Estimation of the masses in the local group by gradient boosted decision trees

ABSTRACT Our goal is to estimate the mass of Local Group (LG) and individual masses its primary galaxies,the M31 Milky Way (MW). We do this by means a supervised machine learning algorithm, gradient boosted decision trees (GBDT) using observed distance relative velocity two as input parameters. The GBDT applied sample 2148 mock LGs drawn from set 5 dark matter (DM)-only simulations, ran withing standard ΛCDM cosmological model. selection guided LG model, which defines such objects. role observational uncertainties parameters gauged applying model an ensemble pairs whose observables are these perturbed their corresponding errors. Finally data actual used infer relevant masses. main results sum MW M31: $M_{tot} = 3.31 ^{+0.79}_{-0.67}$, $M_{MW}=1.15^{+0.25}_{-0.22}$ $M_{M31}=2.01^{+0.65}_{-0.39} \ \times 10^{12}M_{\odot }$ (corresponding median 1st 3rd quartiles). ratio $M_{M31}/M_{MW}=1.75^{+0.54}_{-0.28}$, where convention defined here be more massive haloes.