Anomaly Detection using combination of Autoencoder and Isolation Forest

Abstract

The process of identifying abnormal objects or patterns that deviate from the typical behavior in a dataset or other observations is known as Anomaly Detection. It is an essential technique in many fields, such as cyber security, finance, transportation, and fraud detection. This paper combines an autoencoder and an isolation forest algorithm to enhance anomaly detection. The autoencoder is a neural network trained to reconstruct the input data, while the isolation forest is a tree-based algorithm that can identify outliers in the data. By combining these two methods, the autoencoder can learn a compact representation of the data, and the isolation forest can then be applied to the reconstructed data to identify anomalies. This combination effectively enhances the anomaly detection process in high-dimensional data when compared to utilizing the individual algorithms.