Visualizing Uncertainty and Alternatives in Event Sequence Predictions

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI 2019)

Publication date: January 4, 2019

Shunan Guo, Fan Du, Sana Malik, Eunyee Koh, Sungchul Kim, Leo Zhicheng Liu, Donghyun Kim, Hongyuan Zha, Nan Cao

Data analysts apply machine learning and statistical methods to timestamped event sequences to tackle various problems but face unique challenges when interpreting the results. Especially in event sequence prediction, it is difficult to convey uncertainty and possible alternative paths or outcomes. In this work, informed by interviews with five machine learning practitioners, we iteratively designed a novel visualization for exploring event sequence predictions of multiple records where users are able to review the most probable predictions and possible alternatives alongside uncertainty information. Through a controlled study with 18 participants, we found that users are more confident in making decisions when alternative predictions are displayed and they consider the alternatives more when deciding between two options with similar top predictions.