The Large Synoptic Survey Telescope will generate a data deluge: millions of transients and variable sources will need to be classified from their light curves. Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC) brings a wide range of models together, simulated under LSST-like conditions for the first time. PLAsTiCC was delivered to the community through a Kaggle challenge, designed to stimulate interest in time-series photometric classification and deliver methodologies that will advance the LSST science case. I will give an overview of the road to PLAsTiCC, the models and the validation of the data, discuss some of its science results. I'll present new results on early classification of transients using active learning to prioritize spectroscopic resources, and discuss advances in the end goal: fully photometric supernova cosmology.