According to an embodiment, an information processing apparatus includes one or more processors. The processors are configured to: generate a plurality of shuffle maps obtained by randomly shuffling, from positions to others, at least some of subject values contained in a subject map having the subject values arrayed in N dimensions (N is an integer of 1 or more); generate a subject vector expressing features of a frequency domain of the subject map and random vectors expressing features of respective frequency domains of the shuffle maps; and derive, as an evaluation value for whether the subject map has a random characteristic, a testing result of statistical hypothesis testing on feature differences between the subject vector and the respective random vectors.