Euronext Paris Research Articles

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.

A Whole-Spine Radiography Study to Reduce Patient Exposure Dose and Artifacts Using the EOS Imaging System.

Whole-spine radiography can be accomplished through two methods: (1) segmented imaging employing X-ray tube angulation and detectors, or (2) the Euronext Paris Advanced Orthopedic Solutions (EOS) 2D Imaging system that can capture the entire spine in a single image using X-ray tubes and detectors oriented at a 90-degree angle. This study aimed to establish optimal EOS examination parameters based on patient morphotype and scan speed to reduce patient radiation exposure, repeat examinations, heat stress on equipment, and X-ray tube cooling time. X-ray exposure conditions involved adjustments of scan speed ranging from two to four steps, contingent upon the patient's morphotype ('S', small body; 'M', medium body; and 'L', large body. Patient dose measurements were conducted 20 times for each set of conditions. When transitioning from an 'S' to an 'M' morphotype at a constant scan speed, the entrance skin dose (ESD) exhibited an increase of approximately 41.25 ± 4.57%. A similar change from an 'M' to an 'L' morphotype resulted in an ESD increase of roughly 59.56 ± 24.00%. A transition from an 'S' to an 'L' morphotype at the same scan speed manifested an ESD elevation of approximately 124.21 ± 26.96%. This study underscores significant variations in radiation dose, ranging from 40% to 50%, when altering morphotype while maintaining a consistent scan speed.

The link between abnormal numbers and price movements of financial securities: How does Benford’s law predict stock returns?

This paper studies the potential effect of deviation from Benford’s law on stock return prediction. Departures from the anticipated pattern can act as early indicators of irregular market behavior or possible fraudulent activities, both of which have the potential to impact future price trends. In this study, the deviation is measured by chi-squared test statistics over the first significant digit. Preliminary results indicate no compliance between daily stock returns data from Euronext Paris and Tunisian stock markets with Benford’s distribution. Then, the impact on the returns is explored via several models: linear regression and smooth transition models with various transition variables. Empirical results show the nonlinear effect of Benford’s law on stock returns prediction. We illustrate that this law can detect and predict abnormal returns generated by fraudulent or abnormal activities in both developed and emerging markets. By using Benford’s Law to analyze leading digits, investors and analysts can effectively identify irregularities and gain valuable insights into market dynamics.

Enhancing stock market prediction accuracy with recurrent deep learning models: A case study on the CAC40 index

This paper explores the application of Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks for stock price prediction over a 10-day horizon. The study aims to compare the predictive performance of these two deep learning architectures within the context of financial forecasting. Utilizing historical stock data from the CAC40 dataset, which represents a capitalization-weighted measure of the 40 most significant stocks on the Euronext Paris, we train and evaluate RNN and LSTM models to forecast future stock prices. Our results demonstrate the superior performance of LSTM networks in capturing the intricate temporal dependencies inherent in stock price data. Compared to standard RNNs, LSTM models exhibit higher accuracy and provide more reliable forecasts over the 10-day prediction period. The specialized memory cells and gating mechanisms in LSTM networks enable them to effectively identify both short-term changes and long-term patterns in stock prices, thus outperforming traditional RNN architectures. This enhanced ability to model the complex dynamics of stock market data underscores the potential of LSTM networks to improve investment decision-making, risk management, and the overall efficiency of financial markets. The insights gained from this study contribute to the growing body of knowledge on the application of deep learning in finance and investment, offering valuable guidance for practitioners and researchers seeking to harness the power of advanced algorithms for stock market prediction and optimization.

Equity auction dynamics: latent liquidity models with activity acceleration

Equity auctions display several distinctive characteristics in contrast to continuous trading. As the auction time approaches, the rate of events accelerates causing a substantial liquidity buildup around the indicative price. This, in turn, results in a reduced price impact and decreased volatility of the indicative price. In this study, we adapt the latent/revealed order book framework to the specifics of equity auctions. We provide precise measurements of the model parameters, including order submissions, cancelations, and diffusion rates. Our setup allows us to describe the full dynamics of the average order book during closing auctions in Euronext Paris. These findings support the relevance of the latent liquidity framework in describing limit order book dynamics. Lastly, we analyze the factors contributing to a sub-diffusive indicative price and demonstrate the absence of indicative price predictability.

When private information becomes fraud: evidence from Euronext Paris

When private information becomes fraud: evidence from Euronext Paris

Market Liquidity and Competition Among Designated Market Makers

Do competition and incentives offered to designated market makers (DMMs) improve market liquidity? We employ data from NYSE Euronext Paris to show that exogenous changes in contract design lead to significant decreases in quoted and effective spreads. In particular, market liquidity increases the most for stocks with the largest increase in competition among DMMs. Our analysis shows that competition among DMMs is an important aspect of contract design, along with elements such as rebates and requirements. This paper was accepted by Kay Giesecke, finance. Funding: M. G. Subrahmanyam thanks the Alexander von Humboldt Foundation for generous financial support via the Anneliese Maier Award. L. Pelizzon thanks the Leibniz Institute for Financial Research SAFE for financially sponsoring this research and Italian Ministry for University and Research [MIUR–2017RSMPZZ]. This work was also supported by the Deutsche Forschungsgemeinschaft [Grant 329107530]. Supplemental Material: The Internet Appendix and data files are available at https://doi.org/10.1287/mnsc.2022.01801 .

From the delisting case of P&G to its strategic adjustments and financial status in recent years

As a giant in the FMCG industry, P&’s every move has influenced the choice of consumers and the trend of the industry. In order to maintain their profitability and competitive position, they attach great importance to strategic management. They had their best moments. In 2008, P&G became one of the world’s top 20 companies with net profits of $12 billion. Big acquisitions had allowed them to grow rapidly and continuously. However, in 2013, they began to decline. Declining sales have forced P&G to make strategic changes. In 2019, a piece of news about Procter & Gamble’s delisting from Euronext Paris swept the Internet. In order to explore how large enterprises make the right strategic choice in the face of crisis and analyze the outcomings, this paper will start with the delisting case of Procter & Gamble, analyze its strategic environment, strategic adjustments and financial results in recent years, and finally form conclusions and some suggestions.

Does Stock Market React to Terrorist Attack? An Evidence from 9/11 Attack Using Event Study

The global economy and financial markets around the world are said to be adversely affected by the terrorist attack of 11 September 2001. The present study empirically evaluates the impacts of terrorist attacks on the top 20 stock market indices of the world. The Event study approach is used to conclude that there is a significant impact of the terrorist attack on stock indices of the selected countries, as the following stock market indices showed an adverse abnormal return on the day of the event namely, New York Stock Exchange, NASDAQ, Shenzhen Stock Exchange, National Stock Exchange of India, Frankfurt Stock Exchange, Bombay Stock Exchange, Euronext Paris Exchange, Johannesburg stock exchange and Euronext Brussels. While the rest of the selected stock markets showed a positive abnormal return on the event date. In the following days of the event, the Stock exchange in China showed a negative abnormal CAR for 80 days, while stock exchanges in India showed a negative abnormal CAR in the 20 days following the event. Most of the stock exchanges were not much affected by the event, even if there was an effect it didn’t last long, as the abnormal return was positive after a while.

LOB modeling using Hawkes processes with a state-dependent factor

A point process model for order flows in limit order books is proposed, in which the conditional intensity is the product of a Hawkes component and a state-dependent factor. In the LOB context, state observations may include the observed imbalance or the observed spread. Full technical details for the computationally-efficient estimation of such a process are provided, using either direct likelihood maximization or EM-type estimation. Applications include models for bid and ask market orders, or for upwards and downwards price movements. Empirical results on multiple stocks traded in Euronext Paris underline the benefits of state-dependent formulations for LOB modeling, e.g. in terms of goodness-of-fit to financial data.

Modeling the impact of stock exchange migration on trading volumes in competing markets

This article examines the impact of a stock exchange’s migration on its trading activity and the performance of competing markets. It examines the importance of the location of trading floors for all market participants; analyzes the relationship between the location of a trading floor and the speed of transactions in the stock market, as well as the impact of accelerating transactions on trading activity. The migration of the Euronext exchange from Paris to Basildon on September 25, 2010, was chosen as the event under study. The method of matched pairs demonstrates the possibility of rationalizing of experimental and control sample for further analysis and modeling of the impact of the relocation of the considered stock market on its and competing exchange’s performance. It is illustrated multidirectional changes in the shares of the value volume of trading and the number of transactions on the Euronext exchange itself and four competing markets. In order to model the impact of the migration of the exchange the method of “difference-in-differences” is suggested, that bases on the use of experimental and control samples and on the construction of regression equations of a special kind. Theoretical bases, advantages and disadvantages of the application of the method of “difference of differences” in the analysis of the impact of certain events on economic results were analyzed. Empirical estimates showed a different expected increase in the value of trading volume after the event on the Euronext and Chi-X Europe exchanges. It is noted that as a result of the migration, the Euronext exchange became closer to the alternative trading floors located in London. This accelerated the execution of transactions between them, and stimulated the alternative markets to become more competitive, faster and more fully reflect the changes taking place on the main Euronext Paris market.

Threshold effects of board gender diversity on firm performance: panel smooth transition regression model

PurposeThis study aims to investigate whether threshold effects exist in the relationship between board gender diversity and firm performance.Design/methodology/approachThis study applies the panel smooth threshold regression model (PSTR) to a sample of 284 non-financial French firms listed on Euronext Paris over the period 2009–2017. Firm performance proxies are Tobin’s Q and return on assets (ROA). The board gender diversity is measured by the percentage of women participation in board.FindingsThreshold effects in the relationships between board gender diversity and firm performance measures are found. For Tobin’s Q, the model has one threshold at the 34.17% of women directors’ appointment on boards. Similarly, for ROA, the model has one threshold at the 38.28% of women presence in the board. The results show that above the estimated threshold, women directorship has a positive impact on firm performance. However, below the threshold, there is a neutral relationship. The findings support the critical mass view that a minimum of one third women representation in board is compulsory to achieve the desired effect of gender diversity.Practical implicationsThis study’s finding provides useful insights to managers, investors and policymakers. Managers and investors can identify the adequate board gender diversity levels that enhance firm performance. Policymakers are divided on whether mandatory or voluntary board gender quota should be adopted. This study suggests that a quota of one third can be used in policy implementation.Originality/valueUnlike prior studies that consider the relationship between firm performance and board gender diversity as linear, to the best of the authors’ knowledge, this study is the first to investigate the threshold effects in this relationship using a new econometric approach.

Marked point processes and intensity ratios for limit order book modeling

This paper extends the analysis of Muni Toke and Yoshida (2020) to the case of marked point processes. We consider multiple marked point processes with intensities defined by three multiplicative components, namely a common baseline intensity, a state-dependent component specific to each process, and a state-dependent component specific to each mark within each process. We show that for specific mark distributions, this model is a combination of the ratio models defined in Muni Toke and Yoshida (2020). We prove convergence results for the quasi-maximum and quasi-Bayesian likelihood estimators of this model and provide numerical illustrations of the asymptotic variances. We use these ratio processes to model transactions occurring in a limit order book. Model flexibility allows us to investigate both state-dependency (emphasizing the role of imbalance and spread as significant signals) and clustering. Calibration, model selection and prediction results are reported for high-frequency trading data on multiple stocks traded on Euronext Paris. We show that the marked ratio model outperforms other intensity-based methods (such as “pure” Hawkes-based methods) in predicting the sign and aggressiveness of market orders on financial markets.

Intraday volatility smile: Effects of fragmentation and high frequency trading on price efficiency

In 2007, the European Markets in Financial Instruments Directive ended the national concentration rule. As a result, market fragmentation has accelerated across multiple trading venues. Spatial fragmentation might create opportunities and incentives for High Frequency arbitrageurs to fill the void left by the lack of Reg NMS type order routing requirements in Europe, without neglecting market integrity. This paper examines intra-day volatility and price efficiency through the metric of the normalized volatility ratio for the years 2006, 2012 and 2013 for Euronext Paris, BATS and Chi-X Europe. Our findings show that price determination remains inefficient at market opening due to the complexity of price discovery activity following a period of non-trading and heavy information releases. However, we demonstrate that an active participation of high-frequency traders significantly improves market efficiency at opening session.

Diversidade do perfil dos gestores como uma alavanca estratégica para criação de valor: um enfoque no conservadorismo contábil de empresas brasileiras e francesas

Purpose – The research aimed to analyze the relationship between the diversity of the managers' profile as a lever for value creation and the accounting conservatism of Brazilian and French companies.Design/methodology/approach – The sample consisted of 71 Brazilian companies and 67 French companies, listed in the B3 Index IBrX-100 and the SBF 120 Index of Euronext Paris, respectively. Multiple Regression was used to analyze the data (2011 to 2015).Findings – The results revealed that the characteristics of the diversity of the profile of Brazilian managers that are related to accounting conservatism are: age, place of formation and position occupied in the directive body. In France, the characteristics are: degree of schooling, link with the company and function performed.Research limitations/implications – The limitation of the impossibility of generalizing the results is highlighted. As theoretical contributions, this research analyzes an element that can be considered for analysis in the face of accounting conservatism: the profile of managers.Practical implications – The diversity of the managers' profile should be considered in companies, since it has repercussions on accounting conservatism, that is, on how managers conduct accounting to maximize company value.Social implications – The findings have social implications for professionals who aim to enter the Brazilian and French labor market.Originality/value – The study advances in the accounting area, as it analyzes the governing body of organizations, an important differential in the analysis of the demographic, professional and performance characteristics of managers and their relationship with accounting conservatism.

Equivalent Dose and Risk of Exposure Induced Cancer Death of Different Organs due to Various Image Techniques of EOS Imaging System.

Background: Euronext Paris Advanced Orthopedic Solutions (EOS) system is a new radiography system, capable of obtaining two-dimensional and three-dimensional images from bony structures in the body. Objective: The aim of this study is to estimate equivalent dose and the risk of exposure induced cancer death (REID) in different organs of body due to EOS imaging system.Material and Methods: In this experimental study, totally 120 patients were evaluated for various imaging techniques of lower limb, full spine and whole body. Equivalent dose and REID for colon, liver, lung, stomach, breast, bladder, ovary, blood cells (leukemia) and other organs were calculated using PCXMC software (version 2.0.1.2) based on Monte Carlo simulation of X-ray and human phantoms. The data on imaging technique, including age, sex, kVp, dose area product (DAP), mA, focal to detector distance were introduced as the input of PCXMC.Results: The maximum equivalent dose (mSv) due to EOS imaging system, was estimated for the bladder 0.240±0.066 for the full body technique and 0.240±0.093 for the lower limb technique, respectively, in both males and females. The maximum organ REID (incidence per million) due to EOS imaging system was estimated for lungs as 2.59±1.0 and 2.53±0.9, for the full body technique in both males and females, respectively. Conclusion: Generally, the equivalent dose and REID by EOS imaging system in different organs of body is low due to the low radiation dose received by the body in different techniques and views.

Does International Financial Reporting Standard 8 improve the firms' information environment?

PurposeThis article analyzes the effect of International Financial Reporting Standard (IFRS) 8 on the informational content of segment data. It aims to assess the change in quality of the financial analysts' and the shareholders' information environment due to the new segment reporting standard to verify the International Accounting Standards Board’s (IASB) expectations and the conclusions of its post-implementation review.Design/methodology/approachBased on a sample of 250 companies listed on Euronext Paris in France, a country with poor legal protection for shareholders, over a nine-year period, the authors test whether the new standard makes the financial analysts' forecasts more accurate and reduces the implied cost of equity capital.FindingsThe findings show that IFRS 8 partially improves the informational content of segment data, partially supporting the outcome of IASB. The management approach may have forced some firms to change their segmentation to provide a more economic view of the business. The poor legal protection for shareholders in France may explain this result.Research limitations/implicationsDue to proprietary and agency costs, firms may withhold segment information whatever the standard used.Practical implicationsThis study contributes to the ongoing debate about IFRS 8 and may interest financial statement users and the international standard-setter for such a criticized standard.Originality/valueThe results contribute to the segment reporting literature by addressing the partial improvement of information environment under the managerial approach in a country with lower investor protection.

Financial transaction tax and market quality: Evidence from France†

AbstractThe effectiveness of Financial Transaction Taxes (FTTs) for deterring speculative trading and improving market quality remains controversial. Studying the FTT imposed in 2012 on large‐cap stocks traded on the Euronext Paris, we find that stocks subject to the FTT subsequently experience significantly decreased turnover and increased spreads relative to the untaxed peers. Further tests suggest that the FTT imposition induces investors to migrate their trades and results in less informativeness in the taxed stocks. Collectively our findings support the view that FTTs deter informed trades and reduce market quality.

Međuzavisnost između tržišta u razvoju i razvijenih berzi - slučaj makedonske, beogradske, "Six" švajcarske i "Euronext" pariske berze

The aim of the paper is to examine the level of interdependence between developing and developed stock markets. The correlation of the Macedonian (MBI10) stock exchange index with the Belgrade (BELEX15), the Six Swiss (SLI) and the Euronext Paris (CAC40) stock exchanges from November 2005 to October 2018 was studied. In order to assess the impact of the crisis on the interrelations between these equity markets, the analyzed period was we subdivided into three segments (pre-crisis, during crisis and post-crisis) and the data sets were subjected to linear regression analysis. The research results indicate an increased correlation of the Macedonian with Belgrade and Euronext Paris Stock Exchanges and decreased correlation with Six Swiss during the time of financial distress comparing to pre and post crisis periods. The findings of this study contribute to the overall picture of the relationship between stock markets in the time of Financial Crisis. Moreover, by investigating the interrelationship between developing and developed European stock markets, the results suggest that financial market integration is time-varying.

State and self-regulation for better governance: an implication of collibration

PurposeThe purpose of this study is to study the evolution of French corporate governance law in light of collibration approach and bring statistical evidence from French Companies Executive Compensation practices.Design/methodology/approachThe study has used mixed methods. In the first part, the authors analyzed the French laws in the light of collibration. In the second part of the study, the authors used unbalanced panel data to test the hypotheses related to executive remuneration based on the theoretical underpinning of collibration. Data for 173 firms listed in the Euronext Paris Index is collected from the Bloomberg database. Seemingly unrelated regression (SUR) analysis is performed to investigate the impact of collibration on the governance disclosure of French-listed firms.FindingsSUR results indicate that board size plays a significant role in the governance disclosure before collibration. However, the collibration model is found to be more effective in ensuring the desired level of governance disclosure. Under the collibration approach, executive remuneration, frequency of board meetings, executive directors in the compensation committee and independent directors play a significant role in governance disclosure. Board size, however, does not have a substantial impact on governance disclosure after the adoption of collibration mechanism.Research limitations/implicationsResults provided by this study can allow regulators to improve corporate disclosure regime in France, which could play a vital role in safeguarding the interest of stakeholder.Originality/valueThe authors study the impact of collibration on the extent of governance disclosure in the context of France. Empirical evidence on the implication of collibration as governance mechanisms to enhance stakeholder confidence is rare and allows this study to make a unique contribution to the governance literature.