Search results

This paper aims to analyze the role and performance of different artificial intelligence (AI) algorithms in forecasting future movements in the main indices of the world’s largest stock exchanges.

Drawing on finance-based theory, an empirical and experimental study was carried out using four AI-based models. The investigation comprised training, testing and analysis of model performance using accuracy metrics and F1-Score on data from 34 indices, using 9 technical indicators, descriptive statistics, Shapiro–Wilk, Student’s t and Mann–Whitney and Spearman correlation coefficient tests.

All AI-based models performed better than the markets' return expectations, thereby supporting financial, strategic and organizational decisions. The number of days used to calculate the technical indicators enabled the development of models with better performance. Those based on the random forest algorithm present better results than other AI algorithms, regardless of the performance metric adopted.

The study expands knowledge on the topic and provides robust evidence on the role of AI in financial analysis and decision-making, as well as in predicting the movements of the largest stock exchanges in the world. This brings theoretical, strategic and managerial contributions, enabling the discussion of efficient market hypothesis (EMH) in a complex economic reality – in which the use of automation and application of AI has been expanded, opening new avenues of future investigation and the extensive use of technical analysis as support for decisions and machine learning.

The AI algorithms' flexibility to determine their parameters and the window for measuring and estimating technical indicators provide contextually adjusted models that can entail the best possible performance. This expands the informational and decision-making capacity of investors, managers, controllers, market analysts and other economic agents while emphasizing the role of AI algorithms in improving resource allocation in the financial and capital markets.

The originality and value of the research come from the methodology and systematic testing of the EMH through the main indices of the world’s largest stock exchanges – something still unprecedented despite being widely expected by scholars and the market.

This paper aims to focus on exploring and understanding the practice of analyzing the determinants of the Moroccan Dirham by foreign exchange professionals in trading rooms in the context of transitioning to a more flexible regime initiated by Moroccan authorities. The objective of this study is to highlight how foreign exchange operators analyze the determinants of the Moroccan Dirham in the context of exchange rate liberalization, focusing primarily on qualitative data rather than quantitative data.

Therefore, this paper opted for a methodological approach using interview surveys to understand the underlying behavior of Moroccan foreign exchange operators, conducting a content analysis. This paper targeted six foreign exchange operators from nine Moroccan banks authorized as market makers by Bank Al-Maghrib.

The results indicate that the fluctuations of the Moroccan Dirham are closely linked to two main factors: the analysis of the EUR/USD exchange rate and market liquidity analysis. Furthermore, content analysis revealed five essential aspects regarding the practice of analyzing the determinants of the Dirham: “Dirham determinants,” “complementarity between technical analysis and fundamental analysis,” “trends and reversals,” “utility of macroeconomic models” and “psychological factors.”

Certainly, this methodology allows for exploring and understanding the underlying behavior of currency operators but inherently generates a certain degree of subjectivity that can affect the research validity. Indeed, the subjectivity can arise from the responses of the currency operators themselves. They may present the phenomenon coherently or selectively choose the elements they remember to respond to. On the other hand, the validity of this type of research relies on the researcher's ability to cultivate empathy throughout the knowledge creation process. The empathetic stance adopted in this study proved to be complex due to the uniqueness of operators and interaction, sometimes making it challenging to combine empathy, respect and critical thinking (Olivier De Sardan, 2004). Furthermore, the researcher is often faced with an interpretation bias, which can manifest not only during the coding of collected data but also during the analysis of the constructed content. To mitigate this interpretation bias, this paper subjected the collected data to a double coding procedure.

This study aims to narrow the gap in opinions between academics and practitioners by providing a practical overview for change novices.

This study is the pioneering inquiry exploring the process of determining the Moroccan dirham within the transition to a flexible exchange rate regime, using an exploratory methodological approach.

China is a large country with different regions due to regional differences and project characteristics, and the selection of prefabricated building technology according to local conditions is the key to its sustainable development in China. The purpose of this paper is to develop the suitability evaluation system of prefabricated building technology from the perspective of the suitability concept and to analyze the selection path of prefabricated building technology and to provide a reference for selecting and developing prefabricated building technology schemes that meet regional endowments.

Based on relevant literature, technical specifications, and standards, this paper constructs an index system for analyzing the technical suitability of prefabricated buildings. It includes 23 indicators, 7 dimensions, and 3 aspects through the semantic clustering method. Following this, the comprehensive weight of each index is determined using the order relation method (G1) and the continuous ordered weighted averaging (COWA). The selection of technical schemes is comprehensively evaluated using Visekriterjumska Optimizacija Ikompromisno Resenje (VIKOR) and Fuzzy Comprehensive Evaluation Method.

 (1) The technical suitability of prefabricated buildings is influenced by 7 core factors, such as adaptability of resources and environment, project planning and design level, and economic benefit; (2) When selecting the appropriate technology for prefabricated buildings, economic suitability should be considered first, followed by regional suitability, and then technical characteristic; (3) The prefabricated building technology suitability evaluation model constructed in this paper has high feasibility in the technical suitability selection of the example project.

The comprehensive evaluation model of prefabricated building technology suitability constructed in this paper provides technical selection support for the promotion and development of prefabricated buildings in different regions. In addition, the model can also be widely used in areas related to prefabricated building consulting and decision-making, and provides theoretical support for subsequent research.

This study provides a new decision support tool for prefabricated building technology suitability selection, which helps decision makers to make more rational technology choices.

This study has a positive impact on the advancement of prefabricated building technology, the improvement of construction industry standards, and the promotion of sustainable development.

The contribution of this study is twofold: (1) Theoretically, this paper provides technical evaluation indicators and guidelines for provincial and regional governments to cultivate model cities, plan industrial bases, etc. (2) In practice, it offers project-level appropriate technology system solutions for the technology application of assemblers in various regions.

This study aims to investigate to what extent the predictability of the standard and poor’s 500 (S&P 500) price levels is enhanced by investors’ sentiments extracted from social media content, specifically platform X.

Two recurrent neural network (RNN) models are developed. The first RNN model is merely based on historical records and technical indicators. In addition to the variables included in the first RNN model, the second RNN model comprises the outputs of the sentiment analysis, performed using the TextBlob library. The study was conducted between December 28, 2011, and December 30, 2021, over 10 years, to obtain better results by feeding the RNN models with a significant quantity of data by extending the period and capturing an extensive timespan.

Comparing the performance of both models reveals that the second model, with sentiment analysis inputs, yields superior outcomes. The mean absolute error (MAE) of the second model registered 72.44, approximately 50% lower than the MAE of the technical model, its percentage value, the mean absolute percentage error, recorded 2.16%, and finally, the median absolute percentage error reached a value of 1.30%. This underscores the significant influence of digital platforms in influencing the behavior of certain assets like the S&P 500, emphasizing the relevance of sentiment analysis from social media in financial forecasting.

This study contributes to the growing body of literature by highlighting the enhanced predictive power of deep learning models that incorporate investor sentiment from social media, thereby advancing the application of behavioral finance in financial forecasting.

Information and communication technologies are being increasingly used across various sectors including the tourism industry. However, equitable access to online information remains a significant challenge, especially for people with disabilities (PwD). There is a pressing need for research into the accessibility of the internet to promote social equality. This study aims to identify patterns in both the technical accessibility and the content information related to accessibility and disability that is available on the official websites of leading global tourist destinations.

A cluster analysis assessed the technical accessibility of the websites, while a principal component analysis evaluated the content information concerning accessibility and disability.

There has been a substantial improvement in the technical accessibility of tourism websites over that described in earlier studies. There have been no advances in content information on accessibility and disability, which continues to be very heterogeneous and dispersed.

This evaluation of the technical accessibility and content related to accessibility and disability on tourism websites provides a basis for developing strategies to eliminate barriers that PwD encounter in accessing tourism information. To augment the efficacy of big data inputs, it is imperative to homogenise variables associated with technical access and content information on accessibility. Such standardisation will improve the functionality of algorithms critical to the Internet of Things and artificial intelligence technologies. These enhancements are likely to spur innovations that bridge the inequality gap and promote environments where technology serves as a cornerstone of social inclusion and equality.

信息和通信技术在包括旅游业在内的很多行业的应用越来越广泛。 互联网是游客不可或缺的工具, 但并非每个人（在本研究中为残疾人、PwD）都能以相同的方式获取可用信息。有必要对无障碍使用互联网进行研究, 以促进社会平等。本研究旨在识别全球主要旅游目的地官方网站的技术可及性以及网站内容上有关可及性和残疾信息的规律。

聚类分析评估了网站的技术可及性, 主成成分分析评估了网站的可及性和残疾的相关内容信息。

与早期研究中描述的相比, 旅游网站的技术可访问性有了实质性的改善。关于无障碍和残疾的内容信息没有任何改善, 仍然非常异质性和分散性。

本研究对旅游网站的技术可及性以及有关可及性和残障人士的内容信息的评估为制定以消除残疾人旅游所面临的障碍的未来战略奠定了基础。为了提高大数据输入的有效性, 技术可及性和可及性内容信息相关的变量必须标准化和同质化。这将提高关键算法的效率,以增加物联网和人工智能技术的功能。这些改进可以促进创新, 缩小不平等差距, 并营造让技术成为社会包容和平等基石的环境因素。

Las tecnologías de la información y la comunicación (TIC) se utilizan cada vez más en diversos sectores, incluido el turístico. Sin embargo, el acceso equitativo a la información online sigue siendo un reto importante, especialmente para las personas con discapacidad. Existe una necesidad acuciante de investigar la accesibilidad de Internet para promover la igualdad social. Este estudio identifica patrones en la accesibilidad técnica y en el contenido de la información sobre accesibilidad y discapacidad disponible en las páginas web oficiales de los principales destinos turísticos mundiales.

Un análisis de conglomerados evaluó la accesibilidad técnica y un análisis de componentes principales analizó el contenido de la información sobre accesibilidad y discapacidad en los sitios web.

Se constata una mejora sustancial en la accesibilidad técnica de las páginas web de turismo con respecto a los resultados de estudios anteriores. No ha habido avances en el contenido de la información sobre accesibilidad y discapacidad, que sigue siendo muy heterogénea y dispersa.

Esta evaluación de la accesibilidad técnica y del contenido de la información relativo a la accesibilidad y la discapacidad en las páginas web turísticas proporciona una base para desarrollar estrategias que eliminen las barreras con las que se encuentran las personas con discapacidad para acceder a la información turística. Para mejorar la eficacia de las entradas de big data, es necesario estandarizar las variables relacionadas con la accesibilidad técnica y el contenido de la información sobre accesibilidad. Esta normalización mejorará la funcionalidad de los algoritmos fundamentales para el internet de las cosas y las tecnologías de inteligencia artificial. Es probable que estas mejoras impulsen innovaciones que reduzcan la brecha de la desigualdad y promuevan entornos en los que la tecnología sirva como piedra angular de la inclusión social e igualdad.

In this study, the central objective is to foresee stock market signals with the use of a proper structure to achieve the highest accuracy possible. For this purpose, three hybrid models have been developed for the stock markets which are a combination of support vector machine (SVM) with meta-heuristic algorithms of particle swarm optimization (PSO), imperialist competition algorithm (ICA) and genetic algorithm (GA).All the analyses are technical and are based on the Japanese candlestick model.

Further as per the results achieved, the most suitable algorithm is chosen to anticipate sell and buy signals. Moreover, the authors have compared the results of the designed model validations in this study with basic models in three articles conducted in the past years. Therefore, SVM is examined by PSO. It is used as a classification agent to search the problem-solving space precisely and at a faster pace. With regards to the second model, SVM and ICA are tested to stock market timing, in a way that ICA is used as an optimization agent for the SVM parameters. At last, in the third model, SVM and GA are studied, where GA acts as an optimizer and feature selection agent.

As per the results, it is observed that all new models can predict accurately for only 6 days; however, in comparison with the confusion matrix results, it is observed that the SVM-GA and SVM-ICA models have correctly predicted more sell signals, and the SCM-PSO model has correctly predicted more buy signals. However, SVM-ICA has shown better performance than other models considering executing the implemented models.

In this study, the data for stock market of the years 2013–2021 were analyzed; the long length of timeframe makes the input data analysis challenging as they must be moderated with respect to the conditions where they have been changed.

In this study, two methods have been developed in a candlestick model; they are raw-based and signal-based approaches in which the hit rate is determined by the percentage of correct evaluations of the stock market for a 16-day period.

Construction projects commonly encounter complicated delay problems. Over the past few decades, numerous delay analysis methods (DAMs) have been developed. There is no consensus on whether existing DAMs effectively resolve delays, particularly in the case of complex concurrent delays. Thus, the primary objective of this study is to undertake a comprehensive and systematic literature review on concurrent delays, aiming to answer the following research question: Do existing delay analysis techniques deal with concurrent delays well?

This study conducts a comprehensive review of concurrent delays by both bibliometric and systematic analysis of research publications published between 1982 and 2022 in the Web of Science (WoS) and Scopus databases. For quantitative analysis, a bibliometric mapping tool, the VOSviewer, was employed to analyze 68 selected publications to explore the co-occurrence of keywords, co-authorship and direct citation. Additionally, we conducted a qualitative analysis to answer the targeted research question, identify academic knowledge gaps and explore potential research directions for solving the theoretical and practical problems of concurrent delays.

Concurrent delays are a critical aspect of delay claims. Despite DAMs developed by a limited number of research teams to tackle issues like concurrence, float consumption and the critical path in concurrent delay resolution, practitioners continue to face significant challenges. This study has successfully identified knowledge gaps in defining, identifying, analyzing and allocating liability for concurrent delays while offering promising directions for further research. These findings reveal the incompleteness of available DAMs for solving concurrent delays.

The outcomes of this study are highly beneficial for practitioners and researchers. For practitioners, the discussions on the resolution process of concurrent delays in terms of identification, analysis and apportionment enable them to proactively address concurrent delays and lay the groundwork for preventing and resolving such issues in their construction projects. For researchers, five research directions, including advanced DAMs capable of solving concurrent delays, are proposed for reference.

Existing research on DAMs lacks comprehensive coverage of concurrent delays. Through a scientometric review, it is evident that current DAMs do not deal with concurrent delays well. This review identifies critical knowledge gaps and offers insights into potential directions for future research.

Efficiency and quality are primary factors for the survival of health systems. The evaluation of the efficiency of the healthcare system is a crucial component of promoting long-term health policy actions. Healthcare capacity indicators provide a basis for evaluating and comparing the performance of different healthcare organizations. Intrinsic quality indicators are Donabedian (1980)’s structural and process elements of quality of healthcare. This study aims to integrate capacity and intrinsic quality indicators of healthcare while measuring the efficiency of provinces by using radial and non-radial efficiency measurement techniques.

Efficiency analysis performed in Turkey from 2015 to 2020 by performing input-oriented radial, nonradial, and super-efficiency estimates for 81 provinces of Turkey by incorporating capacity and intrinsic quality indicators into the different model specifications.

Radial and nonradial efficiency results have an increasing trend over the study years obtained from the efficiency models showing high average scores obtained from the models that include intrinsic quality of care indicators. Statistically significant mean rank differences are observed between different radial efficiency models for all study years (p < 0.001). Negative and moderate level correlations were observed between radial efficiency results and quality of care indicators (r < 0.70).

Under long-term centralized health policies, increases in efficiency result in decreased intrinsic quality of care indicators. A better synthesis of health system capacity and intrinsic healthcare quality indicators is necessary to generate evidence-based health systems.

Avoided emissions refer to greenhouse gas emission reductions that are a result of using a product or are emission removals due to a decision or an action. Although there is no uniform standard for calculating avoided emissions, market actors have started referring to avoided emissions as “Scope 4” emissions. By default, making a claim about Scope 4 emissions gives an appearance that this Scope of emissions is a natural extension of the existing and accepted Scope-based emissions accounting framework. The purpose of this study is to explore the implications of this assumed legitimacy.

Via a desktop review and interviews, we analyse extant Scope 4 company reporting, associated accounting methodologies and the practical implications of Scope 4 claims.

Upon examination of Scope 4 emissions and their relationship with Scopes 1, 2 and 3 emissions, we highlight a dynamic and interdependent relationship between quantification, commensuration and standardization in emissions accounting. We find that extant Scope 4 assessments do not fit the established framework for Scope-based emissions accounting. In line with literature on the territorializing nature of accounting, we call for caution about Scope 4 claims that are a distraction from the critical work of reducing absolute emissions.

We examine the implications of assumed alignment and borrowed legitimacy of Scope 4 with Scope-based accounting because Scope 4 is not an actual Scope, but a claim to a Scope. This is as an act of accounting territorialization.

Because the dynamic characteristics of the stock market are nonlinear, it is unclear whether stock prices can be predicted. This paper aims to explore the predictability of the stock price index from a long-memory perspective. The authors propose hybrid models to predict the next-day closing price index and explore the policy effects behind stock prices. The paper aims to discuss the aforementioned ideas.

The authors found a long memory in the stock price index series using modified R/S and GPH tests, and propose an improved bi-directional gated recurrent units (BiGRU) hybrid network framework to predict the next-day stock price index. The proposed framework integrates (1) A de-noising module—Singular Spectrum Analysis (SSA) algorithm, (2) a predictive module—BiGRU model, and (3) an optimization module—Grid Search Cross-validation (GSCV) algorithm.

Three critical findings are long memory, fit effectiveness and model optimization. There is long memory (predictability) in the stock price index series. The proposed framework yields predictions of optimum fit. Data de-noising and parameter optimization can improve the model fit.

The empirical data are obtained from the financial data of listed companies in the Wind Financial Terminal. The model can accurately predict stock price index series, guide investors to make reasonable investment decisions, and provide a basis for establishing individual industry stock investment strategies.

If the index series in the stock market exhibits long-memory characteristics, the policy implication is that fractal markets, even in the nonlinear case, allow for a corresponding distribution pattern in the value of portfolio assets. The risk of stock price volatility in various sectors has expanded due to the effects of the COVID-19 pandemic and the R-U conflict on the stock market. Predicting future trends by forecasting stock prices is critical for minimizing financial risk. The ability to mitigate the epidemic’s impact and stop losses promptly is relevant to market regulators, companies and other relevant stakeholders.

Although long memory exists, the stock price index series can be predicted. However, price fluctuations are unstable and chaotic, and traditional mathematical and statistical methods cannot provide precise predictions. The network framework proposed in this paper has robust horizontal connections between units, strong memory capability and stronger generalization ability than traditional network structures. The authors demonstrate significant performance improvements of SSA-BiGRU-GSCV over comparison models on Chinese stocks.