Iterated K-nearest neighbor method and article of manufacture for filling in missing values

An article of manufacture comprising:

• a computer usable medium having computer readable program code means embodied therein for filling in missing attribute values in a data set array of cases and attribute positions, the computer readable program code means in said article of manufacture comprising:
• computer readable program code means for causing a computer to effect, for a first case which includes an empty attribute position, a determination of a first set of K nearest neighbor cases which have known values for the corresponding attribute position as the empty attribute position in the first case;
• computer readable program code means for causing the computer to determine a filled in attribute value from the first set of K nearest neighbor cases for the empty attribute position in the first case;
• computer readable program code means for causing the computer to determine a second set of K nearest neighbor cases to the first case which have known values for the corresponding attribute position as the empty attribute position in the first case;
• and
• computer readable program code means for causing the computer to revise the filled-in attribute value of the first case with an attribute value determined from the second set of K nearest neighbor cases.

A computer system for filling in missing attribute values in a data set array of cases and attribute positions comprising:

• for a first case which includes an empty attribute position, means for determining a first set of K nearest neighbor cases which have known values for the corresponding attribute position as the empty attribute position in the first case;
• means for determining a filled in attribute value from the first set of K nearest neighbor cases for the empty attribute position of the first case;
• means for determining a second set of K nearest neighbor cases to the first case which have known values for the corresponding attribute position as the empty attribute position in the first case;
• and
• means for revising the filled in attribute value of the first case with an attribute value determined from the second set of K nearest neighbor cases.