Search for $H\rightarrow\tau\tau$ Decays in the Lepton-Hadron Final State using Multivariate Techniques in Proton-Proton Collisions at $\sqrt{s}= 13\,\mathrm{Te\kern -0.1em V}$ with the ATLAS Detector at the LHC

A multivariate analysis (MVA) using machine learning techniques to study the Standard Model decay of the Higgs boson to two $\tau$ leptons ($H\rightarrow \tau^{+}\tau^{-}$) is presented. The analysis focuses on the decay channel, in which one $\tau$ decays leptonically and the other $\tau$ decays hadronically. The background is estimated with a combination of Monte Carlo simulation and data-driven methods. A boosted decision tree (BDT) is trained on the background model and employed to classify events into background and signal to enhance the sensitivity of the analysis. The results of the analysis are compared to a cut-based analysis. The analysis is performed with a dataset of proton-proton collisions at a center-of-mass energy $\sqrt{s} = 13\,\mathrm{Te\kern -0.1em V}$ taken with ATLAS detector at the LHC during Run 2.