This invention deals with a computer-implemented method for using predictive analytics to find a second set of entries in a first array that are related to a first set of entries in the first array without directly calculating entry-to-entry similarities between entries in the first array, the method including: (a) identifying a target entry in a second array, wherein the first set of entries in the first array are linked to the target entry in the second array; (b) finding likely entries in the second array that have similarities to a target entry in the second array using a correlation; (c) finding linked entries in the first array that are linked to the likely entries found in the second array; and (d) using the linked entries found in the first array as the second set of entries in the first array.