SOURCE 2022 has ended
The mission of the Symposium of University Research and Creative Expression (SOURCE) is to provide a university-wide forum for Central Washington University (CWU) students, encouraging equity, diversity, and inclusivity, representing all disciplines and experience levels, to present their mentored research, scholarship, and creative works in a juried environment that meets professional conference standards and expectations.

The 2022 SOURCE program is hybrid. Pre-recorded virtual talks are colored green and can be watched anytime. Live/in-person sessions with Zoom access can be found in the daily schedule. Thank you for joining us!

To vote for the 2023 SOURCE poster, click here
To learn more about SOURCE or give to support the students of Central visit, https://www.cwu.edu/source
Connect on social media with @CentralWashU, @cwusource, #SOURCE2022, #CWUTogether
Back To Schedule
Wednesday, May 18 • 3:15pm - 3:30pm
Interpretable Machine Learning for Self-Service High-Risk Decision-Making

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.

Abstract—This presentation contributes to interpretable machine learning via visual knowledge discovery in general line coordinates (GLC). The concepts of hyperblocks as interpretable dataset units and general line coordinates are combined to create a visual self-service machine learning model. The DSC1 and DSC2 lossless multidimensional coordinate systems are proposed. DSC1 and DSC2 can map multiple dataset attributes to a single two-dimensional (X, Y) Cartesian plane using a graph construction algorithm. The hyperblock analysis was used to determine visually appealing dataset attribute orders and to reduce line occlusion. It is shown that hyperblocks can generalize decision tree rules and a series of DSC1 or DSC2 plots can visualize a decision tree. The DSC1 and DSC2 plots were tested on benchmark datasets from the UCI ML repository. They allowed for visual classification of data. Additionally, areas of hyperblock impurity were discovered and used to establish dataset splits that highlight the upper estimate of worst-case model accuracy to guide model selection for high-risk decision-making. Major benefits of DSC1 and DSC2 is their highly interpretable nature. They allow domain experts to control or establish new machine learning models through visual pattern discovery.


Charles Recaido

Graduate, Computer Science


Boris Kovalerchuk

Mentor, Computer Science;

Wednesday May 18, 2022 3:15pm - 3:30pm PDT
Student Union & Recreation Center (SURC) - Ballroom D

Attendees (1)