The big data revolution is upon us— several hundred thousand alerts are generated by the Zwicky Transient Facility (ZTF) each night, far more than any human (or army of grad students) can process. This data deluge will be exacerbated by the Vera C. Rubin Observatory’s Legacy Survey of Space and Time (LSST), which is estimated to generate roughly 10,000,000 time-domain alerts every night. In response, broker teams like ANTARES were built to handle current data streams and future surveys, annotating events with catalog associations and filtering them to customizable subsets. In this talk, I will discuss my anomaly detection filter on the ANTARES infrastructure, which tags anomalous objects in real-time to catch supernovae and other transient events as they occur and more quickly help trigger followup resources. Also, I will discuss the implementation of a deep learning neural network called RAPID for early time classification of supernovae for the Young Supernova Experiment (YSE). Together, these algorithms help astronomers study the interesting and under-studied physics of some of the fastest-changing and brightest objects in the night sky.