Search results

Deep learning (DL) is a new and relatively unexplored field that finds immense applications in many industries, especially ones that must make detailed observations, inferences and predictions based on extensive and scattered datasets. The purpose of this paper is to answer the following questions: (1) To what extent has DL penetrated the research being done in finance? (2) What areas of financial research have applications of DL, and what quality of work has been done in the niches? (3) What areas still need to be explored and have scope for future research?

This paper employs bibliometric analysis, a potent yet simple methodology with numerous applications in literature reviews. This paper focuses on citation analysis, author impacts, relevant and vital journals, co-citation analysis, bibliometric coupling and co-occurrence analysis. The authors collected 693 articles published in 2000–2022 from journals indexed in the Scopus database. Multiple software (VOSviewer, RStudio (biblioshiny) and Excel) were employed to analyze the data.

The findings reveal significant and renowned authors' impact in the field. The analysis indicated that the application of DL in finance has been on an upward track since 2017. The authors find four broad research areas (neural networks and stock market simulations; portfolio optimization and risk management; time series analysis and forecasting; high-frequency trading) with different degrees of intertwining and emerging research topics with the application of DL in finance. This article contributes to the literature by providing a systematic overview of the DL developments, trajectories, objectives and potential future research topics in finance.

The findings of this paper act as a guide for literature review for anyone interested in doing research in the intersection of finance and DL. The article also explores multiple areas of research that have yet to be studied to a great extent and have abundant scope.

Very few studies have explored the applications of machine learning (ML), namely, DL in finance, which is a much more specialized subset of ML. The authors look at the problem from the aspect of different techniques in DL that have been used in finance. This is the first qualitative (content analysis) and quantitative (bibliometric analysis) assessment of current research on DL in finance.

Confidence intervals play a crucial role in economics and finance, providing a credible range of values for an unknown parameter along with a corresponding level of certainty. Their applications encompass economic forecasting, market research, financial forecasting, econometric analysis, policy analysis, financial reporting, investment decision-making, credit risk assessment and consumer confidence surveys. Signal-to-noise ratio (SNR) finds applications in economics and finance across various domains such as economic forecasting, financial modeling, market analysis and risk assessment. A high SNR indicates a robust and dependable signal, simplifying the process of making well-informed decisions. On the other hand, a low SNR indicates a weak signal that could be obscured by noise, so decision-making procedures need to take this into serious consideration. This research focuses on the development of confidence intervals for functions derived from the SNR and explores their application in the fields of economics and finance.

The construction of the confidence intervals involved the application of various methodologies. For the SNR, confidence intervals were formed using the generalized confidence interval (GCI), large sample and Bayesian approaches. The difference between SNRs was estimated through the GCI, large sample, method of variance estimates recovery (MOVER), parametric bootstrap and Bayesian approaches. Additionally, confidence intervals for the common SNR were constructed using the GCI, adjusted MOVER, computational and Bayesian approaches. The performance of these confidence intervals was assessed using coverage probability and average length, evaluated through Monte Carlo simulation.

The GCI approach demonstrated superior performance over other approaches in terms of both coverage probability and average length for the SNR and the difference between SNRs. Hence, employing the GCI approach is advised for constructing confidence intervals for these parameters. As for the common SNR, the Bayesian approach exhibited the shortest average length. Consequently, the Bayesian approach is recommended for constructing confidence intervals for the common SNR.

This research presents confidence intervals for functions of the SNR to assess SNR estimation in the fields of economics and finance.

The increased capital requirements and the implementation of new liquidity standards under Basel III sparked various concerns among researchers, academics and other stakeholders. The question is whether Basel III regulation is ideal, that is, adequate to deal with a crisis, such as the 2007–2009 global financial crisis? The purpose of this paper is threefold: First, perform a stress testing exercise on the US banking sector, while examining liquidity and solvency risk indicators jointly under the Basel III regulatory framework. Second, allow the study to cover the post-crisis period, while referring to key Basel III regulatory requirements. And third, focus on the resilience of domestic systemically important banks (D-SIBs), which are supposed to support the US financial system in times of stress and therefore whose failure causes the entire financial system to fail.

The authors used a sample of the 24 largest US banks observed over the period Q1-2015 to Q1-2021 and a scenario-based vector autoregressive conditional forecasting approach.

The authors found that the model successfully produces accurate forecasts and simulates the responses of the solvency and liquidity indicators to different real and historical macroeconomic shocks. The authors also found that the US banking sector is resilient and can withstand both historical and hypothetical macroeconomic shocks because of its compliance with the Basel III capital and liquidity regulations, which consist of encouraging banks to hold high-quality liquid assets and stable funding resources and to strengthen their capital, which absorbs the losses incurred in a crisis.

The authors developed a framework for testing the resilience of the US banking sector under macroeconomic shocks, while examining liquidity and solvency risk indicators jointly under Basel III regulatory framework, a point not yet well studied elsewhere, and most studies on this subject are based on precrisis data. The authors also focused on the resilience of D-SIBs, whose failure causes the failure of the entire financial system, which previous studies have failed to examine.

The digital warehouse management system is an emergence that forms a critical part of the transformation of economic structure in Industry 4.0. In the present business scenario, the warehouse management system encounters a messy layout, poor damage control, unsatisfactory order management, lack of visibility and lack of technological interventions. Digital twin (DT) based warehouse system shows the ontology and knowledge graphs for competitive advantage by consolidating and transferring goods directly from an inbound supplier to an outbound customer on short notice and with no or limited storage. There remains a lack of clarity on how the DT can be implemented successfully in warehouse management.

The current literature remains largely unstructured and scattered due to a lack of a systematic approach to integrating the research implications and analysis. This paper probes the conceptualization of the DT with the help of theoretical analysis using the systematic literature analysis method.

The study explores essential concepts such as interoperability and integrability in implementing DT. Further, it analyzes the role of a supply chain control tower (SCCT) in modern supply chain management. A research framework is proposed for practitioners and academicians by incorporating the opportunities and challenges associated with DT implementation. The research findings are mainly threefold: Conceptualization of DT, Featuring SCCT and Exploration of cross-computer platform interfaces, scalability and maintenance strategies.

This study is among the first to analyze and review DT applications in warehouse management. Moreover, the study proposes a theoretical toolbox for the practitioners to successfully implement the DT in warehouse DT-based warehouse management system: A theoretical toolbox for future research and applications.

The production planning problem with fine-grained information has hardly been considered in practice. The purpose of this study is to investigate the data-driven production planning problem when a manufacturer can observe historical demand data with high-dimensional mixed-frequency features, which provides fine-grained information.

In this study, a two-step data-driven optimization model is proposed to examine production planning with the exploitation of mixed-frequency demand data is proposed. First, an Unrestricted MIxed DAta Sampling approach is proposed, which imposes Group LASSO Penalty (GP-U-MIDAS). The use of high frequency of massive demand information is analytically justified to significantly improve the predictive ability without sacrificing goodness-of-fit. Then, integrated with the GP-U-MIDAS approach, the authors develop a multiperiod production planning model with a rolling cycle. The performance is evaluated by forecasting outcomes, production planning decisions, service levels and total cost.

Numerical results show that the key variables influencing market demand can be completely recognized through the GP-U-MIDAS approach; in particular, the selected accuracy of crucial features exceeds 92%. Furthermore, the proposed approach performs well regarding both in-sample fitting and out-of-sample forecasting throughout most of the horizons. Taking the total cost and service level obtained under the actual demand as the benchmark, the mean values of both the service level and total cost differences are reduced. The mean deviations of the service level and total cost are reduced to less than 2.4%. This indicates that when faced with fluctuating demand, the manufacturer can adopt the proposed model to effectively manage total costs and experience an enhanced service level.

Compared with previous studies, the authors develop a two-step data-driven optimization model by directly incorporating a potentially large number of features; the model can help manufacturers effectively identify the key features of market demand, improve the accuracy of demand estimations and make informed production decisions. Moreover, demand forecasting and optimal production decisions behave robustly with shifting demand and different cost structures, which can provide manufacturers an excellent method for solving production planning problems under demand uncertainty.

In today's fast developing era, the volume of data is increasing day by day. The traditional methods are lagging for efficiently managing the huge amount of data. The adoption of machine learning techniques helps in efficient management of data and draws relevant patterns from that data. The main aim of this research paper is to provide brief information about the proposed adoption of machine learning techniques in different sectors of manufacturing supply chain.

This research paper has done rigorous systematic literature review of adoption of machine learning techniques in manufacturing supply chain from year 2015 to 2023. Out of 511 papers, 74 papers are shortlisted for detailed analysis.

The papers are subcategorised into 8 sections which helps in scrutinizing the work done in manufacturing supply chain. This paper helps in finding out the contribution of application of machine learning techniques in manufacturing field mostly in automotive sector.

The research is limited to papers published from year 2015 to year 2023. The limitation of the current research that book chapters, unpublished work, white papers and conference papers are not considered for study. Only English language articles and review papers are studied in brief. This study helps in adoption of machine learning techniques in manufacturing supply chain.

This study is one of the few studies which investigate machine learning techniques in manufacturing sector and supply chain through systematic literature survey.

1. A comprehensive understanding of Machine Learning techniques is presented.

2. The state of art of adoption of Machine Learning techniques are investigated.

3. The methodology of (SLR) is proposed.

4. An innovative study of Machine Learning techniques in manufacturing supply chain.

A comprehensive understanding of Machine Learning techniques is presented.

The state of art of adoption of Machine Learning techniques are investigated.

The methodology of (SLR) is proposed.

An innovative study of Machine Learning techniques in manufacturing supply chain.

Commercial banks face several risks, including credit, liquidity, operational and disruptive risks. In addition to these risks that are challenging for banks to control and manage, crises and disasters can exert substantially more destructive shocks. These shocks can exacerbate internal risks and cause severe damage to the bank's performance, leading banks to bankruptcy and closure. This study aims to facilitate achieving resilient banking policies through a model-based assessment of business continuity management (BCM) policies.

By applying a system dynamics (SD) methodology, a systemic model that includes a causal structure of the banking business is presented. To build a simulation model, data are collected from a commercial bank in Iran. By presenting the simulation model of the bank's business, the consequences of some given crises on the bank's performance are tested, and the effectiveness of risk and crisis management policies is evaluated. Vensim Personal Learning Edition (PLE) software is used to construct the simulation model.

Results indicate that the current BCM policies do not show appropriate resilience in the face of various crises. Commercial banks cannot create sustainable value for the banks' shareholders despite the possibility of profitability, as the shareholders lack adequate resilience and soundness. These commercial banks do not have the appropriate resilience for the next pandemic after coronavirus disease 2019 (COVID-19). Moreover, the robustness of the current banking business model is very fragile for the banking run crisis.

A forward-looking view of resilient banking can be obtained by combining liquidity coverage, stable funding, capital adequacy and insights from stress tests. Resilient banking requires a balanced combination of robustness, soundness and profitability.

The present study is a combination of bank business management, risk and resilience management and SD simulation. This approach can analyze and simulate the dynamics of bank resilience. Additionally, present of a decision support system (DSS) to analyze and simulate the outcomes of different crisis management policies and solutions is an innovative approach to developing effective and resilient banking policies.

This study aims to map the digital risks for the Islamic finance industry. Since 2010, the financial space has largely shifted from being banking-centric to the entrepreneurship spectrum, benefiting from groundbreaking innovations in computer technology. The problem of Islamic Finance is that it is still within its banking-centric moment that is risk averse leading to financial exclusion. As with all innovations, there are associated risks that require careful consideration to ensure the reaping of the benefits of these technologies while controlling the risks at its lowest. In this context, the aim of this study is to highlight the risks associated with financial technologies (FinTech) to prepare the Islamic finance sector to serve the economic ideals of Maqāṣid al-Shariah in financial inclusion and profit and loss sharing. The main research question is as follows: What do Islamic Finance industry need to do to manage the digital risks for financial inclusion?

This study uses narrative review method in analysing the discourse of financial technology literature using qualitative data collected from the literature on the topic. It aimed to problematise associated digital risks from the Shariah compliance and Maqā¸ṣid al-Shariah critical viewpoints. Considering the nature of this conceptual study, it adopts a qualitative methodology by using discourse and thematic analysis of the literature that can lay the foundation for future empirical testing on the topic.

The study found that managing risks faced by the Islamic financial sector while adapting to the digital era can be divided into two main clusters: risk mitigation for Shariah-compliant FinTech and risk avoidance for Shariah non-compliant innovations. The high level of gharar associated with current practices in both cryptocurrencies and smart contracts needs additional regulation and simulation before they can be reconsidered for market-wide application. Cloud computing, crowdfunding and big data have promising applications that can address the limitations of the Islamic finance industry, particularly in terms of reducing transactional costs.

This conceptual article offers some insights into the subject; nevertheless, it does not attempt to establish causation or generalise the results. Additional statistical testing is required prior to generalising the results.

Due to the difficulties experienced since its inception, the Islamic financial industry is in urgent need of the cutting-edge solutions required to gain a competitive edge in the market and get over the limits that came with its late entry into the financial sector. Mapping digital risks is imperative for the development of comprehensive prudential risk management strategies for the Islamic finance industry that can fix its problems and enable it to deliver the more favourable Shariah-based solutions, rather than remaining in the lower bands of Shariah compliance.

Findings of the study lay the foundation for empirical testing the volatility of FinTech innovations for the Islamic finance industry to reduce uncertainties and generate reliable forecasts. Scholarship on managing digital risks for Islamic financial institutions is still developing due to the covid global lockdown and the looming recession, and this study will help enhance theorisation necessary that can aspire economic recovery after current challenges.

The problem statement is how to identify and analyze the corporate risks involved in the relationships with external agents involved in the open product innovation process (OPIP)? Seeking to extend this investigation, the purpose of this paper is to analyze the enterprise risks identified in corporate relations with external agents of the OPIP. This study proposes the systematization of the process of identification and analysis of the enterprise risks involved in the process of open product innovation.

The case explored in this study is the OPIP of Volkswagen do Brasil (VWB), one of the most important subsidiaries of the Volkswagen Group. Criteria were selected to both assessing corporate relations with external agents of the open innovation of VWB and analyzing the enterprise risks identified in these relations. Data collection included interviews with management-level professionals engaged in the OPIP activities and technical visits to a VWB’s industrial plant.

Results demonstrate that the enterprise risks mostly affecting the OPIP have a critical impact on the manufacturing process and initial sales of the new product.

The originality of the study focuses on the proposal of a systematization of how to identify and analyze the corporate risks involved in the process of open product innovation. The study focuses on the theoretical frontier on the open innovation and enterprise risk management (ERM) in the open innovation process.

The purpose of the study is to investigate the impact of implementing anti-dumping duties on imported Australian wine to China in the short- and long-run, respectively.

First, the Difference-in-Differences (DID) method is used in this study to evaluate the short-run causal effect of implementing anti-dumping duties on imported Australian wine to China. Second, a Bayesian ensemble method is used to predict 2023–2025 wine exports from Australia to China. The disparity between the forecasts and counterfactual prediction which assumes no anti-dumping duties represents the accumulated impact of the anti-dumping duties in the long run.

The anti-dumping duties resulted in a significant decline in red and rose, white and sparkling wine exports to China by 92.59%, 99.06% and 90.06%, respectively, in 2021. In the long run, wine exports to China are projected to continue this downward trend, with an average annual growth rate of −21.92%, −38.90% and −9.54% for the three types of wine, respectively. In contrast, the counterfactual prediction indicates an increase of 3.20%, 20.37% and 4.55% for the respective categories. Consequently, the policy intervention is expected to result in a decrease of 96.11%, 93.15% and 84.11% in red and rose, white and sparkling wine exports to China from 2021 to 2025.

The originality of this study lies in the creation of an economic paradigm for assessing policy impacts within the realm of wine economics. Methodologically, it also represents the pioneering application of the DID and Bayesian ensemble forecasting methods within the field of wine economics.