Search for Dark photon in reconstructed High Luminosity LHC Monte-Carlo simulated events

The High Luminosity (HiLumi) upgrade of the LHC will observe a ten-fold increase in the integrated luminosity of the accelerator which in turn will significantly increase the pile-up and unwanted background events hindering our efforts in the search for new physics. In this project we tried to place cuts on simulated Monte-Carlo data with di-muon final state and analyse the dark photon selection efficiency and acceptance with respect to the given background. We have also tried to visualise the challenges faced in storing high volume data and verify the feasibility of storing data after cuts in high luminosity upgrade. Finally we use a neural network to place cuts in order to improve signal efficiency based on the data used in training and testing.