Visible to the public A Temporal Recurrent Neural Network Approach to Detecting Market Anomaly Attacks

TitleA Temporal Recurrent Neural Network Approach to Detecting Market Anomaly Attacks
Publication TypeConference Paper
Year of Publication2018
AuthorsHuang, Yifan, Chung, Wingyan, Tang, Xinlin
Conference Name2018 IEEE International Conference on Intelligence and Security Informatics (ISI)
Date PublishedNov. 2018
ISBN Number978-1-5386-7848-0
Keywordsanomaly detection, Artificial neural networks, Cognitive Hacking, Collaboration, commodities markets, deep learning approaches, feature extraction, financial market security, financial social media messages, financial stocks markets, learning (artificial intelligence), market anomaly attacks detection, Metrics, Neural Network Security, policy-based governance, pubcrawl, recurrent neural nets, recurrent neural network, Recurrent neural networks, resilience, Resiliency, security of data, Sequence Prediction, social media, Social network services, social networking (online), stock markets, temporal recurrent neural network approach, text sequence dependency, TRNN, Twitter, U.S. technology companies

In recent years, the spreading of malicious social media messages about financial stocks has threatened the security of financial market. Market Anomaly Attacks is an illegal practice in the stock or commodities markets that induces investors to make purchase or sale decisions based on false information. Identifying these threats from noisy social media datasets remains challenging because of the long time sequence in these social media postings, ambiguous textual context and the difficulties for traditional deep learning approaches to handle both temporal and text dependent data such as financial social media messages. This research developed a temporal recurrent neural network (TRNN) approach to capturing both time and text sequence dependencies for intelligent detection of market anomalies. We tested the approach by using financial social media of U.S. technology companies and their stock returns. Compared with traditional neural network approaches, TRNN was found to more efficiently and effectively classify abnormal returns.

Citation Keyhuang_temporal_2018