A Fast and Efficient Local Outlier Detection in Data Streams

Abstract

Outlier detection in data streams is used in many applications, such as network flow monitoring, stock trading fluctuation detection and network intrusion detection [1]. These applications require that the algorithms finish outlier detection effectively in a limited amount of time and memory space. Local Outlier Factor (LOF) is a fundamental density-based outlier detection algorithm [2], it determines whether an object is an outlier by calculating LOF score of each observer. There are many LOF-based algorithms that have achieved excellent results with respect to outlier detection in data streams, while most of existing LOF-based algorithms have problems with excessive computation. In this paper, we propose a fast outlier detection algorithm in data streams, the algorithm effectively reduces the LOF calculation of the whole data by Z-score pruning. The algorithm consists of three phases. Firstly, generate the prediction data through the generator. Secondly, judge whether the observation object is a potential outlier by the Z-score of the residual from the origin value and the prediction value. Finally, calculate the LOF of the observation object in the current time window according to the judgment result of the previous step. It is proved by experiments that our algorithm effectively reduces the detection time consumption through Z-score pruning under the condition of ensuring the detection accuracy.