MicroBooNE is a large liquid argon time projection chamber (LArTPC) located at Fermilab. One of the experiments primary aims is to investigate the CCQE-like excess of νe events observed by MiniBooNE at low energy. A novel approach to analyzing LArTPC data using an amalgam of Deep Learning and traditional algorithms has been developed and is capable of end to end reconstruction and selection. We report here an overview and progress to event selection which yields greater than 99.999% rejection of backgrounds. Statistical, flux, and some cross section systematics have also been evaluated. Detector systematics and additional cross section systematics are still under study.