Frequent Pattern Outlier Detection Without Exhaustive Mining

Outlier detection consists in detecting anomalous observations from data. During the past decade, pattern-based outlier detection methods have proposed to mine all frequent patterns in order to compute the outlier factor of each transaction. This approach remains too expensive despite recent progress in pattern mining field. In this paper, we provide exact and approximate methods for calculating the frequent pattern outlier factor (FPOF) without extracting any pattern or by extracting a small sample. We propose an algorithm that returns the exact FPOF without mining any pattern. Surprisingly, it works in polynomial time on the size of the dataset. We also present an approximate method where the end-user controls the maximum error on the estimated FPOF. Experiments show the interest of both methods for very large datasets where exhaustive mining fails to provide the exact solution. The accuracy of our approximate method outperforms the baseline approach for a same budget in time or number of patterns.