census-house dataset

Dataset constructed from the 1990 US Census. It contains 4 prototasks, each concerned with predicting the median price of the house in a small survey region. More information is available in the detailed documentation

Warning: There are some problems with this data set. For instance, the H18.A input is said to be the "average number of persons per ownOcc HU", but it has values between 0 and 1, which is unreasonable. Thanks to Aki Vehtari for pointing this out.

Dataset profile:

Origin: cultivated

Usage: assessment

Number of attributes: 139

Number of cases: 22,784

Number of prototasks: 4

Number of methods run on this dataset: 2

Download census-house.tar.gz

Contributed by: Rafal Kustra

Last Updated 15 October 1996
Comments and questions to: delve@cs.toronto.edu