Forthcoming and Online First Articles
International Journal of Applied Decision Sciences
Forthcoming articles have been peer-reviewed and accepted for publication but are pending final changes, are not yet published and may not appear here in their final order of publication until they are assigned to issues. Therefore, the content conforms to our standards but the presentation (e.g. typesetting and proof-reading) is not necessarily up to the Inderscience standard. Additionally, titles, authors, abstracts and keywords may change before publication. Articles will not be published until the final proofs are validated by their authors.
Forthcoming articles must be purchased for the purposes of research, teaching and private study only. These articles can be cited using the expression "in press". For example: Smith, J. (in press). Article Title. Journal Title.
Articles marked with this shopping trolley icon are available for purchase - click on the icon to send an email request to purchase.
Online First articles are published online here, before they appear in a journal issue. Online First articles are fully citeable, complete with a DOI. They can be cited, read, and downloaded. Online First articles are published as Open Access (OA) articles to make the latest research available as early as possible.
Register for our alerting service, which notifies you by email when new issues are published online.We also offer which provide timely updates of tables of contents, newly published articles and calls for papers.
International Journal of Applied Decision Sciences (41 papers in press)
Abstract: This study proposed a signalling game for a research grant allocation situation involving two players: a funding agency and a researcher whose type was kept secret from the funding agency, where the agency decided the grant amount to fund the researcher. The results showed that a pooling equilibrium existed when the difference between a large and small fund was sufficiently large, and the expected costs of failing the large-fund project for both types were small, whereas the expected costs of failing the small-fund project for both types were large. A case study was examined based on the research impact assessment of other studies. According to the results, we were still in a pooling equilibrium. However, if some model parameters changed (such as when the estimated cost of a penalty to a bad researcher was increased), a separating equilibrium began to show.
Keywords: game theory; signalling game; research funds allocation; decision analysis; Thailand.
An integrated fuzzy multi-criteria decision-making approach for prioritizing strategies to drive the sustainable Roll-on/ Roll-off port development: A case study of Thailand
by Detcharat Sumrit, Ratima Jaidee
Abstract: This study proposes a framework for prioritizing strategies to drive sustainable Roll-on/Roll-off (RO/RO) port development by combining fuzzy multi-criteria decision-making approach The application of the proposed framework uses one of the largest RO/RO ports in Thailand as a case study First, the measuring perspectives/criteria and driving strategies for sustainable port are identified through the extensive literature review along with port development plan The fuzzy Delphi method is applied to select the suitable criteria and driving strategies for sustainable development of RO/RO port Next, the Fuzzy Decision-Making Trail and Evaluation Laboratory (Fuzzy DEMATEL) is employed to analyze the interrelationship between perspective and criteria as well as their importance weights Finally, Fuzzy Technique for Order Preference by Similarity to Ideal Solution (Fuzzy TOPSIS) is utilized to prioritize the driving strategies.
Keywords: Multi-criteria decision-making (MCDM); Fuzzy Delphi; Fuzzy DEMATEL); Fuzzy TOPSIS; Roll-on/Roll-off; Sustainability.
A TWO PHASE APPROACH BASED ON MULTI OBJECTIVE PROGRAMMING AND SIMULATION FOR PHYSICIAN SCHEDULING IN EMERGENCY ROOMS
by Ozgur Yanmaz, Ozgur Kabak
Abstract: Scheduling hospital staff is a complex problem because of the wide fluctuations in demand and staffing needs. Physician scheduling in an emergency room (ER) is the one that is most complex and crucial since it requires not only economic and patient perspectives but also the social needs of physicians. Thus, the working conditions and preferences of physicians should be considered in planning their schedules. This study aims to develop an approach for scheduling physicians in an ER to provide better conditions for physicians and, a qualified and reachable healthcare service to the patients. A multi-objective mathematical model is developed to ensure Pareto optimal solutions considering not only economic aspects but also social aspects including the physician preferences and balancing the workload. A Monte Carlo simulation is used to determine the best schedule among Pareto optimal solutions obtained from the mathematical model and deal with the fluctuations in demand. The approach is applied with real world data.
Keywords: physician scheduling; emergency rooms; multiple objective programming; Monte Carlo simulation; the augmented ?-constraint.
Comparative Analysis of Novel Fuzzy Multi-Criteria Decision Making Methods for Selecting Forth-Party Logistics Service Providers: A Case Study in Plastic Resin Industry.
by Detcharat Sumrit, Kamolchanok Jiamanukulkij
Abstract: This paper proposes a systematic framework to select the best 4PLs by incorporating several MCDM methods. The aim of this paper is to conduct a comparative study to examine how different MCDM methods compare when apply for 4PLs selecting problem. First, 14 criteria of 4PLs selection are identified through literature and input from industrial experts. Second, the objective weights of criteria are derived through interval Shannons entropy based on α-level sets. Afterward, the 4PL candidates are ranked comparatively using five novel MCDM methods reported in literature including CoCoSo, MARCOS, EDAS, MAIRCA, and CODAS. Finally, the sensitivity analysis is performed to test the robustness and reliability of the proposed framework. A case of plastic resin industry in Thailand is used to demonstrate the application of the proposed framework. The practitioners and academicians can utilise the proposed framework to select the best 4PLs.
Keywords: multi-criterion decision making; fuzzy set theory; FST; forth-party logistics providers.
Verification of neural network models for forecasting the volatility of the WIG20 index rates of return during COVID-19 pandemic
by Emilia Fraszka-Sobczyk, Aleksandra Zakrzewska
Abstract: The paper investigates the issue of the volatility of stock index returns on the Warsaw Stock Exchange (the WIG20 index returns volatility). The purposes of this review are to present an alternative neural network and to examine it to predict the stock index returns according to the historical data. Finally, these predictions got from the new neural network are compared with predictions based on a standard neural network MLP. In this article, as the measurements for the best forecasting performance of neural networks are taken common used forecast error measurements: mean error (ME), mean percentage error (MPE), mean absolute error (MAE), mean absolute percentage error (MAPE), root mean square error (RMSE), R (the correlation coefficient). The results show that the introduced neural network has good accuracy in measuring effectively the WIG20 index returns volatility.
Keywords: stock index returns; volatility forecasting; stock index prediction; neural network; machine learning.
Human Rights Disclosure and Sustainable Banking: Evidence from Europe and Implications for Policy
by Loris Di Nallo, Alberto Manzari, Raffaele Trequattrini
Abstract: This paper investigates the nature and quality of human rights reporting and disclosure in sustainable banking and its practices in providing information to stakeholders and assuring sustainability and sustainable development. Thus, this paper aims at analysing what are human rights information reported and disclosed by the banking industry to assure transparency and sustainable practices, drafting corporate transparency, sustainability and responsibility. We used the quantitative methodology based on the statistical analysis to represent the role of human rights disclosure in the sustainable banking. Using frameworks by corporate disclosure theories, we built our sample of all banks included in the EUROStoxx 600. We developed the regression analysis establishing the relationship between sustainability disclosure and human rights. Our results show achievements in the sustainability reporting and disclosure in representing human rights information by sustainable banking and practices. The positioning of human rights information is directed to increase corporate transparency, corporate responsibility and responsible investments decisions as well as sustainability and sustainable development.
Keywords: sustainability; human rights disclosure; sustainable banking; responsible investment decisions; sustainable strategy; sustainable finance; sustainable development; metrics.
Applying customer intelligence in marketing: a holistic approach
by Nguyen Anh Khoa Dam, Thang Le Dinh, William Menvielle
Abstract: Enterprises have started to adopt and apply customer intelligence, which is acquired through the support of business analytics to capitalise on big data, to optimise marketing decisions. However, little research focuses on holistically applying customer intelligence from defining and acquiring the right type of customer intelligence to applying and evaluating it for optimal outcomes. This paper presents a comprehensive approach to value creation from customer intelligence in marketing. Adapted from Blooms taxonomy, the proposed approach significantly contributes to identifying the six levels of applying customer intelligence in marketing, including defining relevant types of customer intelligence, building appropriate strategies, identifying customer data, understanding customer analytics, setting key performance indicators for the evaluation purpose, and creating value through business questions and the interactive dashboard.
Keywords: customer intelligence; marketing decisions; holistic approach; big data; interactive dashboard.
A Robust and Resourceful Automobile Insurance Fraud Detection with Multi-Stacked LSTM Network and Adaptive Synthetic Oversampling
by Isaac Kofi Nti, Kwabena Adu, Peter Nimbe, OWUSU NYARKO-BOATENG, Adebayo Felix Adekoya, Peter Appiahene
Abstract: Insurance companies worldwide are concerned about financial losses due to false claims. Automobile insurance fraud (AIF) has become more sophisticated, causing the yearly loss of trillions of dollars. AIF is tough to establish, and acquiring a thorough knowledge of the problem is complex. Also, AIF investigators have relied on manual claims inspection, proving costly, inefficient, and time-consuming. This paper proposed a robust and resourceful approach to AIF detection with multi-stacked LSTM (MSLSTM) reinforced with the adaptive synthetic (ADASYN) sampling algorithm for imbalanced learning. We experiment with the proposed model with a publicly available AIF dataset from Kaggle. Using accuracy, recall, precision, F1-score, and AUC, we compared the performance of our proposed MSLSTM model with well-known machine learning algorithms and previous AIF detection works. Our results showed a fair performance (accuracy = 95%, precision = 94%, AUC = 97% and F1-score = 92%) of the MSLSTM model than other algorithms and works.
Keywords: automobile insurance fraud; AIF; car fraud detection; stacked LSTM network; adaptive synthetic oversampling.
An exact solution method for seru scheduling problems considering past-sequence-dependent setup time and adjustment activities
by Ru Zhang, Zhe Zhang, Xiaoling Song, Yong Yin
Abstract: This paper concerns production scheduling problems with past-sequence-dependent (p-s-d) setup time and adjustment activities considerations in seru production system (SPS), in which the setup time is proportionate to the sum of processing times of jobs scheduled already, and the adjustment activities are also considered due to the deteriorating positional processing time. Some common scheduling criteria are concerned for five seru scheduling problems, and an exact assignment matrix approach is formulated to prove that these seru scheduling problems can be transformed into assignment problems. The polynomial computation time is also confirmed. Computational experiments are made finally, and it is shown that the proposed approach is effective for resolving seru scheduling problems through reformulation.
Keywords: seru scheduling; setup time; adjustment activities; exact assignment matrix.
Measuring Source, Affiliation, and Permission Likelihood of Consumer Confusion in Trademark Infringement Litigation
by Robert Peterson, Isabella Cunningham, Jeffrey A. Peterson
Abstract: This boundary-spanning article addresses the measurement of 'likelihood of confusion' in trademark infringement litigation. Likelihood of confusion is the sine qua non of trademark infringement litigation and is typically measured by means of consumer surveys. After brief discussions of consumer confusion and the Lanham Act, the three traditional types of likelihood of confusion recognised under the Lanham Act source confusion, affiliation confusion, and permission confusion are described, and two prominent survey approaches for measuring likelihood of confusion, 'Ever-ready' and 'Squirt, ' reviewed. Through a quantitative evaluation of existing likelihood of confusion surveys and an empirical experiment, various measurement issues are examined, and their implications considered. We document how existing measurement procedures can influence likelihood of confusion survey results, and especially how the attention accorded source confusion may inherently or unintentionally produce estimates of likelihood of confusion that understate overall confusion due to affiliation and/or permission likelihood of confusion. Suggestions for future research are discussed and an approach for measuring likelihood of confusion in trademark infringement litigation offered.
Keywords: Lanham Act; trademark infringement; likelihood of confusion.
Extended Fuzzy AHP for Decision under the DeLone McLean Model
by Frantisek Zapletal, Radek Nemec
Abstract: Fuzzy analytic hierarchy process (F-AHP) has been introduced in many variations requiring different conditions and assumptions. In this paper, we deal with a problem when the uncertainty is not primarily implied by a linguistic evaluation scale, but by the hesitance of decision-makers. This assumption is essential in our case study of the project success factor evaluation under the DeLone and McLean model because the evaluators have different skills, knowledge, and even competences. To get the level of hesitance of each decision-maker, we introduce the so-called hesitance degree, which defines the shape of fuzzy evaluations. To derive the fuzzy weights of criteria, we use the linear goal programming priority method introduced by Wang and Chin (2008), and the possibility and necessity measures to interpret the results. We also provide a novel diagram visualising the results. The presented F-AHP approach is used to evaluate the success factors of information system implementation.
Keywords: hesitance; fuzzy; analytic hierarchy process; AHP; DeLone and McLean model.
An Optimization model to design a maritime search and rescue system under uncertainty
by Donya Rahmani, Babak Ebrahimi, Hadi Kian
Abstract: Unfavourable weather conditions, disruptions in equipment, and human error are the factors that lead to maritime accidents. In such cases, delays in providing relief may lead to catastrophic events. Hence, this paper presents a bi-objective mixed-integer linear programming (MILP) model for marine search and rescue under uncertainty. The purpose of the proposed model is to minimise total costs and the completion time of operations, simultaneously. Helicopters and ships equipped with rescue and relief equipment are applied for maximum coverage. We use a stochastic scenario-based approach to cope the uncertain response time. A fuzzy solution approach is developed to deal with the uncertainty and solve the proposed bi-objective model. Finally, an algorithm is presented to generate data using probabilistic distribution functions, and the performance of the proposed model is evaluated by eight simulated problems. The results obtained for the simulated problems and the sensitivity analysis of the coefficients of the objective functions show the effectiveness of the proposed model.
Keywords: maritime search and rescue; mathematical programming; location problem; fuzzy theory; stochastic programming.
Enhance personalized recommendations by exploring online social relations
by Xiaoyun He, Chuleeporn Changchit
Abstract: Personalized digital recommendations are widely used to improve customer experience and drive sales. Although recent research suggests that online social relations influence users' both product choices and ratings, few studies have examined them in the context of personalized recommendations. In this study, we aim to explore how online social relations can be leveraged to enhance personalized recommendations. The empirical results demonstrate that incorporating the ratings from a users social circle improves accuracy and coverage of personalized recommendations; In addition, differentiating these social ratings helps increase the recommendation diversity while limiting the loss of accuracy. The findings have important implications for the applicability of recommender systems in modern online business and social environment.
Keywords: Social relations; recommendation accuracy; the diversity; online recommendation; personalized recommendation; online relations.
Vulnerability to Poverty Due to Schooling: A discussion from the spatial perspective
by Rafael Freitas Souza, Julio Carneiro-da-Cunha, Luiz Corrêa, Cláudia Orsini Machado De Sousa
Abstract: Economic theories point out that regional poverty is more concentrated in regions far from urban centres. However, at Brazilian Midwest, wealth-generating localities are not concentrated in those centres and may create misunderstandings about the theoretical understanding of this phenomenon, and for policymakers who need predictive tools to address the fight against poverty. Thus, it was intended to predict poverty vulnerability from educational levels in a distinct phenomenon of decentralization. A geographically weighted regression was performed using UNDP data on Midwest municipalities. It was pointed out that education levels can predict vulnerability to poverty, confirming the theories existing in the main agricultural area in the world. As a contribution, public policies need to be thought individual and spatially, to consider actions beyond the institutional boundaries of municipalities, in an integrated and coordinated manner between neighbouring cities.
Keywords: Poverty; Education; Public Policies; Brazilian Midwest; Poverty Vulnerability.
SENTIMENT ANALYSIS AND SUPPORT VECTOR MACHINE ONE VERSUS ONE FOR COLLECTIBILITY CLASSIFICATION OF BANKS HOUSE OWNERSHIP LOAN
by Carmelia Nabila Permatasari, Adji Achmad Rinaldo Fernandes
Abstract: Not many applications of sentiment analysis have been developed for the Indonesian language. One classification methods that can be applied to extracting information for large databases is the support vector machine (SVM). This study aims to compile research variables based on the results of sentiment analysis and examine SVM performance to solve multi-class cases using the one versus one method with linear kernel functions, quadratic polynomial kernel functions, and radial basis function (RBF) kernel functions in classifying the collectibility classification of banks house ownership loan based on Pernyataan Standar Akuntansi Keuangan (PSAK) 71, among others: 1) performing loan; 2) under-performing loan; 3) non-performing loan. The results showed that SVM one versus one with the kernel RBF is the most appropriate method in classifying collectibility levels bank mortgage debtors based on the Big Five personality because the accuracy, sensitivity, and specificity values obtained on the perfect testing data are 100%.
Keywords: performance; debtor collectibility; bank; house ownership loan; one versus one; support vector machine; SVM.
Facility Delocation Model Considering Efficiency and Equity: Banks Merger
by Saeed Zarghami, Maghsoud Amiri, Mohammad Taghi Taghavifard, Ahmad Makui
Abstract: Facility delocation emerges due to governance conditions, strategies, technological changes and the new demands in the competition market. Bank merger is no exception in such a condition. In this study, a delocation merging model is presented for the so-called military banks of Iran. The government has taken into account the issues of efficiency and equity, considering the claims of the stakeholders and based on its own goals. Therefore, a multi-objective model is considered and equality is considered with the help of constraints. Meaning that, when subjected to constraints, equality is introduced into the model using fuzzy logic and also the efficiency score of banks is considered as the importance of facilities using data envelopment analysis method. The constraints of the model determine the number of remaining facilities and numerical examples are analysed, using the epsilon-constraint method augmented in the GAMS software.
Keywords: bank; data envelopment analysis; delocation; epsilon-constraint; Fuzzy logic; efficiency and equity; multi-objective model.
Toward a CNN-based Approach for Usability Re-quirements Generation
by Dorra Zaibi, Riadh Ksantini, Meriem Riahi, Faouzi Moussa
Abstract: The explosion of data science in many sectors of technology combined with the enormous rise of deep learning techniques in the last decade has resulted in new automation applications. The most prevalent deep learning architecture is the convolutional neural network (CNN) which has been widely applied for face recognition and various applications, has recently emerged as an effective and potentially useful tool for feature extraction. Unfortunately, human factors engineering (HFE), also known as usability engineering, which is concerned with interactive systems, often has limited attention and awareness of deep learning applications and is therefore unable to provide the important breakthroughs that are required to ensure the success of these emerging interactive systems. This article addresses the issue by exploring the generation of consistent usability requirements based on deep CNN models to enable accurate classification in context-aware environments. Our methodology has been tested and performance analysis is carried out through a case study.
Keywords: human-computer interaction; HCI; usability; context-aware environment; deep learning; convolutional neural network; CNN.
A comparative investigation to determine whether or not to maintain strategic inventory for a two-period green supply chain model using the game theory approach
by Animesh Mondal, Ranjan Jana, Dipak Jana
Abstract: In this research paper, we have developed a green supply chain (GSC), a novel model with a retailer and a manufacturer where the manufacturer produces green products and sells them to the customers by offering quantity discounts via the retailer. Based on four-game structures, viz., manufacturer Stackelberg (MS), retailer Stackelberg (RS), Nash and cost-sharing (CS), we have explored the comparative analysis to determine whether to maintain strategic inventory or not to maintain strategic inventory for a given two-period GSC. The analysis outcome may be beneficial to decide which power strategy supply chain players will adopt and maintain strategic inventory for better profit. A total of eight analytical models have been derived and explored. The novel demand function depends on the retail price, green level and quantity discount. At last, numerical examples and sensitivity analysis are provided to understand the better model comparison. The optimal results are computed in terms of closed-form solutions and displayed graphically. This study indicates that the preference is highly responsive to the game structure.
Keywords: green supply chain; GSC; game theory; quantity discount; strategic inventory; cost sharing.
Risk Management and Project Performance: An Examination of Construction Industry during COVID-19 Pandemic and Future Prospects
by Xuhui Han
Abstract: The scope of risk management concerning to firms performance has widely experimented over the past decades by researchers. Nevertheless, how risk management practices (RMP) may optimise project performance such as construction projects during disastrous times like COVID-19 got far less consideration from developing nations. This study investigates the relationships of risk management practices within three streams, i.e., operational risk (OR), financial risk (FR), and political risk on project performance within the Chinese construction industry through an empirical approach. Using structural equation modelling along with confirmatory factor analysis, the study affirmed a positive connection between risk management and project performance based on 328 sample size (n = 328) obtained from project managers. In addition, the study found a positive nexus between each dimension of risk management and project performance, i.e., OR, FR and PR. This study endows with considerable applications for project managers along with strategies for future challenges. Besides, future research possibilities are recommended to scholars of the world with consideration of the current limitations.
Keywords: risk management; operational risk; financial risk; political risk; project performance; COVID-19; construction industry.
Exploring International Market Selection for Indonesian Tuna
by Elia Oey, Hanijanto Soewandi
Abstract: International market selection is a classical strategic application for multi-criteria decision-making (MCDM) analysis. The study aims to assist Indonesia tuna stakeholders in determining potential export country destinations. Data of 210 countries were screened to get 30 shortlisted countries for a systematic MCDM analysis. Global weight of sub criteria was calculated with analytical hierarchy process by interviewing experts related to Indonesia tuna export. Ranking of shortlisted countries was done using several iterations with ELECTRE I, where results of each round are plotted into a 2 × 2 quadrant, and those in the worst quadrant were eliminated. After six elimination rounds, we propose Japan, Singapore, China, Malaysia, Denmark, and South Korea, as the top six export-country destinations for Indonesian tuna. Using scatter plot visualisation of net superiority vs. net inferiority index into a 2 × 2 quadrant helps enhance the ELECTRE I result in a more pragmatic way, and creates more insight for a sensitivity analysis.
Keywords: AHP; ELECTRE; international market selection; IMS; tuna.
Currency Crisis Early Warning Signal Mechanisms Based On Dynamic Machine Learning
by Omur Saltik, Wasim Ul Rehman, Bahadir Ildokuz, Suleyman Degirmen, Ahmet Sengonul
Abstract: The foremost objective of the study is to reveal that if credit default swap (CDS) is an early warning signals for currency crises by considering stock and flow variables such as external debt stock and reserves (foreign currency and gold) under free exchange rate regimes. As an original aspect of the study, which differs from other studies, is the machine learning methods used and the inclusion of both one lag and lag values of the cds variable, which is an inclusive crisis indicator, into the model. The CDS variable was not detected as a strong signal by the logistic regression model. However, the best-performing XGBoost and GB algorithms show the differenced, and one-lagged values of the CDS variable produce significant signals in forecasting currency crises. Consistent with theoretical underpinnings of study on currency crises, this implies that central banks proactively reacted by increasing monetary policy interest rates and the non-current value CDS but its lagged value performed strong early warning signal that is a follower or supplementary indicator of the credibility of monetary authorities and policies. These results demonstrate that the high and rising interest rate signifies that domestic currencies are being supported against speculative attacks.
Keywords: currency crisis; currency pressure index; credit default swap; CDS; panel logistic regression; machine learning classification.
Exploring intention to use cryptocurrencies payment across age groups and gender: a multi-stage machine learning application on the extended UTAUT model
by Dong L. Tong, P.C. Lai, Ewilly Jie Ying Liew
Abstract: Given the increasingly widespread use of smartphones for cashless payment, the potential for using cryptocurrencies as an alternative e-payment asset becomes attractive. Promoting blockchain-based cryptocurrencies for e-payment faces challenges in payment conversion latency, where hard-earned crypto coins are not a recognised asset for actual payment. This study investigates users intention to use cryptocurrencies in daily e-payment transactions. A multi-stage artificial intelligence-based analysis pipeline was employed to identify key factors of crypto-based e-payment usage and model the interaction between these factors. Experiments were conducted based on different target criteria, and factors corresponding to these target criteria were evaluated. Results show that platform reliability, improved usefulness, user-friendliness, and self-efficacy were directly associated with users intention to use crypto coins for e-payment services. Age and gender differences were also evaluated across factors affecting users intentions to use the new technology. Implications for management and cryptocurrency coin providers were discussed.
Keywords: blockchain; cryptocurrency coin; e-payment; artificial intelligence; genetic algorithm; artificial neural network; ANN; decision tree.
A comparative study of interval forecasting using GARCH models under symmetric and asymmetric distributional assumptions
by Zhe Zhang, CHOO W.E.I. CHONG, Jayanthi Arasan
Abstract: Interval forecasting provides decision-makers with a range of possible future values, along with associated probabilities, which allows for a more informed decision-making process. Although GARCH models under different distributional assumptions are commonly compared for their volatility forecasting performance, their performance in interval forecasting is rarely discussed. This study aims to fill this gap by comparing the interval forecasting accuracy of GARCH models under symmetric and asymmetric distributions. SGARCH, EGARCH, and GJR-GARCH models under normal, student-t, GED distributions, and their skewed extensions are applied for one-day-ahead rolling interval forecasting on five major European and American stock indices: S&P 500, FTSE 100, CAC 40, DAX 30 and AEX. The average Winkler score (AWS) is used to measure the accuracy of interval forecasting. The conclusions of this study can be summarised as follows: In pairwise comparisons, the GARCH models under asymmetric distributional assumptions have better interval forecasting accuracy than the GARCH models under symmetric distributional assumptions. In comparisons among GARCH-type models, GJR-GARCH has better interval forecasting accuracy than SGARCH and EGARCH, while SGARCH and EGARCH exhibit similar interval forecasting performance.
Keywords: comparative study; interval forecasting; GARCH models; symmetric distributions; asymmetric distributions; distributional assumptions; conditional variance; average Winkler score; AWS.
Research on influencing factors of value co-creation in product service system development based on Z-DEMATEL-ISM model
by Yang Xu, Xiuli Geng
Abstract: Product service system (PSS) is an integrated set of products and services with value co-creation as the core. Therefore, a profound understanding of factors and interrelationships that influence value co-creation in PSS development is essential for manufactures. This paper proposes a systematic framework to analyse the influencing factors of value co-creation in PSS development. First, 22 factors are identified through the extensive literature and identification of a panel of experts. Second, decision-making trial and evaluation laboratory (DEMATEL) is adopted to identify the interactions between readiness factors, while Z number is introduced to capture the ambiguity and uncertain information in the decision-making process. Finally, a six-level hierarchical structure is determined based on interpretive structural model (ISM) to demonstrate the complex interrelationships among factors. The proposed framework is illustrated by taking the case of PSS value co-creation in Haier Group. The results indicate intelligent level being the most important factor of value co-creation in PSS development , followed by innovation potential and customer attraction. This finding could help manufacturers who aim for value increment to take appropriate steps to realise value co-creation of PSS.
Keywords: product service system; PSS; value co-creation; influencing factors; Z number; DEMATEL.
Applying Data Science to gauge Virtual Assistants impact on students' well-being during the pandemic
by Swapnil Morande
Abstract: The research offers insights into the impact of the pandemic on students and ruminates on mitigating the negative consequences by using a virtual assistant (VA). In an experimental setting, the study treats 'stress' as a critical factor that relates to students' well-being. The research is exploratory, where mixed-mode data is captured from students using a questionnaire and integrated virtual assistant simultaneously. The research findings establish the role of a virtual assistant to support preventive, predictive, and personalised health. It illuminates heart rate variability as one of the key indicators of perceived stress. As this research is based on the extensive literature on a method called 'photoplethysmography', it can further be scaled for supporting large groups of students. The outcome of the study can be further extended to industries where stress might be detrimental to well-being. The study contributes to the innovative application of data science to reflect on students' well-being.
Keywords: virtual assistant; COVID-19; machine learning; DeepNet modelling; well-being; data science.
Cognitive Technology in Human Capital Management: A Decision Analysis Model in Banking Sector during COVID-19 Scenario
by Senthil Kumar, Joji Abey, Seranmadevi R, Shefali Srivastava, Ashish Dwivedi
Abstract: Cognitive technologies are products of artificial intelligence (AI) domain which execute tasks that only humans used to perform. The impact of cognitive technologies on the management of human capital (HC) has a massive effect in the banking sector. This paper objectives to study the transformation of cognitive technology to human capital management (HCM) in the banking sector during the COVID-19 pandemic. The study draws data from 201 bank employees working in private, public, and foreign banks using a multi-stage sampling method in India. A number of hypotheses were framed and tested using multivariate and regression analyses. The results from the study indicate a significant change in the performances of bank employees statistically during the transformation of cognitive technologies. Cognitive technologies such as payment, product customisation, self-services, workload alleviation, automated back-office function, and a personalised experience significantly contribute to the HCM.
Keywords: artificial intelligence; AI; banking; cognitive technologies; COVID-19; human capital management; HCM; machine learning; ML.
Pricing strategies in a risk-averse dual-channel supply chain with manufacturer services
by Zhenhua Yang, Lin Huang, Yu Xia, Jian Guo Liu
Abstract: This paper studies a dual-channel supply chain consisting of one risk-averse manufacturer and one risk-averse retailer with stochastic demand. Herein, the manufacturer provides value-added services to enhance channel demand. First, the optimal pricing and service decisions of the channel members are investigated under different settings, i.e., the cooperative game, Bertrand game, and manufacturer Stackelberg (MS) game models. Second, the effects of channel members risk aversion on optimal channel prices and expected utilities are analysed under the assumption that the manufacturer service is a decision variable and an exogenous variable, respectively. Third, sensitivity analysis and numerical simulation are performed to verify our propositions consistently and seek more managerial implications. The findings suggest that the manufacturers value-added services in his direct channel will improve the direct price while decreasing the retail price. Consumers channel loyalty degree has a great influence on the optimal price decisions and the performance of the channel members. The direct price increase while the retail price decrease in the manufacturers value-added services. The retailers risk aversion has a greater influence on her own price decisions than that of the manufacturer.
Keywords: dual-channel supply chain; risk aversion; value-added services; Bertrand game; Stackelberg game.
A Novel IoT-based Arrhythmia Detection System with ECG Signals Using a Hybrid Convolutional Neural Network and Neural Architecture Search Network
by Umit Senturk, Ceren Gülen, Kemal Polat
Abstract: Electrocardiogram (ECG) signals are the most common tool to evaluate the hearts function in cardiovascular diagnosis. Irregular heartbeats (Arrhythmia) found in the ECG play an essential role in diagnosing cardiovascular diseases (CVD). In this paper, we proposed an arrhythmia classification method with the neural architecture search network (NASNet) model, an optimised version of the convolutional neural networks (2D-CNN) model, which performs very well in visual information analysis classification. We aimed to use the arrhythmia classification problem in IoT and mobile devices with the NASNet model with low parameter numbers and processing capacity without performance loss. 2D input data have been obtained by converting the classified heart rate signals in the datasets into image files. The 2D data obtained have been classified by machine learning, CNN, and NASNet models. As a result of classification, 2D CNN accuracy was 97.51%, and the NASNet model was 96.89% accuracy. As a result of arrhythmia classification, the accuracy rates of the NASNet and the 2D CNN models were close. In conclusion, the proposed IoT-based arrhythmia detection system with ECG signals using a hybrid CNN and NASNet is a promising tool for the early detection of arrhythmias. Furthermore, it could help to reduce the mortality associated with these potentially fatal conditions.
Keywords: arrhythmia detection; neural architecture search network; NASNet; IoT; network optimisation; time series; real-time measurement.
Channel competition, manufacturer incentive and supply chain coordination
by Zhi Pei, John Wang, Barbara Ross Wooldridge, Jie Sun
Abstract: COVID-19 created a surge in e-commerce usage, leading to fierce channel competition between the manufacturers online sales and the offline retailer. Hence, the imperative need for effective and innovative optimisation strategies to mitigate channel competition. Manufacturer-coupons are widely practiced in market, yet research on the importance they play in coordinating channel competition to achieve optimisation in channel distributions is scarce. This research addresses this gap by examining the effectiveness of manufacturer-coupons on the coordination of the manufacturers online sales and offline retailers sales. The findings indicate that issuing a manufacturer-coupon to the customers who buy from the offline retailer reduces the competition in the different channel distributions, but cost sharing of the retailer coupon is a better strategy. We thus examine if profit sharing is an effective strategy to facilitate the use of manufacturer-coupon in the market. After comparing different scenarios, we conclude that advanced profit-sharing can be effective in making manufacturer-coupon prevalent in the market and thus alleviate channel competition effectively.
Keywords: e-commerce; channel competition; manufacturer-coupon; coordination strategies; game theory.
A DEA-based decision framework for performance evaluation and ranking of workers in a real case from food industries
by Sadegh Niroomand
Abstract: In this study, a performance evaluation problem of operational employees in a real case study is considered. The case study is a firm from food industries where different tomato pastes are produced there. In addition, further than performance evaluation, in this study the operational employees are ranked based on their performances. As the main contribution of this study, a real-world problem from food industries is focused and solved by the optimisation-based approaches. For this aim, the most important criteria from the literature such as salary, work conditions, responsiveness, motivation, and productivity are selected. A decision framework based on data envelopment analysis (DEA) is used. For this aim, the Russel DEA model is used as the first stage to evaluate the performance of each operational worker (DMU) by determining efficient and inefficient DMUs. As the second stage, an Anderson-Peterson approach based on a modification of the Russel model is proposed to rank the DMUs based of their performances. Finally, based on the obtained results, some comparisons with the other DEA models of the literature is performed and the managerial insights are presented.
Keywords: food industry; performance evaluation; performance ranking; data envelopment analysis; DEA; Russel model.
An Extension Behavioral TOPSIS Method for Decision-Making Problems with Fuzzy Information
by Fereshteh Khademi, Farzad Rezai Balf, Mohsen Rabbani, Reza Shahverdi
Abstract: The concept of TOPSIS has been seen in many multi-criteria decisions but it is a built-in multi-attribute value function that is not explicitly specified. In many cases, the decision maker (DM) has to adopt certain policies with regard to the expected benefits and losses in the model and make good economic behaviour with new decisions. The present paper presents the concepts the behavioural TOPSIS under a fuzzy environment that considers the behavioural tendency in the decision-making process. The behavioural TOPSIS may not be the best rational choice, but it is the logical outcome of a variety of decision-making methods. In behavioural fuzzy TOPSIS, DM considers the benefit-loss ratio and provides weighted attributes in the process of economic behaviour. Here, at first, we re-present the classic TOPSIS method according to the traditional decision theory. Then, we describe behavioural TOPSIS and fuzzy TOPSIS in detail. In the following, the proposed method is presented along with its step-by-step algorithm. Finally, a numerical example is presented to illustrate the behavioural fuzzy TOPSIS model and the method of ranking all the suppliers.
Keywords: TOPSIS; fuzzy TOPSIS; behavioural TOPSIS; behavioural fuzzy TOPSIS.
A new model for efficiency estimation and evaluation:DEA-RA-Inverted DEA model
by B.-J. Zhang, Shi-Lan Su, Qizhou Gong
Abstract: Data envelopment analysis (DEA) is widely used in various fields and for various models. Inverted data envelopment analysis (inverted DEA) is an extended model of DEA. Regression analysis (RA) is a statistical process for estimating the relationships among variables based on the model of averaged image. There are no essential relations among DEA and RA and inverted DEA. We creatively combine DEA, RA and inverted DEA to propose a new model: DEA-RA-Inverted DEA model. The model realises the efficiency estimation and evaluation through a discussion of the residual variables and the residual ratio coefficients. In addition, we will demonstrate the effectiveness of the model by applying it to efficiency estimation and evaluation of 16 Chinese logistics enterprises.
Keywords: data envelopment analysis; DEA; inverted data envelopment analysis; inverted DEA; regression analysis; efficiency evaluation; sample decision unit; preference cone.
A Fuzzy-probabilistic Bi-objective Mathematical Model for Integrated Order Allocation, Production Planning, and Inventory Management
by Solikhin Solikhin, Sutrisno Sutrisno, Abdul Aziz, Purnawan Adi Wicaksono
Abstract: An optimisation-based decision-making support is proposed in this study in the form of fuzzy-probabilistic programming, which can be used to solve integrated order allocation, production planning, and inventory management problems in fuzzy and probabilistic uncertain environments. The problem was modelled in an uncertain mathematical optimisation model with two objectives: maximising the expectation of production volume and minimising the expectation of total operational cost subject to demand and other constraints. The model belongs to fuzzy-probabilistic bi-objective integer linear programming, and the generalised reduced gradient method combined with the branch-and-bound algorithm was utilised to solve the derived model. Numerical simulations were performed to illustrate how the optimal decision was formulated. The results showed that the proposed decision-making support was successful in providing the optimal decision with the maximum expectation of the production volume and minimum expectation of the total operational cost. Therefore, the approach can be implemented by decision-makers in manufacturing companies.
Keywords: decision-making support; fuzzy parameter; order allocation; probabilistic parameter; production planning; uncertain programming.
Behavioural Finance Research and Knowledge Mapping: A Comprehensive Bibliometric Analysis from 2010 to 2022
by Anshita Bihari, Manoranjan Dash, Padma Charan Mishra, Sukumar Dash
Abstract: The study aims to explore the patterns and connections in the behavioural biases and investment decisions of existing literature on the Web of Science database using Science mapping and performance analysis tools. This study selected 512 research papers from the Web of Science database published between 2010 and 2022 after deep screening all influential authors with their citations exposed along with top journals. The pattern of the papers highlighted and the connection between literatures gives direction for future research. Publication on behavioural biases and investment decisions increased since 2016. The Journal of Behavioural Finance is leading in published documents, the Journal of Financial Economics has the highest citation count, and the USA is the top country in publications and citations. The outcome of this study provides valuable insights into the intellectual structure of biases of investors and adds value to the existing knowledge. This review offers knowledge and theories for the behavioural finance discipline and provides a road map for the future trend of research on behavioural biases and investment decisions.
Keywords: knowledge mapping; behavioural biases; investment decision; bibliometric analysis.
Does the optimal model always perform the best? A combined approach for interval forecasting
by Zhe Zhang, CHOO W.E.I. CHONG, Jayanthi Arasan
Abstract: Interval forecasting is widely applied by decision makers for it can provide more comprehensive information. In the literature, GARCH models under different distributional assumptions are applied and evaluated to find the optimal interval forecasting model for the experimental data. However, the optimal model selected based on sample data from a specific period may not always perform the best in future periods. Therefore, this study employs GARCH models based on different distributional assumptions for interval forecasting of the daily return data of the Nasdaq Composite Index. The results show that the forecasting performance of some models exhibits significant differences across different periods. To address this issue, this study proposes a Monte Carlo-based non-parametric interval forecasting combination method. The results demonstrate that this method can effectively avoid the risk of forecasting inaccuracies caused by relying on a single model.
Keywords: interval forecasting; optimal model; combined approach; GARCH model; distribution assumptions; Monte Carlo.
Sentiment Analysis on Stocks: A Hybrid Feature Extraction Technique on Fourteen Classifiers
by MEERA GEORGE, R. Murugesan
Abstract: Accurately predicting stock prices is challenging and has garnered massive attention from researchers and investors alike. Though the literature has shown sentiment analysis as a promising approach for efficient stock price prediction, it has found a considerable gap in studies using multiple feature extraction techniques with hybrid models for the efficient sentiment classification. Under these circumstances, this study aims to perform sentiment analysis using five feature extraction techniques including a hybrid and 14 classifiers for the accurate classification of stock tweets. The study extracted 21121 tweets spanning March 2022 to December 2022 using Twitter application programming interface. The empirical result shows the superiority of the hybrid feature extraction technique over the other methods. The support vector machine classifier with a hybrid feature extraction technique is found to be the best-performing sentiment analysis model for Twitter stock data. The study has potential applications in building optimal investment strategies and decision-making.
Keywords: stock price; sentiment analysis; classifiers; feature extraction; hybrid.
Big data analytical capability and firm performance: moderating effect of analytics capability business strategy alignment
by Amal Sindarov, Ali Vafaei-Zadeh, Syafrizal Syafrizal, Razib Chandra Chanda
Abstract: This research investigates the impact of big data analytical capability (BDAC) on decision-making performance, comparative advantage, and firm performance considering the moderating effect of analytical capability business strategy alignment among manufacturing companies. To test the research framework, a survey questionnaire was distributed to Malaysian manufacturing companies. The results indicate that customer orientation, entrepreneurial orientation, and technology orientation positively and significantly affect BDAC. Besides, BDAC has a positive and significant effect on decision making performance, comparative advantage, and firm performance. The results of this study highlighted that BDAC is an important enabler of organisational performance and their competitive advantage. However, DBAC is more strongly related to competitive advantage than to firm performance.
Keywords: ig data analytics; decision making performance; firm performance; competitive advantage; technology orientation; Malaysia; big data analytical capability; BDAC.
Impact of COVID-19 on systemic risk for Indian financial institutions
by Subhash Karmakar, Gautam Bandyopadhyay, Dragan Pamucar, Jayanta Nath Mukhopadhyaya, Sanjib Biswas
Abstract: This paper studies differential impact of COVID-19 on systemic risk during different phases of lockdown on the financial institutions in India. We use SRISK as a measure of systemic risk and study three categories of financial institutions viz., public sector banks (PSBs), private sector banks and non-banking financial companies (NBFCs). We use Kruskal-Wallis test for examining the difference in the SRISK parameter for the three categories of financial institutions considered in this paper and observe significant difference. We have also estimated the Spearman correlations between the Indian volatility index (VIX) and SRISK across the three categories of financial institutions. The PSBs are foremost in risk contribution compared to private banks and NBFCs but they are not affected by market volatility index as compared to their counterparts, on the other hand medium and small sized PSBs have performed well as compared to large PSBs. Based on the result it is inferred that the month of April 2020-June 2020 (lockdown period) had the most significant increase in systemic risk.
Keywords: systemic risk; SRISK; COVID-19; NBFC; banks; financial institutions; volatility index; VIX.
FE-TAC: an effective document classification method combining feature extraction and feature selection
by Kshetrimayum Nareshkumar Singh, Haobam Mamata Devi, Anjana Kakoti Mahant, Ahongsangbam Dorendro
Abstract: An effective classification method requires the most informative and relevant set of features. In this paper, we discuss an enhanced text classification method combining feature extraction (FE) and feature selection. First, we used the FE method to extract features from text data and then apply the feature selection method to select the most relevant features out of those extracted features. During feature selection, we introduce a new measure called term affinity to the class (TAC) to estimate the degree of retaining capability of the term as a member of the particular class. TAC is computed based on the combination of normalise document frequency and summing up the occurrence frequency of the term to the specific class. Experimental results on three existing datasets - BBC, Classic4, 20 Newsgroup, and our own dataset called 'Sangai' show that the proposed method outperforms the other competent methods in terms of accuracy.
Keywords: bag of words; BoW; document representation; term weights; text classification; word vectors.
Factors predicting customer satisfaction in online hotel booking using machine learning technique: evidence from developing countries
by Mehnaz, Jiahua Jin, Wasim Ahmad, Azhar Hussain
Abstract: This paper predicts and documents the determinants of customer satisfaction in online hotel booking for the foreign tourists in developing countries. The data was taken from the customer web-based reviews and comments. The study forecasts customer satisfaction by comparing logistic model with artificial neural network (ANN) in terms of prediction accuracy. In case of both datasets, i.e., training and testing, ANN outperformed the logistic regression model in terms of prediction. In other words, ANN is more robust in terms of prediction as compared to logistic regression model. Furthermore, empirical results depict that rental price, staff performance, location, services quality, and rating are the significant tools to maximise customer satisfaction. Hotel authorities in developing countries need to focus on these factors where customer feedback may play a significant role implementing the best services of hotels. These incentives will help to increase the booking incentives and ensure sufficient revenues for hotel industry of developing nations.
Keywords: online hotel booking; customer satisfaction; location; price; service quality; artificial neural network; ANN.
Green integrated inventory model for deteriorating items with imperfect production process under inflationary environment
by Nidhi Handa, S.R. Singh, Neha Punetha
Abstract: Supply chain activities significantly contribute to ecological deterioration due to carbon emission. Mainly its purpose is to integrate environmental issues as energy efficiency and carbon emission. The paper develops three-echelon sustainable supply chain of deteriorating products with deterministic demand rate under energy and carbon emission cost. This work minimises the total integrated cost and optimises critical time. The supply chain system with carbon emission under inflation provides a better result for environmental concern. Some theoretical work is done to enunciate the objective function using the classical optimisation techniques. The decision-makers may reduce integrated costs by considering the effect of inflation. To exemplify and validate the proposed study, numerical analysis is done. Further, sensitivity analysis is presented to study the effect of inventory parameters on inventory decisions. The total integrated cost with carbon emissions is highest compared to without carbon emissions.
Keywords: supply chain management; SCM; imperfect items; deterioration; rework; energy; inflation; carbon emission.