DeepAI AI Chat
Log In Sign Up

A Design Space for Explainable Ranking and Ranking Models

by   I. Al Hazwani, et al.

Item ranking systems support users in multi-criteria decision-making tasks. Users need to trust rankings and ranking algorithms to reflect user preferences nicely while avoiding systematic errors and biases. However, today only few approaches help end users, model developers, and analysts to explain rankings. We report on the study of explanation approaches from the perspectives of recommender systems, explainable AI, and visualization research and propose the first cross-domain design space for explainers of item rankings. In addition, we leverage the descriptive power of the design space to characterize a) existing explainers and b) three main user groups involved in ranking explanation tasks. The generative power of the design space is a means for future designers and developers to create more target-oriented solutions in this only weakly exploited space.


page 1

page 2

page 3


Faithfully Explaining Rankings in a News Recommender System

There is an increasing demand for algorithms to explain their outcomes. ...

Personalization in E-Grocery: Top-N versus Top-k Rankings

Business success in e-commerce depends on customer perceived value. A cu...

Privacy-Preserving Fair Item Ranking

Users worldwide access massive amounts of curated data in the form of ra...

Comparative Explanations of Recommendations

As recommendation is essentially a comparative (or ranking) process, a g...

A Robust Reputation-based Group Ranking System and its Resistance to Bribery

The spread of online reviews and opinions and its growing influence on p...

Proportional Rankings

In this paper we extend the principle of proportional representation to ...

Valid Explanations for Learning to Rank Models

Learning-to-rank (LTR) is a class of supervised learning techniques that...