Naso, LucaSole, LaviniaPatti, AndreaArmetta, FrancescoCelso, Fabrizio LoPatatu, Wladimiro CarloSaladino, Maria LuisaCampana, StefanoFerdani, DanieleGraf, HolgerGuidi, GabrieleHegarty, ZackaryPescarin, SofiaRemondino, Fabio2025-09-052025-09-052025978-3-03868-277-6https://doi.org/10.2312/dh.20253153https://diglib.eg.org/handle/10.2312/dh20253153This paper presents the initial findings of the ongoing MML-ARCH project, which uses machine learning (ML) algorithms to create predictive, supervised models for analyzing archaeological, numismatic and physicochemical data. Specifically, the study proposes using convolutional neural network (CNN) algorithms to predict the minting year of ancient Roman Republican coins based on the iconography on the obverse and reverse.Attribution 4.0 International LicenseCCS Concepts: Computing methodologies → Supervised learning by regression; Applied computing → ArchaeologyComputing methodologies → Supervised learning by regressionApplied computing → Archaeology10.2312/dh.202531533 pages