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

Baqar Rizvi,Ian Watson,Ammar Belatreche,Ahmed Bouridane

doi:10.1109/access.2020.3011590

Abstract

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 F-measure values and a significant reduction in false alarm rate (FAR) has been achieved.

Highlights

Stock market manipulation creates a false impression of stock prices through some illegitimate means [1]
The method claims an improved performance in terms of the area under the Receiver Operating Characteristics (ROC) curve and the F-measure, for the four features proposed over other classification techniques like One Class Support Vector Machines (SVM) (OCSVM) and kNN
Area Under its Curve (AUC) values in table 1 for some of the existing benchmark approaches in stock price manipulation detection are calculated only for Microsoft dataset for 21st June 2012

Summary

Introduction

Stock market manipulation creates a false impression of stock prices through some illegitimate means [1]. It affects investor’s interest in the manipulated stocks and undermines their confidence in the integrity of the entire market. Information based manipulation intends to spread a false rumor or release some inside information about a company or its stock with an intention to influence the price. Trade based manipulation on the other hand has everything to do inside a stock exchange where traders, investors or brokers buy/sell stocks at different prices for different volumes [2], [3]. One of the major types of trade-based manipulation is price manipulation in which the trader targets to influence the buy/sell prices of any company stock. Unlike the first two types of manipulation that can be avoided

Objectives

Methods

Results

Conclusion