Using Artificial Intelligence to Shed Light on the Star of Biscuits: The Jaffa Cake

TL;DR

This paper applies machine learning classifiers to classify Jaffa Cakes as cakes or biscuits, concluding they are cakes based on recipe analysis, and discusses the cultural debate surrounding their classification.

Contribution

It introduces a novel approach using AI classifiers trained on recipes to resolve the debate about Jaffa Cake classification.

Findings

Classifiers achieved over 90% accuracy in distinguishing cakes from biscuits.

Jaffa Cake recipes are classified as cakes by the algorithms.

Proposes a new theory explaining why some consider Jaffa Cakes biscuits.

Abstract

Before Brexit, one of the greatest causes of arguments amongst British families was the question of the nature of Jaffa Cakes. Some argue that their size and host environment (the biscuit aisle) should make them a biscuit in their own right. Others consider that their physical properties (e.g. they harden rather than soften on becoming stale) suggest that they are in fact cake. In order to finally put this debate to rest, we re-purpose technologies used to classify transient events. We train two classifiers (a Random Forest and a Support Vector Machine) on 100 recipes of traditional cakes and biscuits. Our classifiers have 95 percent and 91 percent accuracy respectively. Finally we feed two Jaffa Cake recipes to the algorithms and find that Jaffa Cakes are, without a doubt, cakes. Finally, we suggest a new theory as to why some believe Jaffa Cakes are biscuits.