Search results
1 – 10 of 208
The purpose of this study is to examine the effects of banking innovations (INNs) on customer experience (EXP), satisfaction (SAT) and loyalty (LOY).
Abstract
Purpose
The purpose of this study is to examine the effects of banking innovations (INNs) on customer experience (EXP), satisfaction (SAT) and loyalty (LOY).
Design/methodology/approach
The author evaluated the data using a structural equation method-artificial neural network (SEM-ANN) method. The author’s results show the presence of relationship between INN, EXP, SAT and LOY. In this study, the node layers of ANNs add an input layer, hidden layers and an output layer. Each “node” acts as an artificial neuron that communicates with others. The ANN model takes the variables from the SEM analysis as input neurons.
Findings
The author observed the significant effects between INN, EXP, SAT and LOY using the normalised importance generated by the multilayer perceptron used in the feed-forward back propagation of the ANN methodology. In this study, the ANN model can predict LOY through service innovation, with a forecast accuracy of 77.6%.
Originality/value
By applying neural network modelling, this research helps us understand how service innovation affects customer behaviour. For the first time, the author examined service innovations' direct and indirect impact on loyalty through EXP and SAT. The author made a significant conceptual contribution by using a non-compensatory model of ANNs to circumvent the limitations of linear models.
Details
Keywords
This study aims to show the effectiveness and applicability of artificial intelligence applications in the measurement and evaluation of university services. Universities can gain…
Abstract
Purpose
This study aims to show the effectiveness and applicability of artificial intelligence applications in the measurement and evaluation of university services. Universities can gain competitive advantage through providing their students with quality services in various aspects, such as bookstores, dormitories, recreation centers as well as cafeterias. Among these facilities, university cafeterias are places where students spend a significant amount of time. Therefore, this study aims to integrate artificial intelligence application in the evaluation of university cafeteria services based on students' perceptions with two-stage structural equation modeling (SEM) and artificial neural network (ANN) approach.
Design/methodology/approach
An artificial intelligence based SEM-ANN hybrid approach was used to determine the factors that have significant influence on student satisfaction, sufficiency-of-services and likelihood-of-recommendation. Data were collected from 373 students through a face-to-face questionnaire. Initially, four service quality dimensions were attained through factor analysis. Then, hypotheses, which were determined via literature review, were tested through SEM-ANN hybrid approach.
Findings
Incorporating the results of SEM analysis into the ANN technique resulted in superior models with good prediction performance. Based on four ANN models created and ANN sensitivity analyses conducted, significant predictors of satisfaction, sufficiency, reliability and recommendation are determined and ranked.
Originality/value
Prior studies have assessed service quality using traditional techniques, whereas, this study integrates artificial intelligence in the assessment of higher-educational institutions' services quality. Also, as a distinction from previous studies, this study ranked importance levels of predictor variables through ANN sensitivity analysis.
Details
Keywords
Nirodha Fernando, Kasun Dilshan T.A. and Hexin (Johnson) Zhang
The Government’s investment in infrastructure projects is considerably high, especially in bridge construction projects. Government authorities must establish an initial…
Abstract
Purpose
The Government’s investment in infrastructure projects is considerably high, especially in bridge construction projects. Government authorities must establish an initial forecasted budget to have transparency in transactions. Early cost estimating is challenging for Quantity Surveyors due to incomplete project details at the initial stage and the unavailability of standard cost estimating techniques for bridge projects. To mitigate the difficulties in the traditional preliminary cost estimating methods, there is a requirement to develop a new initial cost estimating model which is accurate, user friendly and straightforward. The research was carried out in Sri Lanka, and this paper aims to develop the artificial neural network (ANN) model for an early cost estimate of concrete bridge systems.
Design/methodology/approach
The construction cost data of 30 concrete bridge projects which are in Sri Lanka constructed within the past ten years were trained and tested to develop an ANN cost model. Backpropagation technique was used to identify the number of hidden layers, iteration and momentum for optimum neural network architectures.
Findings
An ANN cost model was developed, furnishing the best result since it succeeded with around 90% validation accuracy. It created a cost estimation model for the public sector as an accurate, heuristic, flexible and efficient technique.
Originality/value
The research contributes to the current body of knowledge by providing the most accurate early-stage cost estimate for the concrete bridge systems in Sri Lanka. In addition, the research findings would be helpful for stakeholders and policymakers to propose policy recommendations that positively influence the prediction of the most accurate cost estimate for concrete bridge construction projects in Sri Lanka and other developing countries.
Details
Keywords
Paravee Maneejuk, Binxiong Zou and Woraphon Yamaka
The primary objective of this study is to investigate whether the inclusion of convertible bond prices as important inputs into artificial neural networks can lead to improved…
Abstract
Purpose
The primary objective of this study is to investigate whether the inclusion of convertible bond prices as important inputs into artificial neural networks can lead to improved accuracy in predicting Chinese stock prices. This novel approach aims to uncover the latent potential inherent in convertible bond dynamics, ultimately resulting in enhanced precision when forecasting stock prices.
Design/methodology/approach
The authors employed two machine learning models, namely the backpropagation neural network (BPNN) model and the extreme learning machine neural networks (ELMNN) model, on empirical Chinese financial time series data.
Findings
The results showed that the convertible bond price had a strong predictive power for low-market-value stocks but not for high-market-value stocks. The BPNN algorithm performed better than the ELMNN algorithm in predicting stock prices using the convertible bond price as an input indicator for low-market-value stocks. In contrast, ELMNN showed a significant decrease in prediction accuracy when the convertible bond price was added.
Originality/value
This study represents the initial endeavor to integrate convertible bond data into both the BPNN model and the ELMNN model for the purpose of predicting Chinese stock prices.
Details
Keywords
Marc Roedenbeck and Petra Poljsak-Rosinski
This study investigates whether the artificial neural network approach, when used on a large organizational soft HR performance dataset, results in a better (R2/RMSE) model…
Abstract
Purpose
This study investigates whether the artificial neural network approach, when used on a large organizational soft HR performance dataset, results in a better (R2/RMSE) model compared to the linear regression. With the use of predictive modelling, a more informed base for managerial decision making within soft HR performance management is offered.
Design/methodology/approach
The study builds on a dataset (n > 43 k) stemming from an annual employee MNC survey. It covers several soft HR performance drivers and outcomes (such as engagement, satisfaction and others) that either have evidence of a dual-role nature or non-linear relationships. This study applies the framework for artificial neural network analysis in organization research (Scarborough and Somers, 2006).
Findings
The analysis reveals a substantial artificial neural network model performance (R2 > 0.75) with an excellent fit statistic (nRMSE <0.10) and all drivers have the same relative importance (RMI [0.102; 0.125]). This predictive analysis revealed that the organization has to increase six of the drivers, keep two on the same level and decrease one.
Originality/value
Up to date, this study uses the largest dataset in soft HR performance management. Additionally, the predictive results reveal that specific target values lay below the current levels to achieve optimal performance.
Details
Keywords
In order to analyze the text complexity of Chinese and foreign academic English writings, the artificial neural network (ANN) under deep learning (DL) is applied to the study of…
Abstract
Purpose
In order to analyze the text complexity of Chinese and foreign academic English writings, the artificial neural network (ANN) under deep learning (DL) is applied to the study of text complexity. Firstly, the research status and existing problems of text complexity are introduced based on DL. Secondly, based on Back Propagation Neural Network (BPNN) algorithm, analyzation is made on the text complexity of Chinese and foreign academic English writings. And the research establishes a BPNN syntactic complexity evaluation system. Thirdly, MATLAB2013b is used for simulation analysis of the model. The proposed model algorithm BPANN is compared with other classical algorithms, and the weight value of each index and the model training effect are further analyzed by statistical methods. Finally, L2 Syntactic Complexity Analyzer (L2SCA) is used to calculate the syntactic complexity of the two libraries, and Mann–Whitney U test is used to compare the syntactic complexity of Chinese English learners and native English speakers. The experimental results show that compared with the shallow neural network, the deep neural network algorithm has more hidden layers and richer features, and better performance of feature extraction. BPNN algorithm shows excellent performance in the training process, and the actual output value is very close to the expected value. Meantime, the error of sample test is analyzed, and it is found that the evaluation error of BPNN algorithm is less than 1.8%, of high accuracy. However, there are significant differences in grammatical complexity among students with different English writing proficiency. Some measurement methods cannot effectively reflect the types and characteristics of written language, or may have a negative relationship with writing quality. In addition, the research also finds that the measurement of syntactic complexity is more sensitive to the language ability of writing. Therefore, BPNN algorithm can effectively analyze the text complexity of academic English writing. The results of the research provide reference for improving the evaluation system of text complexity of academic paper writing.
Design/methodology/approach
In order to analyze the text complexity of Chinese and foreign academic English writings, the artificial neural network (ANN) under deep learning (DL) is applied to the study of text complexity. Firstly, the research status and existing problems of text complexity are introduced based on DL. Secondly, based on Back Propagation Neural Network (BPNN) algorithm, analyzation is made on the text complexity of Chinese and foreign academic English writings. And the research establishes a BPNN syntactic complexity evaluation system. Thirdly, MATLAB2013b is used for simulation analysis of the model. The proposed model algorithm BPANN is compared with other classical algorithms, and the weight value of each index and the model training effect are further analyzed by statistical methods. Finally, L2 Syntactic Complexity Analyzer (L2SCA) is used to calculate the syntactic complexity of the two libraries, and Mann–Whitney U test is used to compare the syntactic complexity of Chinese English learners and native English speakers. The experimental results show that compared with the shallow neural network, the deep neural network algorithm has more hidden layers and richer features, and better performance of feature extraction. BPNN algorithm shows excellent performance in the training process, and the actual output value is very close to the expected value. Meantime, the error of sample test is analyzed, and it is found that the evaluation error of BPNN algorithm is less than 1.8%, of high accuracy. However, there are significant differences in grammatical complexity among students with different English writing proficiency. Some measurement methods cannot effectively reflect the types and characteristics of written language, or may have a negative relationship with writing quality. In addition, the research also finds that the measurement of syntactic complexity is more sensitive to the language ability of writing. Therefore, BPNN algorithm can effectively analyze the text complexity of academic English writing. The results of the research provide reference for improving the evaluation system of text complexity of academic paper writing.
Findings
In order to analyze the text complexity of Chinese and foreign academic English writings, the artificial neural network (ANN) under deep learning (DL) is applied to the study of text complexity. Firstly, the research status and existing problems of text complexity are introduced based on DL. Secondly, based on Back Propagation Neural Network (BPNN) algorithm, analyzation is made on the text complexity of Chinese and foreign academic English writings. And the research establishes a BPNN syntactic complexity evaluation system. Thirdly, MATLAB2013b is used for simulation analysis of the model. The proposed model algorithm BPANN is compared with other classical algorithms, and the weight value of each index and the model training effect are further analyzed by statistical methods. Finally, L2 Syntactic Complexity Analyzer (L2SCA) is used to calculate the syntactic complexity of the two libraries, and Mann–Whitney U test is used to compare the syntactic complexity of Chinese English learners and native English speakers. The experimental results show that compared with the shallow neural network, the deep neural network algorithm has more hidden layers and richer features, and better performance of feature extraction. BPNN algorithm shows excellent performance in the training process, and the actual output value is very close to the expected value. Meantime, the error of sample test is analyzed, and it is found that the evaluation error of BPNN algorithm is less than 1.8%, of high accuracy. However, there are significant differences in grammatical complexity among students with different English writing proficiency. Some measurement methods cannot effectively reflect the types and characteristics of written language, or may have a negative relationship with writing quality. In addition, the research also finds that the measurement of syntactic complexity is more sensitive to the language ability of writing. Therefore, BPNN algorithm can effectively analyze the text complexity of academic English writing. The results of the research provide reference for improving the evaluation system of text complexity of academic paper writing.
Originality/value
In order to analyze the text complexity of Chinese and foreign academic English writings, the artificial neural network (ANN) under deep learning (DL) is applied to the study of text complexity. Firstly, the research status and existing problems of text complexity are introduced based on DL. Secondly, based on Back Propagation Neural Network (BPNN) algorithm, analyzation is made on the text complexity of Chinese and foreign academic English writings. And the research establishes a BPNN syntactic complexity evaluation system. Thirdly, MATLAB2013b is used for simulation analysis of the model. The proposed model algorithm BPANN is compared with other classical algorithms, and the weight value of each index and the model training effect are further analyzed by statistical methods. Finally, L2 Syntactic Complexity Analyzer (L2SCA) is used to calculate the syntactic complexity of the two libraries, and Mann–Whitney U test is used to compare the syntactic complexity of Chinese English learners and native English speakers. The experimental results show that compared with the shallow neural network, the deep neural network algorithm has more hidden layers and richer features, and better performance of feature extraction. BPNN algorithm shows excellent performance in the training process, and the actual output value is very close to the expected value. Meantime, the error of sample test is analyzed, and it is found that the evaluation error of BPNN algorithm is less than 1.8%, of high accuracy. However, there are significant differences in grammatical complexity among students with different English writing proficiency. Some measurement methods cannot effectively reflect the types and characteristics of written language, or may have a negative relationship with writing quality. In addition, the research also finds that the measurement of syntactic complexity is more sensitive to the language ability of writing. Therefore, BPNN algorithm can effectively analyze the text complexity of academic English writing. The results of the research provide reference for improving the evaluation system of text complexity of academic paper writing.
Details
Keywords
Driven by the evidence from the literature on the significance of mobile (m-)payment in economic growth and productivity and at the same time the relative dismal adoption of this…
Abstract
Purpose
Driven by the evidence from the literature on the significance of mobile (m-)payment in economic growth and productivity and at the same time the relative dismal adoption of this service, the purpose of present paper is to elucidate the merchants’ m-payment adoption from the perspective of trust, drawing upon the game theory framework, in the Malaysian context.
Design/methodology/approach
An online survey consisting of 302 respondents was carried out to investigate the impact of trust and opportunism on merchants’ perceived trustworthiness using a two-staged structural equation modeling–neural network approach to determine the significance and relative importance of variables. This study also applies a game-theoretic approach to analyze the impact of trust on the relationship between merchants and m-payment service providers.
Findings
The results indicate a positive and statistically significant relationship between merchant trust, merchant opportunism and perceived trustworthiness, and a statistically significant negative relationship was found between m-payment provider opportunism and perceived trustworthiness. The findings from the prisoner’s dilemma two-player model indicate that the scenarios of mutual trust and mutual opportunism as paradigmatic of cooperation and defection produce the best and worse outcomes, respectively. An intriguing result was the positive impact of merchant opportunism on perceived trustworthiness, which indicates a very calculative orientation of merchants in m-payment contracting.
Originality/value
To the best of the authors’ knowledge, this is among the first attempts to propose a game theory approach to the interaction between merchants and m-payment providers under the framework of trust and opportunism. A game theory study in the context of m-payment adoption can contribute to the theoretical literature by providing insights into the decision-making processes of merchants. By incorporating trust and opportunism into the game theory model, we can gain a better understanding of how they affect the decision-making process and overall adoption rates. The conclusions and implications provide useful insights for managers of both m-payment platforms and merchants in this relational exchange. The results of the present research can provide insights into the factors that influence merchant decisions and guide them toward suitable partnerships for successful adoption and can guide authorities for policy interventions and supporting adoption efforts.
Details
Keywords
Ngoc Tuan Chau, Hepu Deng and Richard Tay
Understanding the adoption of m-commerce in small and medium-sized enterprises (SMEs) is critical for their sustainable development. This study aims to investigate the adoption of…
Abstract
Purpose
Understanding the adoption of m-commerce in small and medium-sized enterprises (SMEs) is critical for their sustainable development. This study aims to investigate the adoption of m-commerce in Vietnamese SMEs, leading to the identification of the critical determinants and their relative importance for m-commerce adoption.
Design/methodology/approach
An integrated model is developed by combining the diffusion of innovation theory and the technology–organization–environment framework. Such a model is then tested and validated using structural equation modeling and artificial neural networks in analyzing the survey data.
Findings
The study indicates that perceived security is the most critical determinant for m-commerce adoption. It further shows that customer pressure, perceived compatibility, organizational innovativeness, perceived benefits, managers’ IT knowledge, government support and organizational readiness all play a critical role in the adoption of m-commerce in Vietnamese SMEs.
Practical implications
The findings of this study can lead to the formulation of better strategies and policies for promoting the adoption of m-commerce in Vietnamese SMEs. Such findings are also of practical significance for the diffusion of m-commerce in SMEs in other developing countries.
Originality/value
To the best of the authors’ knowledge, this is the first attempt to explore the adoption of m-commerce in Vietnamese SMEs using a hybrid approach. The application of this approach can lead to better understanding of the relative importance of the critical determinants for the adoption of m-commerce in Vietnamese SMEs.
Details
Keywords
The advent of technology has propelled audit firms to incorporate AI-based audit services, bringing the relationship between audit clients and firms into sharper focus…
Abstract
Purpose
The advent of technology has propelled audit firms to incorporate AI-based audit services, bringing the relationship between audit clients and firms into sharper focus. Nonetheless, the understanding of how AI-based audit services affect this relationship remains sparse. This study strives to probe how an audit client's satisfaction with AI-based audit services influences their trust in audit firms. Identifying the variables affecting this trust, the research aspires to gain a deeper comprehension of the implications of AI-based audit services on the auditor-client relationship, ultimately aiming to boost client satisfaction and cultivate trust.
Design/methodology/approach
A conceptual framework has been devised, grounded in the client-company relationship model, to delineate the relationship between perceived quality, perceived value, attitude and satisfaction with AI-based audit services and their subsequent impact on trust in audit firms. The research entailed an empirical investigation employing Facebook ads, gathering 288 valid responses for evaluation. The structural equation method, utilized in conjunction with SPSS and Amos statistical applications, verified the reliability and overarching structure of the scales employed to measure these elements. A hybrid multi-analytical technique of structural equation modeling and artificial neural networks (SEM-ANN) was deployed to empirically validate the collated data.
Findings
The research unveiled a significant and positive relationship between perceived value and client satisfaction, trust and attitude towards AI-based audit services, along with the link between perceived quality and client satisfaction. The findings suggest that a favorable attitude and perceived quality of AI-based audit services could enhance satisfaction, subsequently augmenting perceived value and client trust. By focusing on the delivery of superior-quality services that fulfill clients' value expectations, firms may amplify client satisfaction and trust.
Research limitations/implications
Further inquiries are required to appraise the influence of advanced technology adoption within audit firms on client trust-building mechanisms. Moreover, an understanding of why the impact of perceived quality on perceived value proves ineffectual in the context of audit client trust-building warrants further exploration. In interpreting the findings of this study, one should consider the inherent limitations of the empirical analysis, inclusive of the utilization of Facebook ads as a data-gathering tool.
Practical implications
The research yielded insightful theoretical and practical implications that can bolster audit clients' trust in audit firms amid technological advancements within the audit landscape. The results imply that audit firms should contemplate implementing trust-building mechanisms by creating value and influencing clients' stance towards AI-based audit services to establish trust, particularly when vying with competing firms. As technological evolutions impinge on trustworthiness, audit firms must prioritize clients' perceived value and satisfaction.
Originality/value
To the researcher's best knowledge, no previous study has scrutinized the impact of satisfaction with AI-based audit services on cultivating audit client trust in audit firms, in contrast to past research that has focused on the auditors' trust in the audit client. To bridge these gaps, this study employs a comprehensive and integrative theoretical model.
Details
Keywords
Abdelhadi Ifleh and Mounime El Kabbouri
The prediction of stock market (SM) indices is a fascinating task. An in-depth analysis in this field can provide valuable information to investors, traders and policy makers in…
Abstract
Purpose
The prediction of stock market (SM) indices is a fascinating task. An in-depth analysis in this field can provide valuable information to investors, traders and policy makers in attractive SMs. This article aims to apply a correlation feature selection model to identify important technical indicators (TIs), which are combined with multiple deep learning (DL) algorithms for forecasting SM indices.
Design/methodology/approach
The methodology involves using a correlation feature selection model to select the most relevant features. These features are then used to predict the fluctuations of six markets using various DL algorithms, and the results are compared with predictions made using all features by using a range of performance measures.
Findings
The experimental results show that the combination of TIs selected through correlation and Artificial Neural Network (ANN) provides good results in the MADEX market. The combination of selected indicators and Convolutional Neural Network (CNN) in the NASDAQ 100 market outperforms all other combinations of variables and models. In other markets, the combination of all variables with ANN provides the best results.
Originality/value
This article makes several significant contributions, including the use of a correlation feature selection model to select pertinent variables, comparison between multiple DL algorithms (ANN, CNN and Long-Short-Term Memory (LSTM)), combining selected variables with algorithms to improve predictions, evaluation of the suggested model on six datasets (MASI, MADEX, FTSE 100, SP500, NASDAQ 100 and EGX 30) and application of various performance measures (Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error(RMSE), Mean Squared Logarithmic Error (MSLE) and Root Mean Squared Logarithmic Error (RMSLE)).
Details