A method for mining association rules in quantitative and fuzzy data

In the last ten years data mining has become an interesting research area. In this paper we propose an algorithm based on fuzzy clustering for mining fuzzy association rules using a combination of crisp and quantitative data. By clustering the transactions, we obtain rules easier and with less complexity. To use this algorithm we need to execute a C-means fuzzy clustering process to extract data distribution knowledge, to partition every attribute intervals into the fuzzy numbers and then to transform quantitative data into fuzzy discrete transactions. Results are obtained using real data from an internet website´s subscribers. In comparison to other algorithms, this algorithm gives stronger and more realistic rules. In this paper rules are mined from clusters according to prominence of some attribute in clusters and obtained rules have higher confidence coefficient.