Uncovering time series anomaly using deep learning technique
Department of CSE (Data Science), ACE Engineering College, Hyderabad, Telangana, India.
Review Article
World Journal of Advanced Research and Reviews, 2024, 22(01), 879–887
Publication history:
Received on 03 March 2024; revised on 11 April 2024; accepted on 13 April 2024
Abstract:
Time series data, characterized by its sequential and temporal nature, plays a crucial role in various domains such as finance, healthcare, and industrial processes. Identifying anomalies within time series data is a critical task with applications ranging from fault detection to fraud prevention. Traditional anomaly detection techniques often struggle to capture complex temporal patterns and dependencies in time series data. This study presents a novel time series anomaly detection method using long short-term memory (LSTM) neural networks. LSTMs are a type of recurrent neural networks (RNNs) designed to model long-term dependencies, making them suitable for capturing the complex temporal relationships present in time series data. Here we use a financial dataset featuring opening and closing time, we predict the volume of money and the current price of that money at a specific time. The results demonstrate the efficacy of the deep learning-based approach in detecting anomalies within time series data, outperforming traditional methods in terms of sensitivity and adaptability to complex temporal patterns. The proposed methodology presents a promising solution for real-world applications where early detection of anomalies is crucial for proactive decision-making and system integrity.
Keywords:
Classification; Machine Learning; Neural networks; LSTM; Decision-making; System integrity
Full text article in PDF:
Copyright information:
Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0