Connecting Web Event Forecasting with Anomaly Detection: A Case Study on Enterprise Web Applications Using Self-Supervised Neural Networks

TL;DR

DeepEvent is a novel self-supervised neural network approach for forecasting web events and detecting anomalies in enterprise web applications, leveraging sequence embeddings and web-specific features to improve accuracy and situational awareness.

Contribution

This paper introduces DeepEvent, a new self-supervised neural network model tailored for enterprise web event forecasting and anomaly detection, addressing data scarcity and dependency modeling.

Findings

DeepEvent outperforms baseline models in forecasting accuracy.

DeepEvent effectively detects anomalies in enterprise web applications.

The approach demonstrates robustness across six real-world datasets.

Abstract

Recently web applications have been widely used in enterprises to assist employees in providing effective and efficient business processes. Forecasting upcoming web events in enterprise web applications can be beneficial in many ways, such as efficient caching and recommendation. In this paper, we present a web event forecasting approach, DeepEvent, in enterprise web applications for better anomaly detection. DeepEvent includes three key features: web-specific neural networks to take into account the characteristics of sequential web events, self-supervised learning techniques to overcome the scarcity of labeled data, and sequence embedding techniques to integrate contextual events and capture dependencies among web events. We evaluate DeepEvent on web events collected from six real-world enterprise web applications. Our experimental results demonstrate that DeepEvent is effective in forecasting sequential web events and detecting web based anomalies. DeepEvent provides a context-based system for researchers and practitioners to better forecast web events with situational awareness.