ML-based classification in an open-source framework for the ALICE heavy-flavour analysis

The ALICE Collaboration aims to precisely measure heavy-flavour (HF) hadron production in high-energy proton-proton and heavy-ion collisions to provide valuable tests of perturbative quantum chromodynamics models and insights into hadronisation mechanisms. Measurements of the production of the Ξ+c and Λ+c baryons decaying into a proton (p) and charged π and K mesons are remarkable examples of investigation in the HF sector. As in other ALICE analyses, a Boosted Decision Tree (BDT) classifiers has been adopted to discriminate the signal yields from the background processes. Especially for the Ξ+c → pK−π+ process, the Machine Learning (ML)-based approach is required and particularly challenging due to its large combinatorial background, small branching ratio, and short O(100 µm) decay length. FAIR, a European project synergic to the ALICE experiment, aims to set up an open-source, user-friendly, and interactive pytorch-based environment external to the official ALICE framework to perform BDT-based multivariate analyses. The FAIR benchmark imports different ML libraries (XGBoost, Sklearn, and Ray) to prepare the data and configure the BDT models in Jupyter notebooks. Currently, the training is performed on a preliminary dataset with limited statistics using a partitioned shared GPU available through an Apache Mesos cluster at the ReCaS-Bari datacenter. In the future, when a larger dataset is available, we intend to leverage a GPU-powered Kubernetes cluster for processing large-scale applications, including ML tool training. This contribution will present a performance comparison of the investigated ML architectures trained with simulated signal events and background data provided by ALICE during LHC Run 3 proton-proton collisions at √s = 13.6 TeV.