neil Spring, Associate Professor, Computer Science
- Final Summary paper (TIST’ 2019) TO APPEAR
Du, F., Plaisant, C., Spring, N., Crowley, K., and Shneiderman, B., EventAction: A Visual Analytics Approach to Explainable Recommendation for Event Sequences, ACM Trans. Interactive Intelligent Systems (2019) to appear.
- Ph.D Dissertation of Fan Du, from the Department of Computer Science (2018)
Explainable Recommendation for Event Sequences: A Visual Analytics Approach
- TIST’18: Introducing of the LikeMeDonuts visualization
Fan Du, Catherine Plaisant, Neil Spring, Ben Shneiderman. Visual Interfaces for Recommendation Systems: Finding Similar and Dissimilar Peers. ACM Transactions on Intelligent Systems and Technology, 10, 1, Article 9 (2019) 23 pages.
- CHI’17: Focuses on the problem of finding similar people
Fan Du, Catherine Plaisant, Neil Spring, Ben Shneiderman. Finding Similar People to Guide Life Choices: Challenge, Design, and Evaluation. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, 2017 (Best Paper Honorable Mention, top 5%).
- VAST’16: early paper describing the overall system
Fan Du, Catherine Plaisant, Neil Spring, Ben Shneiderman. EventAction: Visual Analytics for Temporal Event Sequence Recommendation. In Proceedings of the IEEE Visual Analytics Science and Technology, 2016
- Application to marketing (from Fan Du’s internship at ADOBE):
Fan Du, Sana Malik, Eunyee Koh, Georgios Theocharous. Interactive Campaign Planning for Marketing Analysts. CHI Extended Abstracts on Human Factors in Computing Systems, 2018.
- Application to travel recommendation (from Fan Du’s internship at ADOBE):
Personalizable and Interactive Sequence Recommender System, ACM CHI Extended Abstracts on Human Factors in Computing Systems, 2018.
- Early design with medical example:
Fan Du, Catherine Plaisant, Ben Shneiderman. What Did Others Like Me Do to Reach Their Health Goals? EventAction for Event Sequence Recommendations. Workshop on Valuable Visualization of Healthcare Information, AVI, 2016.
|Video demonstrating the final version of the EventAction system:|
|Videos showing the EventAction system and recommendation workflow (also see our VAST’16 paper):|
|Videos demonstrating PeerFinder, a visual interface that enables users to find and explore records that are similar to a seed record (also see our CHI’17 paper):|
Software – Want to use EventAction?
- Commercial Use:
EventAction is available for licensing from the UMd Store
If needed you can request a software review agreement or more information about licensing agreements that better suit your needs (e.g. access to source code) by contacting:
Office of Technology Commercialization (OTC)
2130 Mitchell Building
7999 Regents Dr.
University of Maryland
College Park, MD 20742
Phone: (301) 405-3947 | Fax: (301) 314-9502
- Non Profit / Academic Use
An academic license is also available from the UMd Store (with a reduced Non Profit/Academic licensing fee).
- Not sure? Special cases? Just testing?
We might be able to share EventAction temporarily for academic research. Contact firstname.lastname@example.org and describe your affiliation and project and we will do what we can to help you!
The press kit includes EventAction-related papers, figures, posters, and videos.