Combining quantitative approaches to differentiate between backed products from discoidal and Levallois reduction sequences

Backed flakes (core edge and pseudo-Levallois points) represent special products of Middle Paleolithic centripetal flaking strategies. Their peculiarities are due to their roles as both a technological objective in the management core convexities retain its geometric properties during reduction. In contexts, these backed implements commonly produced Levallois discoidal reduction sequences. from sequences often show common morphological features that complicate attribution one methods. This study examines identification experimentally recurrent (including all stages reduction) based on features. 3D morphometrics employed quantify variability among experimental sample. Dimensionality though principal component analysis is combined with 11 machine learning models for knapping A supported vector polynomial kernel has been identified best model (with general accuracy 0.76 an area under curve [AUC] 0.8). indicates combining morphometrics, analysis, succeeds capturing differences according method.