Data Mining in Financial Markets (original) (raw)
Related papers
ANALYSIS OF STOCK MARKET MANIPULATIONS USING KNOWLEDGE DISCOVERY TECHNIQUES
This paper addresses challenges relating to applying data mining techniques to detect stock price manipulations and extends previous results by incorporating the analysis of intraday trade prices in addition to closing prices for the investigation of trade-based manipulations. In particular, this work extends previous results on the topic by analysing empirical evidence in normal and manipulated hourly data and the particular characteristics of intraday trades within suspicious hours. Furthermore, the analytical models described in this paper reinforce the results of previous market manipulation studies that are based on traditional statistical and econometrical methods providing an alternative portfolio of methods and techniques originating from the data mining and knowledge discovery areas. With the application of the analytical approach described in this paper, it is possible to identify new fraud manipulation pattern characteristics encoded as decision trees which can be readily employed in fraud detection systems. The paper also proposes a number of policy recommendations towards increasing the effectiveness of the operational processes executed by stock exchange fraud departments and regulatory authorities.
Expert Systems with Applications, 2011
This paper addresses challenges relating to applying data mining techniques to detect stock price manipulations and extends previous results by incorporating the analysis of intraday trade prices in addition to closing prices for the investigation of trade-based manipulations. In particular, this work extends previous results on the topic by analysing empirical evidence in normal and manipulated hourly data and the particular characteristics of intraday trades within suspicious hours. Furthermore, the analytical models described in this paper reinforce the results of previous market manipulation studies that are based on traditional statistical and econometrical methods providing an alternative portfolio of methods and techniques originating from the data mining and knowledge discovery areas. With the application of the analytical approach described in this paper, it is possible to identify new fraud manipulation pattern characteristics encoded as decision trees which can be readily employed in fraud detection systems. The paper also proposes a number of policy recommendations towards increasing the effectiveness of the operational processes executed by stock exchange fraud departments and regulatory authorities.
The detection of market abuse on financial markets: a quantitative approach
Quaderni Di Finanza, No. 54, 2003
In every country with legislation on market abuse, i.e. on market manipulation and insider trading, the repression of these o¤ences is entrusted to supervisory and judicial authorities with powers that vary with the legislation in question. A procedure permitting cases of market abuse to be detected in real time is a need that is strongly felt by …nancial market supervisory authorities. Such a procedure consists basically in the analysis of the transactions carried out on the market by traders in order to detect anomalies that could be symptomatic of market abuse. The aim of this paper is to develop, through recourse to probability theory, a method for identifying cases of market abuse more e¤ectively.
An Analysis of Data Mining Applications for Fraud Detection in Securities Market
In recent securities fraud broadly refers to deceptive practices in connection with the offering for sale of securities. There are many challenges involved in developing data mining applications for fraud detection in securities market, including: massive datasets, accuracy, privacy, performance measures and complexity. The impacts on the market and the training of regulators are other issues that need to be addressed. In this paper we present the results of a Comprehensive systematic literature review on data mining techniques for detecting fraudulent activities and market manipulation in securities market. We identify the best practices that are based on data mining methods for detecting known fraudulent patterns and discovering new predatory strategies. Furthermore, we highlight the challenges faced in the development and implementation of data mining systems for detecting market manipulation in securities market and we provide recommendation for future research works accordingly.
Machine Learning, Market Manipulation and Collusion on Capital Markets: Why the 'Black Box' matters
SSRN Electronic Journal, 2021
This Article offers a novel perspective on the implications of increasingly autonomous and "black box" algorithms, within the ramification of algorithmic trading, for the integrity of capital markets. Artificial intelligence (AI) and particularly its subfield of machine learning (ML) methods have gained immense popularity among the great public and achieved tremendous success in many real-life applications by leading to vast efficiency gains. In the financial trading domain, ML can augment human capabilities in price prediction, dynamic portfolio optimization, and other financial decision-making tasks. However, thanks to constant
Qatar University College of Engineering Detecting Market Manipulation in Stock Market Data by Haya
2017
Anomaly Detection is an extensively researched problem that has diverse applications in many domains. Anomaly detection is the process of finding data points or patterns that do not conform to expected behavior within a dataset. Solutions to this problem have used techniques from disciplines such as statistics, machine learning, data mining, spectral theory and information theory. In the case of stock market data, the input is a non-linear complex time series that render statistical methods ineffective. The aim of this thesis, is to detect anomalies within the Standard and Poor and Qatar Stock Exchange using the behavior of similar time series. Many works on stock market manipulation focus on supervised learning techniques, which require labeled datasets. The labeling process requires substantial efforts. Anomalous behavior is also dynamic in nature. For those reasons, the development of an unsupervised market manipulation detection technique would be very interesting. The Contextual Anomaly Detector (CAD) is an unsupervised method that finds anomalies by looking at similarly behaving time series and uses them to predict expected values. When the predicted value is different from the actual value in the time series by a certain threshold, it is considered an anomaly. This thesis will look at the Contextual Anomaly Detector (CAD) and implement a different preprocessing step to improve recall and precision. iv ACKNOWLEDGMENTS This thesis would not have been what it is if not for the support of my supervisors.
Analyzing Stock Market Fraud Cases Using a Lin-guistics-Based Text Mining Approach
The paper proposes a linguistics-based text mining approach to demonstrate the process of extracting financial concepts from the Security Exchange Commission (SEC) litigation releases (LR). The proposed approach presents the extracted information as a knowledge base to be used in market monitoring surveillance systems. Also, it facilitates users' acquisition, maintenance and access to financial fraud knowledge and improves search results in the SEC enforcement portal. Answering questions such as: who are the agents involved in the manipulation? Which patterns are associated with this manipulation? When was this manipulative action performed? This paper used the financial ontology for fraud purposes introduced by [19] to provide underlying framework for the extraction process and capture financial fraud concepts from the SEC-LR. In particular, text mining analysers have been developed to extract metadata concepts (e.g. 'LR No.', 'dates') and stock market fraud concepts (e.g. agents and manipulation types) from the actual SEC fraud case.
Who Is the Next “Wolf of Wall Street”? Detection of Financial Intermediary Misconduct
Journal of the Association for Information Systems
Financial intermediaries are essential for investors' participation in financial markets. Due to their position within the financial system, intermediaries committing misconduct not only harm investors but also undermine trust in the financial system, which ultimately has a significant negative impact on the economy as a whole. Building upon information manipulation theory as well as warranting theory and making use of self-disclosed data with varying levels of external verification, we propose different classifiers that automatically detect financial intermediaries committing misconduct. Therefore, we focus on self-disclosed information by financial intermediaries on the business network LinkedIn. We match user profiles with regulatory-disclosed information and use this data for classifier training and evaluation. We find that self-disclosed information provides valuable input to detect financial intermediary misconduct. Regarding external verification, our classifiers achieve the best predictive performance when additionally taking regulatory-confirmed information into account. These results are supported by an economic evaluation. Our findings are highly relevant for both investors and regulators in order to identify financial intermediaries committing misconduct and thus contribute to the societal challenge of building and ensuring trust in the financial system.
Stock-touting” through spam e-mails: a data mining case study
Journal of Manufacturing Technology Management, 2011
Purpose -Although the financial markets are regulated by robust systems and rules that control their efficiency and try to protect investors from various manipulation schemes, markets still suffer from frequent attempts to mislead or misinform investors in order to generate illegal profits. The impetus to effectively and systematically address such schemes presents many challenges to academia, industry and relevant authorities. This paper aims to discuss these issues. Design/methodology/approach -The paper describes a case study on fraud detection using data mining techniques that help analysts to identify possible instances of touting based on spam e-mails. Different data mining techniques such as decision trees, neural networks and linear regression are shown to offer great potential for this emerging domain. The application of these techniques is demonstrated using data from the Pink Sheets market. Findings -Results strongly suggest the cumulative effect of "stock touting" spam e-mails is key to understanding the patterns of manipulations associated with touting e-mail campaigns, and that data mining techniques can be used to facilitate fraud investigations of spam e-mails. Practical implications -The approach proposed and the paper's findings could be used retroactively to help the relevant authorities and organisations identify abnormal behaviours in the stock market. It could also be used proactively to warn analysts and stockbrokers of possible cases of market abuse. Originality/value -This research studies the relationships between the cumulative volume of spam touts and a number of financial indicators using different supervised classification techniques. The paper aims to contribute to a better understanding of the market manipulation problem and provide part of a unified framework for the design and analysis of market manipulation systems.
IJERT-Data Mining Tools To Detect Financial Fraud
International Journal of Engineering Research and Technology (IJERT), 2013
https://www.ijert.org/data-mining-tools-to-detect-financial-fraud https://www.ijert.org/research/data-mining-tools-to-detect-financial-fraud-IJERTV2IS90775.pdf Every day, news of financial statement fraud is adversely affecting the economy worldwide. Considering the influence of the loss incurred due to fraud, effective measures and methods should be employed for prevention and detection of financial statement fraud. I synthesize academic literature related to fraudulent financial reporting with dual purposes: (1) to better understand the nature and extent of the existing literature on financial reporting fraud, and (2) to highlight areas where there is need for future research. I review publications in accounting and related disciplines including criminology, ethics, finance, organizational behavior accepted for publication. Data mining techniques has been proved the most commonly used techniques for prevention and detection of financial frauds. The implementation of data mining techniques for fraud detection follows the traditional information flow of data mining, which begins with feature selection followed by representation, data collection and management, pre-processing, data mining, post-processing, and performance evaluation.