Discrimination of China's stock price manipulation based on primary component analysis

Yang, Fengzhao; Yang, Huahai; Yang, Mian

doi:10.1109/besc.2014.7059519

Cited by 8 publications

(5 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Roodposhti và cộng sự đã sử dụng mô hình logit, mạng nơron nhân tạo và phân tích đa phân biệt để tạo ra các mô hình nhận diện thao túng giá cổ phiếu trên sàn giao dịch chứng khoán Tehran 22 . Trong nghiên cứu của Yangs, mô hình hồi quy logistic được lựa chọn để phát hiện các hoạt động thao túng giá cổ phiếu tại thị trường Thượng Hải và Thâm Quyến 35 . Cao và McGinnity đã đề xuất Mô hình Markov ẩn thích ứng với các trạng thái bất thường (Adaptive Hidden Markov Model with Anomaly States) để phát hiện các hoạt động thao túng giá cổ phiếu trong ngày 36 .…”

Section: Các Phương Pháp Và Mô Hình Nhận Diện Thao Túng Giá Cổ Phiếuunclassified

Issues of stock price manipulation and solutions for Vietnam's stock market

Luu Thu,

Nguyen Duy,

Duong Dang

2023

Sci.Tech.Dev.J.-Eco.Law Manag.

View full text Add to dashboard Cite

Stock price manipulation is a widespread issue globally, but it becomes particularly acute in emerging markets due to severe information asymmetry. This harmful practice has significant adverse effects on society, the economy, and investors, driven primarily by the pursuit of economic gain. Stocks of small companies with limited liquidity and transparency are particularly vulnerable to manipulation. Although institutional investors may engage in stock price manipulation at times, they also have the potential to enhance transparency and reduce such activities in the market. To identify instances of manipulation, economists have developed advanced models utilizing machine learning, artificial neural networks, support vector machines, and decision trees. In light of previous studies, the author proposes several solutions to curb stock price manipulation in Vietnam. These include raising awareness among investors, providing professional ethics training for employees in the financial industry and government, enhancing market transparency and integration, strengthening supervision, and imposing strict sanctions on individuals and organizations violating securities regulations.

show abstract

Section: Các Phương Pháp Và Mô Hình Nhận Diện Thao Túng Giá Cổ Phiếuunclassified

Issues of stock price manipulation and solutions for Vietnam's stock market

Luu Thu,

Nguyen Duy,

Duong Dang

2023

Sci.Tech.Dev.J.-Eco.Law Manag.

View full text Add to dashboard Cite

show abstract

“…A vast number of empirical studies have been conducted in stock price manipulation but most of them claimed significant improvements in the detection results either based on certain assumptions in their applied research or using labelled datasets, which makes it easier for the model to learn the anomalous patterns and provide better detection accuracy on the test data. Yang et al [22] constructed a prediction model for the detection of stock price manipulation activities using PCA followed by a logistic regression representing the discrimination for the manipulated stock prices. However, the results obtained do not highlight the detection performance rather the prediction of the stock prices is given only.…”

Section: Related Workmentioning

confidence: 99%

“…Some of the major constraints in the implementation of KPCA are the choice of RBF kernel parameter and the number of principal components to be considered. It is well documented that for anomaly detection using PCA, the number of components extracted should be such that the cumulative variance must be greater than or equal to 90% of the total variance in the mapped feature set [22,45] which settles down to = 7. This helps in reducing the uncertainty over the optimal size of the components used and will efficiently reduce the computational complexity of the overall approach.…”

Section: Wherementioning

confidence: 99%

Detection of Stock Price Manipulation Using Kernel Based Principal Component Analysis and Multivariate Density Estimation

et al. 2020

View full text Add to dashboard Cite

Stock price manipulation uses illegitimate means to artificially influence market prices of several stocks. It causes massive losses and undermines investors' confidence and the integrity of the stock market. Several existing research works focused on detecting a specific manipulation scheme using supervised learning but lacks the adaptive capability to capture different manipulative strategies. This begets the assumption of model parameter values specific to the underlying manipulation scheme. In addition, supervised learning requires the use of labelled data which is difficult to acquire due to confidentiality and the proprietary nature of trading data. The proposed research establishes a detection model based on unsupervised learning using Kernel Principal Component Analysis (KPCA) and applied increased variance of selected latent features in higher dimensions. A proposed Multidimensional Kernel Density Estimation (MKDE) clustering is then applied upon the selected components to identify abnormal patterns of manipulation in data. This research has an advantage over the existing methods in overcoming the ambiguity of assuming values of several parameters, reducing the high dimensions obtained from conventional KPCA and thereby reducing computational complexity. The robustness of the detection model has also been evaluated when two or more manipulative activities occur within a short duration of each other and by varying the window length of the dataset fed to the model. Validation on multiple datasets and a comprehensive assessment of the model performance has been conducted without providing any prior information about the location of the manipulation. The results show a significant performance enhancement in terms of the Fmeasure values and a significant reduction in false alarm rate (FAR) has been achieved.

show abstract

“…Yang et al [12] conducted a comparative analysis of various supervised learning algorithms with the objective of identifying suspected cases of market manipulation. Among the algorithms evaluated, the naive Bayes classifier emerged as the most effective, thus demonstrating superior performance in detecting potential manipulation instances.…”

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

Discrimination of China's stock price manipulation based on primary component analysis

Cited by 8 publications

References 2 publications

Issues of stock price manipulation and solutions for Vietnam's stock market

Issues of stock price manipulation and solutions for Vietnam's stock market

Detection of Stock Price Manipulation Using Kernel Based Principal Component Analysis and Multivariate Density Estimation

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

Contact Info

Product

Resources

About