In this paper, we introduce a proof of concept that addresses the assumption and limitation of linear local boundaries by Local Interpretable Model-Agnostic Explanations (LIME), a popular technique used to add interpretability and explainability to black box models. LIME is a versatile explainer capable of handling different types of data and models. At the local level, LIME creates a linear relationship for a given prediction through generated sample points to present feature importance. We redefine the linear relationships presented by LIME as quadratic relationships and expand its flexibility in non-linear cases and improve the accuracy of feature interpretations. We coin this use of quadratic relationships as QLIME and demonstrate its viability by comparing its utility to LIME on a black box model. Using data from a global staffing company, the goal of the model is to predict successful candidate placements. QLIME adds explainability to the model and shows an improvement for both successful and unsuccessful predictions, and our quadratic approach is validated with mean squared error (MSE) improvements of 3.8% and 2.9%.
Bramhall, Steven; Horn, Hayley; Tieu, Michael; and Lohia, Nibhrat
"QLIME-A Quadratic Local Interpretable Model-Agnostic Explanation Approach,"
SMU Data Science Review: Vol. 3:
1, Article 4.
Available at: https://scholar.smu.edu/datasciencereview/vol3/iss1/4
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License
Business Analytics Commons, Business Intelligence Commons, Computational Engineering Commons, Management Sciences and Quantitative Methods Commons, Other Computer Engineering Commons, Risk Analysis Commons, Robotics Commons, Technology and Innovation Commons