Market Surveillance System Research Articles

Anomaly Pattern Detection in High-Frequency Trading Using Graph Neural Networks

This paper presents a new method for detecting abnormal patterns in high-frequency trading (HFT) using graph neural networks (GNNs). The increasing sophistication of trading algorithms and the large volume of data have often created unprecedented challenges for traditional market analysis. Our framework addresses these challenges by introducing a GNN-based architecture that takes advantage of the physical and structural properties of business data. The proposed method transforms HFT data into graphical models where the nodes represent market conditions and the edges capture their physical and price relationships. A specialized GNN architecture, incorporating attention mechanisms and temporal convolution modules, is developed to learn complex trading patterns and identify potential anomalies. The model is evaluated on high-frequency trading data from five major stocks listed on NASDAQ, spanning six months of trading activity with over 10 million events. Experimental results demonstrate superior performance compared to existing approaches, achieving a 15% improvement in detection accuracy and maintaining robust performance across different market conditions. The framework exhibits particular strength in identifying complex manipulation patterns while maintaining low false positive rates. Our approach processes large volumes of trading data in real time with significantly reduced computational requirements compared to traditional methods. This research contributes to the development of more effective market surveillance systems and provides valuable insights for regulatory authorities in maintaining market integrity.

WALDATA: Wavelet transform based adversarial learning for the detection of anomalous trading activities

Detecting manipulative activities in stock market trading poses a significant challenge due to the complex temporal correlations inherent to the dynamically changing stock price data. This challenge is further exacerbated by the limited availability of labelled anomalous trading data instances. Stock price manipulations, which consist of infrequent anomalies in stock price trading data, are challenging to capture due to their sporadic occurrence and dynamically evolving nature. This scarcity and inherent complexity significantly complicate the creation of labelled datasets hence hinders the development of robust detection of different stock price manipulation schemes through supervised learning methods. Overcoming these challenges is crucial for enhancing our understanding of market dynamics and implementing robust market surveillance systems. To address these challenges, we introduce a novel stock price manipulation detection approach called WALDATA (Wavelet Transform based Adversarial Learning for the Detection of Anomalous Trading Activities). We leverage the Wavelet Transform (WT) to decompose non-stationary stock price time series into informative features and capture multi-scale dynamics within the data. We encode stock price data by transforming it into scalogram images through the Continuous Wavelet Transform, effectively converting stock price time series data into a 2D image representation. Subsequently, we employ a Generative Adversarial Network (GAN) architecture, originally applied to computer vision, to learn the underlying distribution of normal trading behaviour from the encoded images. We then train the discriminator as an anomaly detector for identifying manipulative trading activities in the stock market. The efficacy of WALDATA is rigorously evaluated on diverse real-world stock datasets using 1-level tick data from the LOBSTER project and the experimental results demonstrate the significant performance of our approach achieving an average AUC of 0.99 while maintaining low false alarm rates across various market conditions. These findings not only validate the effectiveness of the proposed WALDATA approach in accurately identifying stock price manipulations but also provide investors and regulators alike with valuable insights for the development of advanced market surveillance systems. This research demonstrates the promising potential of combining wavelet-based feature extraction and stock price time series to image representation with generative adversarial learning frameworks for anomaly detection in financial time series data. The successful implementation of WALDATA contributes to the development of advanced market surveillance systems and paves the way for further advancements in market surveillance, contributing towards a more efficient and robust financial system and a fair market environment.

Projected changes concerning UAS in the Polish Aviation Law and other acts

The unmanned aerial vehicle industry is developing dynamically and ahead of the regulations. Integrating manned and unmanned aviation is necessary to ensure an appropriate level of safety and the sustainable development of the unmanned aerial vehicle industry. Therefore, an amendment to the Polish aviation law has been prepared. It includes the effective EU regulations on UAS, which have been applied directly since the beginning of 2021. EU law, however, requires more details in many aspects. Specifying EU solutions will allow for a more effective impact of the regulations on UAS users and aviation authorities and the achievement of the assumed goals of the proposed changes. The article presents the reasons for the introduced changes, the outline and essence of EU regulatory solutions, and elements of national solutions. The proposed changes to the Aviation Law, the PANSA Act of December 8, 2006, and April 13, 2016, Act on compliance assessment and market surveillance systems were presented. The most important thing is the additional Section VIa - Unmanned Aerial Vehicles added to the Aviation Law. The article covers the content of six chapters, additional provisions, penal provisions, and new charges for geographic zones. The proposed amendments to the PANSA Act related to new obligations for the Agency are also presented. The article ends with a summary and conclusions that indicate the positive impact of the amendment. At the same time, an attempt was made to evaluate the introduced changes by identifying the shortcomings and imperfections of the new regulations.

Post-marketing sampling and testing programs for licensed medicinal products: a narrative review

The globalization of the pharmaceutical market has enabled access to a considerable number of new medicinal products. Consequently, the circulation of substandard medicinal products has also increased. To minimize this problem, post-marketing quality sampling and testing programs are performed to monitor and confirm that the medicinal products available in the market meet appropriate quality requirements. In this review, the post-approval sampling and testing procedures of six regulatory authorities were compared with the goal of strengthening these market surveillance systems. Similarities were observed between the procedures adopted by different regulatory authorities. However, the agencies were not always transparent about the results of these monitoring procedures. A probable mismatch between the registration procedures and the quality requirements listed in official compendiums was observed, which resulted in dissonance and contradiction between the specifications approved by the regulatory authorities and those required in the pharmacopeias. Therefore, strengthening harmonization projects related to these activities can help minimize such difficulties.

Liquidity, informed trading, and a market surveillance system: Evidence from the Vietnamese stock market

This paper investigates the effectiveness of a market surveillance system (MSS) on improving the market quality of the Vietnamese stock market, as measured by liquidity and informed trading level. We find that market liquidity decreases after the introduction of the MSS, and that the effect is more pronounced for small firms. Although the level of informed trading, on average, does not change significantly after the MSS, the subsample analysis indicates a significant decrease in informed trading among large and liquid firms.

The Situation of Securities Maket Supervision in Vietnam

In order to ensure the transparency as well as the efficiency and maintain the stability of the securities market, the supervision system needs to be established with the goal of detecting, preventing and handling violations of regulations, laws enacted by the State. In Vietnam, the State manages the securities market and assigns the securities market supervision task to the State Securities Commission (SSC). Over the past time, the SSC has implemented several supervision operations and obtained certain results. However, the monitoring results also showed that the number of violations on the stock market tended to increase, reports on stability and risk identification were not yet or clear. Some reasons come from the limitations of the market surveillance system such as the lack of close coordination between the stock market supervision with banks, insurance, and the supervisory authority cannot develop the overall risk report form. Potential as well as systematic risk, control of different accounts of stock market participants is loosened, supervision focuses on issues with complaints or duplicating supervision that cause many subjects. It is possible to take advantage of the monitoring gap to make violations more sophisticated. The research results provide solutions to complete the supervision system of Vietnam's securities market to achieve the targets set in the coming time.

Correlation of the International and National Institutional and Legal Regulations of Applying Some Aspects of Technical Barriers in Practices of Ukraine and the European Union

Summary This study contains the attempt of the comprehensive approach to issues of the correlation of concepts, provisions and obligations of States and their associations with respect to technical barriers to trade (in particular, technical regulations, standardization, certification, and accreditation, conformity assessment procedures and market surveillance systems) enshrined in international world treaties (in particular, the Agreement on Technical Barriers to Trade (TBT), which is binding for Member-States in the system of the WTO treaties) and regional multilateral and bilateral treaties (for example, the Association Agreement between Ukraine, from one part, and the European Union, European Atomic Energy Community, and their Member-States, from the other part, dd. June 27, 2014). The particular attention is paid to the national, including unified (or that being in the process of unification/adaptation), institutional and legal provision in this area, most notably in Ukraine and the European Union (first of all, the Regulation of the European Parliament and of the Council No. 765/2008/EC and Decision of the European Parliament and of the Council No. 768/2008/EC of 9 July 2008). The performance by Ukraine at the domestic/national level of its international obligations in accordance with the Association Agreement 2014 has been separately considered in terms of technical regulations and standardization, accreditation, conformity assessment procedures and market surveillance systems and their implementation (adaptation, entrenchment) in relevant regulatory legal, and organizational and institutional forms.

Regulatory clearance: How are outcome measurements critical?

In May 2017 the European Medical Device Regulation (MDR) was published to replace the current Medical Device Directive (MDD) and the Active Implantable Medical Device Directive (AIMDD). After a transition period of 3 years (ending May 2020) the MDR will apply in the European Union (EU). With this new legislative framework, the requirements for placing new medical devices and keeping existing medical devices on the EU market will become more stringent. This is mainly due to the focus on clinical data for all medical devices regardless of their classification and the increased requirements on the post market surveillance system. In most cases, the MDR will require pre-market clinical studies for implantable medical devices and devices falling in the highest risk class (Class III). Since 2000 there has been a significant increase in the quantity and quality of publications in the fields of orthopaedic and orthopaedic trauma surgery. However, there is still a large number of medical devices without direct clinical data which rely on market experience and the established level of a specific technology or a group of devices. Due to this fact, and the fact that the new MDR is requiring sufficient clinical data for devices which shall stay on the market after May 2020, there is an increasing need for new clinical data sources reflecting the real-world use of medical devices.

Distribution Channel Management and the Control of Fake/Counterfeit Products in Selected Pharmaceuticals Companies in Benue State.

This study evaluated distribution channel management and control of counterfeit products in Nigeria with specific reference to selected pharmaceutical industries in Benue State. The study used mainly primary data obtained by the use of a well-structured questionnaire. The study used multiple regression analysis to test the two hypotheses of the study. The result shows that a negative relationship exist between distribution management and its effect on consumer's accessibility and it is statistically significant (p<0.05) and in line with a priori expectation. Also, the study found that the source of fake and counterfeit product is positively related to distribution channel management but it is not statistically significant (p>0.05). It was concluded therefore that efficient distribution channel management could help to greatly reduce the proliferation of counterfeit products in the health sector. In view of this, it was recommended that laws guiding the regulation of imported and manufactured products should be strengthened to ensure effectiveness by regulatory authorities. Hence, the distribution channels management policies should be an approach to control counterfeit products by instituting on a clear post market surveillance system that will aid the fast identification of counterfeit and other substandard drugs while consumer's access to counterfeit product should be restricted through an efficient distribution channel management.

Ability of EU Legislation to Deter: the Volkswagen Case

After the discovery of the fraud committed by Volkswagen to circumvent emission control tests, it became clear that the current EU legal framework on type approval and emission standards for cars shows structural weaknesses. The Member States are primarily responsible for implementing and enforcing the legislation, but often fail to do this. Consequently, the Commission has started infringement procedures against several Member States. Nevertheless, there is no doubt that the current legal framework has to be updated. In a first part, the current legislation is examined. However, not only the EU legislation on type approval and emission standards is considered, but as well other legislation that can have a deterrent effect for the carmaker. Besides, public law actions and private law claims can also incentivize the car manufacturer to honour the emission standards, and complement the type approval legislation. Still, strengthening the current environmental legislation is necessary to overcome the present problems, such as the quality and independence of testing, the effectiveness of the market surveillance system and the European oversight in the type-approval process. The Commission proposed to replace the current framework with a new Regulation. In a second part, this proposal is dealt with. The Parliament and the Council already expressed their position at first reading.

Создание тестовых данных для систем контроля и мониторинга рынка, содержащих встроенные алгоритмы машинного обучения

Market surveillance systems, used for monitoring and analysis of all transactions in the financial market, have gained importance since the latest financial crisis. Such systems are designed to detect market abuse behavior and prevent it. The latest approach to the development of such systems is to use machine learning methods that largely improve the accuracy of market abuse predictions. These intelligent market surveillance systems are based on data mining methods, which build their own dependencies between the variables. It makes the application of standard user-logic-based testing methodologies difficult. Therefore, in the context of intelligent surveillance systems, we built our own model for classifying the transactions. To test it, it is important to be able to create a set of test cases that will generate obvious and predictable output. We propose scenarios that allow to test the model more thoroughly, compared to the standard testing methods. These scenarios consist of several types of test cases which are based on the equivalence classes methodology. The division into equivalence classes is performed after the analysis of the real data used by real surveillance systems. We tested the created model and discovered how this approach allows to define its weaknesses. This paper describes our findings from using this method to test a market surveillance system that is based on machine learning techniques.

A Commonsense Knowledge-Enabled Textual Analysis Approach for Financial Market Surveillance

Market surveillance systems (MSSs) are increasingly used to monitor trading activities in financial markets to maintain market integrity. Existing MSSs primarily focus on statistical analysis of market activity data and largely ignore textual market information, including, but not limited to, news reports and various social media. As suggested by both theoretical explorations in finance and prevailing market surveillance practice, unstructured market information holds major yet underexplored opportunities for surveillance. In this paper, we propose a news analysis approach with the help of commonsense knowledge to assess the risk of suspicious transactions identified in market activity analysis. Our approach explicitly models semantic relations between transactions and news articles and provides semantic references to words in news articles. We conducted experiments using data collected from a real-world market and found that our proposed approach significantly outperforms the existing methods, which are based on transaction characteristics or traditional textual analysis methods. Experiments also show that the performance advantage of the proposed approach mainly comes from the modeling of news-transaction relationships. The research contributes to the market surveillance literature and has significant practical implications.

Unusual Trade or Market Manipulation? How Market Abuse is Detected by Securities Regulators, Trading Venues and Self-Regulatory Organizations

Securities regulators protect the integrity of capital markets by detecting, investigating and then prosecuting, insider trading and market manipulation, known collectively as market abuse. The main method of detection of market abuse is surveillance of markets by software designed to identify unusual trading. Such market surveillance is undertaken by trading venues, self-regulatory organizations, and securities regulators. Two other important methods used to detect market abuse are suspicious transaction reports made to regulators by financial intermediaries and voluntary reports to regulators by the public of possible market abuse. This article describes the main methods of detection of market abuse in five jurisdictions which comprise over 50 per cent of the world’s securities markets, namely the USA, Canada, Germany, the UK, and Australia. Furthermore, given the growing internationalization of securities markets, there exists the possibility that many market abuse offences will not be confined to one country and may span two or more jurisdictions. As such regulatory bodies must increasingly work together to exchange information to detect market abuse. This article also examines how such information is exchanged, the challenges in exchanging such information and suggests ways in which this could be improved. In particular, more investment is needed in market surveillance systems to improve both the detection of market abuse and to enable securities regulators to swiftly determine the cause of any market disruption. This will in turn facilitate a more targeted regulatory response to ensure that such a disruption is not repeated.

Design Theory for Market Surveillance Systems

Market surveillance systems (MSSs) are information systems that monitor financial markets to combat market abuses. Existing MSSs focus mainly on analyzing trading activities and are often developed through a trial-and-error approach by screening data mining algorithms and features. The void of theoretical direction limits the effectiveness of MSSs and calls for the development of a design theory based on a thorough examination of the meta-requirements of MSSs. Based on the efficient market hypothesis and text understanding theory, this paper argues that market information analysis should be incorporated into MSSs and commonsense knowledge should be employed to connect related events to transactions and provide reference concepts for understanding market context and assessing transaction risk. We show the effectiveness of this proposed design theory through developing and evaluating a prototype system in the context of a real-world stock exchange market. By taking a theory-driven approach, this research shows the possibility and provides guidelines on the use of market information analysis to alleviate the market surveillance problem, which has significant implications for financial markets and the economy given the explosive growth of illegal trading activities worldwide.

An Ontology for Monitoring and Surveillance Systems in Financial Markets

Ontologies play a key role in all aspects of information management within different domains as they provide a common and usable representation of the domain knowledge. The objective of the ontology is to describe the different classes (terms and vocabularies), and to define their relationships according to specific domain rules, in order to describe the knowledge of domain in a generic way. Ontology can be useful in many ways. One contemporary use is as a framework to represent information of domain in useful way. It enables computers to process its contents as it offers a way to give information about common representation and semantics to domains. In particular, it helps in bridging the communication gaps between humans and software systems through representing a shared and common understanding of a domain.Researchers in the field of artificial intelligence (AI), business intelligence (BI), and knowledge management have recognized that capturing knowledge is the key to building large and powerful systems. It is argued that ontologies could create new computational models which enable certain kinds of automation of information representation. While the sheer size and scale of data has been growing exponentially, these data presents its own challenge. Knowing how to first understand the data, garnering information and knowledge from it, and then intelligently combine it with other data sets means that there is a need to accurately represent this data and effectively allows identifying insightful information out of context.In the context of financial markets, there is a wealth of knowledge that is generated and it is important that this knowledge is managed and communicated efficiently and effectively. This is especially true in the context of monitoring and surveillance due to the changes in the structure, connectivity and operation of financial markets and the increased complexity in dealing with possible fraud cases. An ontology addressing the needs for market monitoring and surveillance could help support better the increased requirements of market operators, brokers and regulators to ensure that markets operate in an efficient way.The report discusses the development of ontology for financial markets monitoring and surveillance. The proposed ontology brings together existing domain knowledge from previous efforts together with new knowledge derived from the analysis of unstructured sources based on existing fraud cases reported by SEC. The ontology is represented using semantic representation techniques and contains a comprehensive set of concepts that could help analysts to understand financial fraud practices, assist open investigation by managing relevant facts gathered for case investigations, informing detection and pattern monitoring techniques, developing prevention practices, and sharing manipulation patterns from prosecuted cases with investigators and relevant stakeholders.The ontology is evaluated through specific case studies to show the applicability of the ontology to help users in the market monitoring surveillance systems. In particular, the three cases are considered as intelligent systems that extract information from unstructured sources based on the financial ontology. First case aims to provide an empirical evidence of how text mining could be integrated with the proposed ontology to improve the efficiency of extracting financial fraud concepts from Security Exchange Commission (SEC) litigation releases and demonstrating the published prosecuted cases from SEC website in appropriate knowledge base. Second case aims to demonstrate how text mining techniques could automatically extract key attributes and characteristics of different unstructured sources generated as part of ’touting campaigns’. Last case aims to describe business intelligence (BI) service system for a financial market monitoring and surveillance system in order to produce alarms for possible securities fraud cases. The evaluation of the proposed ontology with the BI service system is carried out through an exemplar case that relates to a real case from the over-the-counter (OTC) market and which was prosecuted by SEC.

Analyzing Financial Fraud Cases Using a Linguistics-Based Text Mining Approach

The paper proposes a linguistics-based text mining approach to automate the process of extracting financial concepts from the Security Exchange Commission (SEC) litigation releases. The text mining application includes data source analyzers that extract concepts such as 'litigation release number', 'release publication dates', 'actions', 'document format type', 'document link', 'short description', 'detailed description', and 'plaintiff'. Furthermore, the application includes analyzers to extract concepts such as manipulation participants, type of manipulation, laws and regulations, and timeline manipulation events and actions from the actual SEC complaint fraud case. In order to extract these concepts, this paper used the financial ontology for fraud purposes introduced by [17] to provide underlying framework for the extraction process and capture financial fraud concepts from the SEC litigation releases.Domain-specificity is incorporated through the development of linguistic resources for financial fraud domain in order to make the analysis more effective. The proposed approach demonstrates the extracted information as a knowledge base to facilitate users’ acquisition, maintenance and access to financial fraud knowledge and improving search results in the SEC enforcement portal. When was this manipulative action performed? Where is the manipulator getting his profit from?Finally, a very important implication of the approach is that it addresses the need to reuse the proposed text-mining in other parts of the domain, and to integrate the extracted information with other financial systems such as market monitoring and surveillance systems, crowd monitoring and fraud knowledge management system.

(A294) The Veterinary Stability Operations Practitioner Course: A Model for Bridging the Gap in Veterinary Medical Education for the Global Veterinary Medicine Practitioner

Veterinary education provides a solid clinical and public health background that is applicable to several international development and humanitarian assistance sectors; however key skills and experiences that are required to be an effective Global Veterinary Medicine practitioner are not covered. In response to the US Department of Defense adopting Stability Operations as a core mission, the US Army Veterinary Corps has developed a Veterinary Stability Operations Practitioner Course intended to prepare Veterinary Corps officers to function effectively if tasked to conduct or support Stability Operations. The Veterinary Stability Operations Practitioner Course is a two part workshop series that provides a global veterinary perspective including knowledge, skills and experience necessary for Veterinarian to function in an international developing setting. Skills in assessment methodologies, program planning and evaluation are core to each workshop. Knowledge is based on production, market, and disease surveillance systems in the developing world. The intent is for the attendee after completing the course series to view their operational environment differently by understanding the social and cultural context that influences local population decisions and behaviors.

Market Microstructure Patterns Powering Trading and Surveillance Agents

Market Surveillance plays important mechanism roles in constructing market models. From data analysis perspective, we view it valuable for smart trading in designing legal and profitable trading strategies and smart regulation in maintaining market integrity, transparency and fairness. The existing trading pattern analysis only focuses on interday data which discloses explicit and high-level market dynamics. In the mean time, the existing market surveillance systems available from large exchanges are facing crucial challenges of diversified, dynamic, distributed and cyber-based misuse, mis-disclosure and misdealing of information, announcement and orders in one market or crossing multiple markets. Therefore, there is a crucial need to develop innovative and workable methods for smart trading and surveillance. To deal with such issues, we propose the innovative concept microstructure pattern analysis and corresponding approaches in this paper. Microstructure pattern analysis studies trading behaviour patterns of traders in market microstructure data by utilizing market microstructure knowledge. The identified market microstructure patterns are then used for powering market trading and surveillance agents for automatically detecting/designing profitable and legal trading strategies or monitoring abnormal market dynamics and trader's behaviour. Such trading/surveillance agent-driven market trading/surveillance systems can greatly enhance the analytical, discovery and decision-support capability of market trading/surveillance than the current predefined rule/alert-based systems.

Changes in European Legislation Make it Timely to Introduce a Transparent Market Surveillance System for Cosmetics

Marketing of cosmetics often makes strong claims linked to active ingredients. This is especially so for anti-ageing products, where the presentation and content of "active" ingredients may create new difficulties in their classification as cosmetics or medicinal products. A recent change in European legislation classifies a product as medicinal by virtue of its "function", in addition to the previous definition of "presentation" (i.e. marketing linked to diseases). Thus, formulations that also restore, correct or modify physiological functions by exerting a pharmacological, immunological or metabolic action should henceforth be covered by the Medicinal Products Directive. A cosmetic product must be suitable for its purpose and should not lead to adverse reactions that are disproportional in relation to its intended effect. However, the forthcoming ban on animal testing of cosmetic ingredients and the new European regulation, REACH (Registration, Evaluation and Authorisation of Chemicals), which aims to ensure a high level of chemical safety to protect human health and the environment, will probably have limited impact on the safety assessment of cosmetics. In order to enable consumers to make informed purchasing decisions, greater transparency in the process of assessing the performance of cosmetics is needed. Introduction of a more transparent system, enabling consumers and professionals to examine the scientific evidence for the claimed effect and the safety assessment of cosmetics, is therefore timely. Lack of transparency increases the risk of consumers wasting money on cosmetics that do not deliver the desired effects. This may jeopardize public trust in the cosmetic industry.

Spatial Integration of the Rice Market: Empirical Evidence from Mid-west and Far-west Nepal, and the Nepalese-Indian Border

This paper studies the integration of rice markets in the mid-west and far-west districts of Nepal. The data were drawn mainly from the World Food Programme (WFP) database on Nepal. Results indicate that the rice markets of the hinterland are poorly integrated with the regional market of Nepalgunj. In contrast, price fluctuations are transmitted, both in the short and medium run, across the Indian-Nepali border between Nepalgunj and the Indian border districts of Rupedia and Jogbani. Large price differentials relative to transport costs indicate market inefficiencies in the mid-west and far-west districts of Nepal. Moreover, the poor road infrastructure determines the price differentials. Poor infrastructure impedes price correlation and convergence between these districts. Given its opendoor policy with India and the ongoing efforts to further align trade policies with the World Trade Organization, the findings suggest that Nepal would maintain its partnership with India and build an effective market surveillance system that covers the Indian border markets as well, to ensure food security in the short run. However, substantial investment in transport infrastructure is required to improve market integration and accessibility in the long run, especially in the hilly and mountainous areas.