Abstract: Systems and methods for machine learning to adjust a baseline model are provided. In example embodiments, a networked system determines an initial value for each of a plurality of homes. The networked system applies a baseline model to each initial value to generate a baseline value for each of the plurality of homes. A randomization process is performed by the networked system on an input value for each of the plurality of homes to generate a final value for each of the plurality of homes, whereby each input value being based on a corresponding baseline value. Each of the plurality of homes is listed at a corresponding final value. The networked system then analyzes a result of the listing for the plurality of homes. Based on the analyzing, the networked system automatically adjusts the baseline model.