FPI: FPI - Frequent Pattern Isolation algorithm

Description Usage Arguments Value Examples

Description

Algorithm proposed by: J. Kuchar, V. Svatek: Spotlighting Anomalies using Frequent Patterns, Proceedings of the KDD 2017 Workshop on Anomaly Detection in Finance, Halifax, Nova Scotia, Canada, PMLR, 2017.

Usage

1
FPI(data, minSupport = 0.3, mlen = 0)

Arguments

data

data.frame or transactions from arules with input data

minSupport

minimum support for FPM

mlen

maximum length of frequent itemsets

Value

model output (list) with all results including outlier scores

Examples

1
2
3
4
library("fpmoutliers")
dataFrame <- read.csv(
     system.file("extdata", "fp-outlier-customer-data.csv", package = "fpmoutliers"))
model <- FPI(dataFrame, minSupport = 0.001)

jaroslav-kuchar/fpmoutliers documentation built on May 18, 2019, 4:48 p.m.