Data Mining and Machine Learning

Technically, Data Mining and Machine Learning can be intertwined. You may find this description useful: “Data Mining refers to extracting knowledge from a large amount of data . . . we can say data mining is the process to discover various types of patterns that are inherent in the data and are accurate, new and useful. Usually . . . Machine Learning uses data mining techniques to build models of what is happening behind the data so that it can predict future outcomes.”

black and yellow calipers measuring tiny sculpture of a head
Measuring a Levantine ivory female head from Nimrud (Iraq), c. 8th-9th century BCE (British Museum, inv. no. 118198)

Beginning in 2004, in search of a mathematical template of ancient beauty underlying the production of ancient Levantine ivory carvings of women, I collaborated with computer scientists and applied mathematicians to uncover patterns from a dataset of over 30,000 quantitative and qualitative observations. The results were unexpected. While providing some information about figural proportions related to cultural aesthetics, the data also pointed strongly to clusters indicative of regional carving styles.

Data and code are available on GitHub.

I published this work in phases, with the final results being published in 2014. All publications listed below are available for download on Academia.

Amy Gansell (first author) with Chris Wiggins, et al., “Stylistic Clusters and the Syrian/South Syrian Tradition of First Millennium BCE Levantine Ivory Carving: A Machine Learning Approach,” Journal of Archaeological Science 44 (2014): 194-205.

Amy Gansell, “Measuring Beauty: An Anthropometric Methodology for the Assessment of Ideal Feminine Beauty as Embodied in First Millennium BCE Ivory Carvings,” pp. 155-70, in Syrian and Phoenician Ivories of the First Millennium BCE, Proceedings of the Conference held in Pisa, December 9th-11th, 2004, ed. S. M. Cecchini, et al., Pisa: Edizioni ETS, 2009.

Amy Gansell (first author) with Chris Wiggins, et al., “Predicting Regional Classification of Levantine Ivory Sculptures: A Machine Learning Approach,”  pp. 369-78, in Digital Discovery: Exploring New Frontiers in Human Heritage. Computer Applications and Quantitative Methods in Archaeology, Proceedings of the 34th Conference, Fargo, United States, 2006, ed. J. T. Clark and E. M. Hagemeister, Budapest: Archeolingua, 2007.

Also see Ch 4 of my dissertation “Women of Ivory as Embodiments of Ideal Feminine Beauty in the Ancient Near East during the First Millennium BCE” (Harvard, 2008).