Please use this identifier to cite or link to this item: http://hdl.handle.net/10125/63859

Model Interpretation and Explainability towards Creating Transparency in Prediction Models

File Size Format  
0096.pdf 707.89 kB Adobe PDF View/Open

Item Summary

Title:Model Interpretation and Explainability towards Creating Transparency in Prediction Models
Authors:Dolk, Daniel
Kridel, Donald
Dineen, Jacob
Castillo, David
Keywords:Big Data and Analytics: Pathways to Maturity
explainable ai
explainable models
prrediction models
Date Issued:07 Jan 2020
Abstract:Explainable AI (XAI) has a counterpart in analytical modeling which we refer to as model explainability. We tackle the issue of model explainability in the context of prediction models. We analyze a dataset of loans from a credit card company and apply three stages: execute and compare four different prediction methods, apply the best known explainability techniques in the current literature to the model training sets to identify feature importance (FI) (static case), and finally to cross-check whether the FI set holds up under “what if” prediction scenarios for continuous and categorical variables (dynamic case). We found inconsistency in FI identification between the static and dynamic cases. We summarize the “state of the art” in model explainability and suggest further research to advance the field.
Pages/Duration:10 pages
URI:http://hdl.handle.net/10125/63859
ISBN:978-0-9981331-3-3
DOI:10.24251/HICSS.2020.120
Rights:Attribution-NonCommercial-NoDerivatives 4.0 International
https://creativecommons.org/licenses/by-nc-nd/4.0/
Appears in Collections: Big Data and Analytics: Pathways to Maturity


Please email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.

This item is licensed under a Creative Commons License Creative Commons