Performance is not enough: the story told by a Rashomon quartet

TL;DR

This paper demonstrates that multiple models with similar predictive accuracy can have fundamentally different explanations of data relationships, highlighting the importance of visualization beyond performance metrics.

Contribution

It introduces the Rashomon Quartet, a set of four models with similar performance but different explanations, emphasizing the need for visualization in model comparison.

Findings

Models with similar accuracy can have different data explanations

Visual analysis reveals diverse relationships despite comparable performance

Encourages use of visualization to understand model differences

Abstract

The usual goal of supervised learning is to find the best model, the one that optimizes a particular performance measure. However, what if the explanation provided by this model is completely different from another model and different again from another model despite all having similarly good fit statistics? Is it possible that the equally effective models put the spotlight on different relationships in the data? Inspired by Anscombe's quartet, this paper introduces a Rashomon Quartet, i.e. a set of four models built on a synthetic dataset which have practically identical predictive performance. However, the visual exploration reveals distinct explanations of the relations in the data. This illustrative example aims to encourage the use of methods for model visualization to compare predictive models beyond their performance.