Search for the $W^{\prime}$ boson decaying to a top and a bottom quark with the CMS detector at the LHC by employing machine learning techniques.

An analysis strategy for the search of a $W^{\prime}$ boson decaying to a top quark and a bottom quark using Machine Learning (ML) techniques is presented. The analysis is performed on Monte Carlo simulated samples of $W^{\prime}$ signal events and its main background processes, produced in proton-proton collisions at a centre-of-mass energy of 13 TeV at the Large Hadron Collider and reconstructed with the CMS detector. Leptonic decays of the top quark are considered and, in order to improve the top quark reconstruction efficiency, a ML algorithm is employed to define several categories for the top candidate according to the separation of the lepton and $b$-jet from the top quark decay. Projections of expected upper limits on the $W^{\prime}$ production cross-section are given for the full Run 2 statistics of $137 {fb^{-1}}$. The obtained results are promising and will be the centre of future developments for the analysis to be implemented in Run 3.