Trading System Research Articles

Deep Learning in Finance: A Survey of Applications and Techniques

Machine learning (ML) has transformed the financial industry by enabling advanced applications such as credit scoring, fraud detection, and market forecasting. At the core of this transformation is deep learning (DL), a subset of ML that is robust in processing and analyzing complex and large datasets. This paper provides a comprehensive overview of key deep learning models, including Convolutional Neural Networks (CNNs), Long Short-Term Memory networks (LSTMs), Deep Belief Networks (DBNs), Transformers, Generative Adversarial Networks (GANs), and Deep Reinforcement Learning (Deep RL). Beyond summarizing their mathematical foundations and learning processes, this study offers new insights into how these models are applied in real-world financial contexts, highlighting their specific advantages and limitations in tasks such as algorithmic trading, risk management, and portfolio optimization. It also examines recent advances and emerging trends in the financial industry alongside critical challenges such as data quality, model interpretability, and computational complexity. These insights can guide future research directions toward developing more efficient, robust, and explainable financial models that address the evolving needs of the financial sector.

Allocation or Skill? What is Driving Corporate Trading Performance in the EU ETS?

This study empirically analyzes factors related to companies’ profits from trading emission allowances in the European Union Emissions Trading System (EU ETS) for the period from 2005 to 2017 by combining information on trading activities with company characteristics of more than 6,000 companies. The factors considered include net position (i.e., free allocation of allowances minus emissions), strategic skills (i.e., banking of allowances, timing of trading, transaction frequency, use of intermediaries), skill-related structural factors (i.e., number of installations, sector affiliation), market pressure, year, and region effects. The results from estimating a Panel Heckman Selection Model suggest that companies’ profits from buying and selling emission allowances are related to a company’s net position, banking of allowances, timing of trading, and the number of installations. The findings further indicate that companies choose the number of banked allowances efficiently, that is, they take into account the opportunity costs of selling these allowances on the market. JEL Classification: Q48, Q54, Q58

Does Floor Trading Matter?

ABSTRACTAlthough algorithmic trading now dominates financial markets, some exchanges continue to use human floor traders. On March 23, 2020 the NYSE suspended floor trading because of COVID‐19. Using a difference‐in‐differences analysis around the closure of the floor, we find that floor traders are important contributors to market quality. The suspension of floor trading leads to higher spreads and larger pricing errors for treated stocks relative to control stocks. To explore the mechanism, we exploit two partial floor reopenings that have different characteristics. Our finding suggests that in‐person human interaction facilitates the transfer of valuable information that algorithms lack.

Effect of Integrated Customs Management Systems (ICMS) on Customs Duty Performance in Nairobi County, Kenya

Purpose: Tax is an important stream of revenue for government’s development projects and therefore all efforts must be made by governments to ensure that it is accurately and efficiently collected to facilitate the government’s operations. This study sought to determine the of integrated customs management system on factors affecting customs duty performance Nairobi County, Kenya. The theories supporting the study is comparative theory of international trade. Methodology: The study employed explanatory research design. The target population of this study was 438 respondents comprising customs heads of departments, customs officers and customs agents at Embakasi Inland Depot, Nairobi. with a sample size of 209, out of which 173 respondents correctly filled the questionnaires and submitted them accordingly. The data collected was analyzed through descriptive and inferential statistics. A linear regression model was used. Results: The coefficient study showed that a unit change in ICMS increases customs duty performance significantly β =0.205 p-value =0.000<0.05. Conclusion: The study recommends that the KRA and the government of Kenya prioritize the continuous improvement of the Integrated Customs Management System (ICMS). Customs management should ensure full utilization of the ICMS by training customs officials and stakeholders, given its positive impact on duty performance. Future research may be carried out on the effects of tax incentives on Customs duty performance

Emergence of information aggregation to rational expectations equilibria in markets populated by biased heuristic traders

Information aggregation is a key economic function of markets. We report results of a computational experiment with markets populated by simple algorithmic traders who follow two heuristics usually thought of as leading to biased information processing in behavioral economics literature (anchor-and-adjust, and representativeness). Outcomes of these markets either tend to cluster around (or fail to do so) rational expectations equilibria under specific conditions, consistent with markets populated by profit-motivated human traders. Algorithmic trader convergence is slower and noisier than that of human traders. Our results illustrate the emergence of rational expectations equilibria through complex interactions among actions of biased heuristic traders with limited information processing capabilities.

Between abolition and opium: civility and force across Asian and Caribbean British imperialisms

ABSTRACT This paper explores the relationship between Britian’s abolition of slavery in its Caribbean colonies in 1838 and its instigation of the First Opium War with China in 1840. In so doing, it works against the occlusion of this relationship in the study of British imperialism despite the centrality of these events to the birth of global systems of free trade and free labour. It draws on the parliamentary debates and correspondence of British Foreign Secretary Lord Palmerston to analyze Britain’s negotiation of anti-slavery efforts with Haiti and its trade of Indian opium with China. It argues that these negotiations position British masculine civility against less-civilized foreign others in ways that legitimate the use of maritime force. This logic of imperial civility produces contradictory effects by demanding an end to the brutality of African enslavement while condoning the devastation of Asian opium addiction enacted in the name of free trade.

On the legality of national carbon pricing instruments alongside the new EU ETS 2

With the EU ETS 2 a new EU-wide emissions trading system is introduced that covers the greenhouse gas emission of the buildings and road transport sectors, i.e. sectors the decarbonization of which has so far been the responsibility of the Member States under the Effort Sharing Regulation. Since they will remain responsible for the achievement of their national greenhouse gas emission reduction targets under that regime, the question arises whether the Member States can maintain or introduce additional carbon pricing instruments alongside the new EU ETS 2. Hence, this paper examines the legality of such an approach, by assessing relevant provisions of EU secondary and primary law. Without going deep into the economic and political considerations, it concludes that from a legal perspective, the coexistence of national carbon pricing instruments and the EU ETS 2 is not prohibited.With the latest reform of the EU Emissions Trading System Directive (ETS Directive), the European Union (EU) has introduced a new EU emissions trading system for buildings and road transport (EU ETS 2)1. The decarbonization of those sectors traditionally falls within the responsibility of the EU Member States under the regime of the Effort Sharing Regulation (ESR). The ESR introduces legally binding national greenhouse gas (GHG) emission reduction targets. Hence, over the last few years, the Member States have introduced different measures in order to reach their targets. Those include carbon pricing instruments, understood as measures that put a price on the emission of GHG and thus create an incentive to reduce those emissions. Carbon pricing instruments include carbon taxes, as well as emissions trading systems2. With the introduction of the new ETS 2, the question arises whether the Member States can maintain (or introduce) such national carbon pricing instruments in parallel to the new EU ETS 2.

Resource nationalism: the intersection of politics and economics

Resource nationalism has a complex economic, political, and cultural history and reality. The evolution of the supply and demand structure of the global mineral metal market influences it. It is closely linked to the “economic-political” system within resource-rich countries. We analyze the ‘economic-political’ logic of resource nationalist behavior using the two-tier game theory. We examine 261 cases of resource nationalism since 1990 and test the theoretical hypotheses using quantitative techniques. The results show that rising mineral prices are the main trigger for contemporary resource nationalism. However, ideology, institutional quality, social climate, and economic dependence within resource countries play a non-negligible role. Resource wealth dependence in host countries makes it difficult for policymakers to escape national resource interventions. We argue that (1) The global economic trading system imbalance is the root of resource nationalism. (2) Resource nationalism is an endeavor by resource-rich countries to seek entitlements from mineral resource endowments. (3) Resource nationalism is not a zero-sum competition in the national economic trading system. In the face of the potential risks posed by resource nationalism to the global supply of minerals, the relevant interest groups should have sufficient strategic reserves to cope with the possible game of interests.

Assessing the internationalization dynamics of emerging markets: a comprehensive analysis utilizing SWARA-WASPAS techniques

Purpose This paper aims to evaluate the internationalization of countries represented in the MSCI Emerging Markets Index. The evaluation considers high-technology product imports, foreign direct investments, research and development expenditures, patent and industrial design applications, exports and gross domestic product (GDP) data, representing production. Design/methodology/approach This paper uses the Step-Wise Weight Assessment Ratio Analysis (SWARA) method to assess and rank the criteria for evaluating emerging markets. Four academics who are authorities in the field of foreign trade were consulted to weigh the criteria. The Weighted Aggregated Sum Product Assessment (WASPAS) method, considered one of the most reliable and robust MCDM techniques, was then used to evaluate and rank the countries. Findings The findings obtained during the research process reveal the internationalization dynamics of these countries based on the indicators they possess. As a result, it is observed which countries achieve higher performance in the internationalization process based on relevant criteria. Originality/value This study is theoretically unique and valuable as it simultaneously offers the potential for development to macro-level international trade theories, such as the technologic deficit hypothesis, and meso-level internationalization theories, such as the Uppsala model. Additionally, integrated multiple criteria decision-making (MCDM) methods, which are not frequently used in cross-country studies, have been used, and the performance of emerging markets has been ranked. The findings obtained from this application distinguish the research from the existing literature by transforming it into a performance ranking rather than focusing on the antecedents or consequences of internationalization and their interactions.

Does Speculation Matter in the Carbon Pricing Framework? Insights from the EU Emissions Trading System

Does Speculation Matter in the Carbon Pricing Framework? Insights from the EU Emissions Trading System

A new sociology of humans and machines.

From fake social media accounts and generative artificial intelligence chatbots to trading algorithms and self-driving vehicles, robots, bots and algorithms are proliferating and permeating our communication channels, social interactions, economic transactions and transportation arteries. Networks of multiple interdependent and interacting humans and intelligent machines constitute complex social systems for which the collective outcomes cannot be deduced from either human or machine behaviour alone. Under this paradigm, we review recent research and identify general dynamics and patterns in situations of competition, coordination, cooperation, contagion and collective decision-making, with context-rich examples from high-frequency trading markets, a social media platform, an open collaboration community and a discussion forum. To ensure more robust and resilient human-machine communities, we require a new sociology of humans and machines. Researchers should study these communities using complex system methods; engineers should explicitly design artificial intelligence for human-machine and machine-machine interactions; and regulators should govern the ecological diversity and social co-development of humans and machines.

Carbon disclosures and information asymmetry: Empirical evidence on the importance of text in understanding numerical emission allowance disclosures

AbstractCarbon disclosures are essential for investors to evaluate firms’ efforts to combat climate change. In this study, we focus on a specific type of carbon disclosures—namely, emission allowance disclosures—that capture how firms implement emission reductions under the European Union emission trading system (EU ETS). Given the continuously changing institutional features of the EU ETS and the lack of authoritative guidance on how firms should account for emission allowances in their financial statements, it is exceedingly difficult for investors to understand numerical emission allowance disclosures and to compare them across—and even within—firms. Motivated by this criticism, we hypothesize and find that textual disclosures complementing numerical emission allowance disclosures are associated with lower information asymmetries between firms and their investors. Further analyses show that textual disclosures that: (i) describe the accounting approach, and (ii) contain institutional information on the EU ETS, respectively, are particularly important for improving the information environment of numerical emission allowance disclosures. Overall, our findings suggest that text can improve the understanding of numbers in a carbon disclosure context. Therefore, our study not only contributes to the (industrial ecology) literature but also has important implications for regulators, policymakers, investors, financial analysts, and firms.

Polynomial Moving Regression Band Stocks Trading System

In this research, we attempted to fit a trading system based on polynomial moving regression bands (MRB) to Nasdaq100 stocks from 2017 till the end of March 2024. Since stocks movement does not follow a linear behavior, we used multiple degree polynomial regression models to identify the stocks’ trends and two standard deviations from the regression model to generate the trading signals. This way, the MRB was transformed into a momentum indicator designed to identify strong uptrends that can be used by a fully automated trading system. Our results indicate that the behavior of Nasdaq100 stocks can be tracked using all three examined polynomial models and can be traded profitably using fully automated systems based on those models. The best performing model was the model that used a four-degree polynomial MRB achieving the highest average net profit (USD 162.73). Regarding the risks involved, the third model has the lowest loss in dollar value (USD −95.52), and the highest minimum percent of profitable trades (41.51%) and profit factor (0.55) that indicates that this strategy is relatively less risky than the other two strategies.

AI in Business and Finance: A Micro-to-Macro Perspective on Its Impact

This comprehensive survey examines the transformative impact of machine learning (ML), deep learning (DL), and natural language processing (NLP) across diverse business and finance sectors. From micro-level operational efficiencies to macro-level strategic decision-making, we delve into the multifaceted applications of AI and its influence on traditional practices. Our analysis highlights the increasing prominence of ML in enhancing decision-making and achieving greater accuracy and efficiency. We also identify key challenges such as data quality, modelinterpretability, and linguistic information processing. By addressing these challenges, we can further unlock the potential of ML in revolutionizing business and finance. We conducted a systematic literature review using the PRISMA technique to identify relevant research published within the last five years. Our findings reveal the growing adoption of ML techniques in various business and finance applications, such as fraud detection, risk assessment, customer relationship management, and algorithmic trading. We identified relevant publications through comprehensive searches in leading academic databases, including Scopus, Web of Science, and Google Scholar. We also discuss the challenges associated with implementing ML models in these domains, including data quality issues, model interpretability, and ethical considerations. Byunderstanding the applications, challenges, and opportunities associated with AI, businesses, policymakers, researchers, and investors can make informed decisions and leverage AI to drive innovation and growth in the business and finance sectors.

The Impact of the EU Carbon Border Adjustment Mechanism on Chinas Exports and Suggestions on Countermeasures

The European Parliament plans to gradually introduce the Carbon Border Adjustment Mechanism in 2023, with a complete implementation set for 2026. As an essential trading partner of the EU, China will shoulder an additional carbon border tariff due to the lack of low-carbon technology and the dependence on extensive development patterns. These extra costs will undermine the profit margins of Chinas carbon-intensive industry sectors, possibly resulting in decreased exports and a restructuring of production. The latest estimate of the exact costs of Chinas embedded carbon exports to the EU is a problem that has received limited academic attention. Using the IPCC carbon emission accounting methodology and non-competitive single-region input-output analysis, this research precisely measures the embedded carbon in Chinas exports to the EU for the nine most affected industries. Furthermore, this study quantifies the impact of the CBAM on Chinas exports of these nine industry sectors. The findings suggest that China should improve the domestic carbon emission trading system and take the initiative to participate in formulating a carbon pricing consultation and dialogue mechanism, mitigating the negative impact of the EU CBAM on exports.

An optimized decentralized peer-to-peer energy trading system for smart grids incorporating uncertain renewable energy sources through fuzzy optimization

The significant issue in today's world is that the power system is undergoing on account of unafforded power generation and distribution. Consequently, improper utilization of renewable energy, as well as its pricing mechanism of electrical energy, is also a vital issue in transmission and distribution systems (TDS). In addition, in the context of upcoming power systems, ensuring energy stability and effective energy management have become paramount. This paper introduces a novel approach to address these challenges by proposing an optimal demand response grid-connected decentralized peer-to-peer (P2P) energy trading system. This system efficiently manages energy transactions among prosumers, the grid, and renewable energy sources (RES) under uncertain conditions. Fuzzy optimization (FO) is employed to facilitate interconnections between these entities. A fuzzy logic controller with intelligent rules governs the overall strategy and pricing mechanism based on prosumer power deviation (PPD). Inspired by human thinking, these rules prioritize P2P transactions, with surplus energy exported to the main grid (MG) and energy imported from the MG when necessary. Pricing adjusts dynamically with load demand. Simulation results demonstrate the effectiveness of the fuzzy rules across various conditions, ensuring proper system operation. The proposed model also proves that the P2P energy trading system has reduced power consumption by balancing the generated power and the load demand. The proposed system is environmentally friendly, emitting no harmful gases.

Can't see the carbon for the CO2? Regulating CCU value chains under and beyond climate law

AbstractTo realise the objectives of the European Green Deal (EGD), fossil carbon will have to be not only reduced but also replaced with recycled carbon. The European Commission considers industrial carbon management and carbon capture and utilisation (CCU) technologies to be part of the solution. A value chain ensues when carbon dioxide (CO2) is captured and utilised as raw material. Examination of the climate, energy and environmental legal landscape of one specific CCU value chain—comprising of waste, waste incineration and plastic raw material—reveals the varied approaches regulation has towards CO2 and carbon. In this article, both carbon cycle legislation and legislation on the carbon source and the material storing carbon are analysed. The legislation being developed directly for CCU for products (other than synthetic fuels) focusses on the carbon cycle and CO2 under the EU emissions trading system (ETS) and a proposed Carbon Removal Certification Framework. Regulatory uncertainty remains for the studied CCU value chain as the capture of CO2 from waste incineration has yet to be incentivised under the EU ETS. Further, the criteria for the permanence of carbon storage in products to qualify under the EU ETS and of the long‐term storage under the Carbon Removal Certification Framework (CRCF) have yet to be developed. For a more complete understanding, we have also analysed waste and product regulations. The conceptual structure of the EU Waste Framework Directive does not seem to support circulating carbon. This context also raises the fundamental question of whether the purpose of waste incineration could be carbon recycling instead of mere energy production. Regarding material storing carbon, plastics, the regulator has been silent as CCU‐originated plastic raw material is not recognised in EU plastics law. These issues must be identified and resolved one by one before the EGD can be secured; revisiting only climate law instruments does not suffice.

Investigating the price determinants of the European Emission Trading System: a non-parametric approach

Understanding the intricacies of factors influencing European Union Emission Trading System (EU ETS) market prices is paramount for effective policy making and strategy implementation. We propose the use of the Information Imbalance, a non-parametric measure recently introduced in the physics community for quantifying the degree to which a set of variables is informative with respect to another one, to study the relationships among macroeconomic, economic, uncertainty, and energy variables concerning EU ETS price between January 2014 and April 2023. Our analysis shows that in Phase 3, commodity-related variables such as the ERIX index are the most informative in explaining the behaviour of the EU ETS market price. Transitioning to Phase 4, financial fluctuations take centre stage, with the uncertainty in the EUR/CHF exchange rate emerging as a crucial determinant. These results reflect the disruptive impacts of the COVID-19 pandemic and the energy crisis in reshaping the importance of the different variables. In addition to highlighting the shift in influential factors between Phase 3 and Phase 4, our findings underscore how macroeconomic volatility and energy disruptions have altered market dynamics. Notably, during the COVID-19 pandemic, the volatility in financial markets and fluctuations in energy demand and supply significantly affected the predictive power of different variables. Moreover, the energy crisis amplified the sensitivity of EU ETS prices to energy-related factors, reinforcing the importance of incorporating multiple dimensions into market analysis. Beyond variable analysis, we also propose to leverage the Information Imbalance to address the problem of mixed-frequency forecasting, and we identify the weekly time scale as the most informative for predicting the EU ETS price. Finally, we show how the Information Imbalance can be effectively combined with Gaussian Process regression for efficient nowcasting and forecasting using very small sets of highly informative predictors.

Artificial Intelligence in Finance: Applications and Implications

The definition and uses of Artificial Intelligence, often abbreviated as AI, has come a long way since its inception. This technology is rapidly changing some business operations in the areas of trading, identification of frauds, and customer service in particular, the modern finance sector, and this article highlights the importance of technology in these processes. Significant Applications of Artificial Intelligence in Finance: From Algorithmic Trading to Robo-Advisors. Explaining, the paper analyzes the current trends and practices in the industries, addressing the positive and negative aspects of AI in the finance sector, with respect to the visions of the future. One that relates to the socio-technical implications that include the use of such technology in finance and the associated risks of data breach, availability, and loss of control and trust in processes.

Predictive modeling in high-frequency trading using machine learning

High-frequency trading (HFT) has transformed financial markets by enabling rapid trade execution and exploiting minute market inefficiencies. This study explores the application of machine learning (ML) techniques to predictive modeling in HFT. Four ensemble boosting methodsAdaptive Boosting, Logic Boosting, Robust Boosting, and Random Under-Sampling (RUS) Boostingwere evaluated using order book data from Euronext Paris. The models were trained and validated on data from a single trading day, with performance assessed using precision, recall, ROC curves, and feature importance analysis. Results indicate that Robust Boosting achieves the highest precision (90%), while Adaptive Boosting and RUS Boosting demonstrate higher recall (94% and 93%, respectively). This research highlights the potential of ML in enhancing HFT strategies, with implications for future trading system developments.