AAAI Publications, 2018 AAAI Spring Symposium Series

Font Size: 
Customers’ Retention Requires an Explainability Feature in Machine Learning Systems They Use
Boris Galitsky

Last modified: 2018-03-15

Abstract


We formulate a question of how important explainability feature is for customers of machine learning (ML) systems. We analyze the state of the art and limitations of explainable and unexplainable ML. To quantitatively estimate the volume of customers who request explainability from companies employing ML systems, we analyze customer complaints. We build a natural language (NL) classifier that detects a request to explain in implicit or explicit form, and evaluate it on the set of 800 complaints. As a result of classifier application, we discover that a quarter of customers demand explainability from companies, when something went wrong with a product or service and it has to be communicated properly by the company. We conclude that explainability feature is more important than the recognition accuracy for most customers.

Keywords


explainability of machine learning; deep learning; customer complaints

Full Text: PDF