Predicting Regional Classification of Levantine Ivory Sculptures: A Machine Learning Approach

TL;DR

This study employs machine learning techniques to classify the regional origins of Levantine ivory sculptures with high accuracy, providing new insights into their regional features and aiding art historical interpretation.

Contribution

It introduces a quantitative machine learning approach for regional classification of ivory sculptures, surpassing traditional visual methods and revealing previously unknown feature relationships.

Findings

Achieved 98% prediction accuracy in regional style classification.

Identified key features with high predictive power for regional classification.

Discovered new relationships among features that assist in interpreting regional origins.

Abstract

Art historians and archaeologists have long grappled with the regional classification of ancient Near Eastern ivory carvings. Based on the visual similarity of sculptures, individuals within these fields have proposed object assemblages linked to hypothesized regional production centers. Using quantitative rather than visual methods, we here approach this classification task by exploiting computational methods from machine learning currently used with success in a variety of statistical problems in science and engineering. We first construct a prediction function using 66 categorical features as inputs and regional style as output. The model assigns regional style group (RSG), with 98 percent prediction accuracy. We then rank these features by their mutual information with RSG, quantifying single-feature predictive power. Using the highest- ranking features in combination with nomographic visualization, we have found previously unknown relationships that may aid in the regional classification of these ivories and their interpretation in art historical context.