The task is to predict house sale prices based on the house information, such as # of bedrooms, living areas, locations, near-by schools, and the seller summary. The training dataset consists of 40K houses sold in the [bay area](https://en.wikipedia.org/wiki/San_Francisco_Bay_Area) before 05/01/2020.  The test dataset has 23K houses sold after, which is divided into two parts for the public leaderboard and private leaderboard, respectively. The private leaderboard houses were sold after the ones in the public leaderboard.