For customer transaction database, the support (customer support) of the sequential pattern is defined as the fraction of the customers supporting the sequence. We define new forms of the mining patterns, called cyclic patterns, as an extension to the sequential pattern mining by introducing a new parameter, the repetition support. For customer transaction database, the repetition support specifies the minimum number of repetitions of the patterns in each customer transaction sequence. Repeated patterns can also be viewed as cyclic since the beginning of a sequence will follow the end of the previous occurrence of the same sequence. In this paper, we introduce the repetition support parameter, the cyclic pattern mining problem, describe the related algorithms, and at the end of the paper we give some performance results. (C) 2003 Elsevier Ltd. All rights reserved.