Stock Price Manipulation Detection based on Autoencoder Learning of Stock Trades Affinity

Rizvi, Baqar; Belatreche, Ammar; Bouridane, Ahmed; Mistry, Kamlesh

doi:10.1109/ijcnn48605.2020.9207346

Cited by 5 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model achieved an accuracy of 68% in detecting only the synthesized pump-anddump scheme without requiring knowledge about the manipulation patterns. Rizvi et al [52] implemented AE using the information captured by the affinity matrix to detect stock price manipulation. They used the same dataset and injected the same manipulative patterns as in [50].…”

Section: B Methods For Identifying Market Manipulation Activitiesmentioning

confidence: 99%

Stock Price Manipulation Detection Using Deep Unsupervised Learning: The Case of Thailand

2021

View full text Add to dashboard Cite

Detecting stock price manipulation is a cat-and-mouse game. Manipulators have continuously invented new techniques to avoid being caught. Most of the related work used supervised learning techniques, which require known manipulation patterns as examples for their models to recognize. To catch unknown and never-before-seen manipulation, we implemented unsupervised learning to train deep neural networks for detecting stock price manipulation. The models were trained to recognize normal trading behaviors that were expressed on a limit order book. Anomaly trading actions, which did not conform to the learned patterns were identified as manipulated. The strength of our method is that it does not require prior knowledge about the characteristics of manipulation. Therefore, it is best used for catching new or unknown types of manipulation. Two model architectures were tested: autoencoder (AE) and generative adversarial networks (GANs). They were tested on six prosecuted real manipulation cases in the Stock Exchange of Thailand (SET). Both models could identify five out of six cases with a low false-positive rate. A strategy to optimize the decision boundary, called "MinManiMax", was also proposed for practical usage of the models.

show abstract

Section: B Methods For Identifying Market Manipulation Activitiesmentioning

confidence: 99%

Stock Price Manipulation Detection Using Deep Unsupervised Learning: The Case of Thailand

2021

View full text Add to dashboard Cite

show abstract

“…The best overall performance was obtained by using a kNN classifier with frequency input features that were selected by using the PCA method. Rizvi et al [61] then applied the same early setup used in the previous work, but with a minor modification of periodicity removal to highlight unique patterns on the tick stock data. However, they used full synthetic data to validate the proposed method, in which the manipulation cases were artificially injected into the normal data taken from the NASDAQ Stock Exchange Market.…”

Section: Stock Market Manipulation Detection: Supervised Conventional...mentioning

confidence: 99%

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

“…Their results were, on average, 29.8% higher in terms of area under the ROC curve (AUC) than those observed in studies that used traditional statistical tools. Rizvi et al [14] proposed an unsupervised model based on the idea of learning the relationship between stock prices in the form of an affinity matrix; the characteristics extracted from this matrix were used to train an autoencoder. Finally, they used clustering based on kernel density estimation (MKDE) to detect manipulated operations, where nonclustered data were treated as manipulated.…”

Section: Introductionmentioning

confidence: 99%

Ensemble Approach Using k-Partitioned Isolation Forests for the Detection of Stock Market Manipulation

Núñez Delafuente,

Astudillo,

Díaz

2024

Mathematics

View full text Add to dashboard Cite

Stock market manipulation, defined as any attempt to artificially influence stock prices, poses significant challenges by causing financial losses and eroding investor trust. The prevalent reliance on supervised learning models for detecting such manipulations, while showing promise, faces notable hurdles due to the dearth of labeled data and the inability to recognize novel manipulation tactics beyond those explicitly labeled. This study ventures into addressing these gaps by proposing a novel detection framework aimed at identifying suspicious hourly manipulation blocks through an unsupervised learning approach, thereby circumventing the limitations of data labeling and enhancing the adaptability to emerging manipulation strategies. Our methodology involves the innovative creation of features reflecting the behavior of stocks across various time windows followed by the segmentation of the dataset into k subsets. This setup facilitates the identification of potential manipulation instances via a voting ensemble composed of k isolation forest models, which have been chosen for their efficiency in pinpointing anomalies and their linear computational complexity—attributes that are critical for analyzing vast datasets. Evaluated against eight real stocks known to have undergone manipulation, our approach demonstrated a remarkable capability to identify up to 89% of manipulated blocks, thus significantly outperforming previous methods that do not utilize a voting ensemble. This finding not only surpasses the detection rates reported in prior studies but also underscores the enhanced robustness and adaptability of our unsupervised model in uncovering varied manipulation schemes. Through this research, we contribute to the field by offering a scalable and efficient unsupervised learning strategy for stock manipulation detection, thereby marking a substantial advancement over traditional supervised methods and paving the way for more resilient financial markets.

show abstract

Stock Price Manipulation Detection based on Autoencoder Learning of Stock Trades Affinity

Cited by 5 publications

References 26 publications

Stock Price Manipulation Detection Using Deep Unsupervised Learning: The Case of Thailand

Stock Price Manipulation Detection Using Deep Unsupervised Learning: The Case of Thailand

A Survey on Stock Market Manipulation Detectors Using Artificial Intelligence

Ensemble Approach Using k-Partitioned Isolation Forests for the Detection of Stock Market Manipulation

Contact Info

Product

Resources

About