Using Generative Adversarial Networks for Detecting Stock Price Manipulation: The Stock Exchange of Thailand Case Study

Leangarun, Teema; Tangamchit, Poj; Thajchayapong, Suttipong

doi:10.1109/ssci47803.2020.9308284

Cited by 6 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In summary, the concept of market manipulation encompasses a wide range of frequently varying tactics that typically include the intention of producing a false appearance of a security's price or trading operation. As technology becomes more advanced, experimental research to detect manipulation cases can now utilize more advanced techniques such as complex data analytic methods [42,43]. However, advanced data analytics and artificial intelligence-based strategies for trading behavior analysis have not yet been extensively reviewed.…”

Section: Early Experimental Researches On Stock Market Manipulationmentioning

confidence: 99%

“…Then, the input of the sentiment analysis system was added to increase detection accuracy using various analyzers, including SVM, deep neural decision forest, RF, and 5-layer CNN classifiers. By using a 3-layer LSTM, Leangarun et al [43] developed a generative adversarial network (GAN) to detect stock manipulation cases. The unique aspect of this adversarial approach was the two competing networks that aimed to detect and produce fake incidents, which refers to manipulation incidents in this case.…”

Section: Stock Market Manipulation Detection: Deep Machine Learning A...mentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Stock Market Manipulation Detectors Using Artificial Intelligence

Zulkifley¹,

Munir²,

Sukor³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

A well-managed financial market of stocks, commodities, derivatives, and bonds is crucial to a country's economic growth. It provides confidence to investors, which encourages the inflow of cash to ensure good market liquidity. However, there will always be a group of traders that aims to manipulate market pricing to negatively influence stock values in their favor. These illegal trading activities are surely prohibited according to the rules and regulations of every country's stock market. It is the role of regulators to detect and prevent any manipulation cases in order to provide a trading platform that is fair and efficient. However, the complexity of manipulation cases has increased significantly, coupled with high trading volumes, which makes the manual observations of such cases by human operators no longer feasible. As a result, many intelligent systems have been developed by researchers all over the world to automatically detect various types of manipulation cases. Therefore, this review paper aims to comprehensively discuss the state-of-theart methods that have been developed to detect and recognize stock market manipulation cases. It also provides a concise definition of manipulation taxonomy, including manipulation types and categories, as well as some of the output of early experimental research. In summary, this paper provides a thorough review of the automated methods for detecting stock market manipulation cases.

show abstract

Section: Early Experimental Researches On Stock Market Manipulationmentioning

confidence: 99%

Section: Stock Market Manipulation Detection: Deep Machine Learning A...mentioning

confidence: 99%