Search results
1 – 10 of over 6000Seyed Hossein Razavi Hajiagha, Shide Sadat Hashemi and Hannan Amoozad Mahdiraji
Data envelopment analysis (DEA) is a non-parametric model that is developed for evaluating the relative efficiency of a set of homogeneous decision-making units that each unit…
Abstract
Purpose
Data envelopment analysis (DEA) is a non-parametric model that is developed for evaluating the relative efficiency of a set of homogeneous decision-making units that each unit transforms multiple inputs into multiple outputs. However, usually the decision-making units are not completely similar. The purpose of this paper is to propose an algorithm for DEA applications when considered DMUs are non-homogeneous.
Design/methodology/approach
To reach this aim, an algorithm is designed to mitigate the impact of heterogeneity on efficiency evaluation. Using fuzzy C-means algorithm, a fuzzy clustering is obtained for DMUs based on their inputs and outputs. Then, the fuzzy C-means based DEA approach is used for finding the efficiency of DMUs in different clusters. Finally, the different efficiencies of each DMU are aggregated based on the membership values of DMUs in clusters.
Findings
Heterogeneity causes some positive impact on some DMUs while it has negative impact on other ones. The proposed method mitigates this undesirable impact and a different distribution of efficiency score is obtained that neglects this unintended impacts.
Research limitations/implications
The proposed method can be applied in DEA applications with a large number of DMUs in different situations, where some of them enjoyed the good environmental conditions, while others suffered from bad conditions. Therefore, a better assessment of real performance can be obtained.
Originality/value
The paper proposed a hybrid algorithm combination of fuzzy C-means clustering method with classic DEA models for the first time.
Details
Keywords
Chae Mi Lim, Rodney Runyan and Youn-Kyung Kim
This study aims to identify consumer segments among luxe-bargain shoppers using a fuzzy clustering method based on psychographic variables related to both luxury consumption and…
Abstract
Purpose
This study aims to identify consumer segments among luxe-bargain shoppers using a fuzzy clustering method based on psychographic variables related to both luxury consumption and bargain processes and profiles the identified segments in behavioral tendencies.
Design/methodology/approach
The sample consists of 500 consumers who purchased a luxury brand at a bargain. The analyses involve running a confirmatory factor analysis, a fuzzy clustering analysis based on psychographic variables, and ANOVA for profiling the segments.
Findings
A fuzzy clustering analysis identifies four distinct segments: deal hunters, sale-prone shoppers, active luxe-bargain shoppers, and royal shoppers. Each consumer segment exhibits differences in consumer characteristics, demographics, and behavioral tendencies. The study provides insight into varied luxury consumers.
Research limitations/implications
In an effort to fill the gap between traditional framework in luxury research and today ' s luxury market that provides accessibility of luxury items at lower price points to mass consumers, this study introduces a new concept of “luxe-bargain shopper” and examines varied luxury good consumers in the bargain shopping context. However, the findings of the current study should be interpreted with caution due to sampling method, product category of luxury brands, the limited number of luxury brands used in the study.
Practical implications
The results provide marketing suggestions for each segment of luxe-bargain shoppers.
Originality/value
There is virtually no luxury study conducted in the context of bargain shopping. By examining luxe-bargain shoppers using a robust fuzzy clustering method, this study extends our knowledge of luxury consumption as well as provides a new perspective to segmentation research.
Details
Keywords
Harry Barton and Malcolm J. Beynon
The UK police service has a major challenge to introduce innovative ways of improving efficiency and productivity, whilst at the same time improving public opinion as to their…
Abstract
Purpose
The UK police service has a major challenge to introduce innovative ways of improving efficiency and productivity, whilst at the same time improving public opinion as to their effectiveness in the “fight against crime”. The purpose of this paper is to outline an exploratory study of the ability to cluster police forces based on their sanction detection levels over a number of different offence groups and whether these clusters have different associated public opinions towards them.
Design/methodology/approach
Using secondary data and the fuzzy c‐means clustering technique to exposit clusters of police forces based on sanction detection levels, relating them in a statistical analysis with public opinion on the police.
Findings
The clustering analysis shows how police forces can be considered relative to each other, based on their sanction detection levels of certain offence groups, including; burglary, fraud and forgery and criminal damage. Using the established clusters of police forces, in respect of independent variables relating to public opinion, including confidence in police; there does appear to be statistically significant differences amongst the clusters of police force.
Research limitations/implications
The results demonstrate the connection between the police's attempt to fight crime and public opinion. With the public opinion measures considered post the establishing of police forces’ clusters, the results show the public does notice the level of sanction detections achieved. The identified disconnect of the public with the criminal justice system is something that can be improved on in the future.
Practical implications
Demonstrates that there is a significant link in the relationship between the levels of sanction detection levels of police forces and public opinion about their ability to fight crime.
Originality/value
This paper employs fuzzy c‐means, a modern clustering technique nascent in this area of research.
Details
Keywords
M. Ameer Ali, Gour C. Karmakar and Laurence S. Dooley
Existing shape‐based fuzzy clustering algorithms are all designed to explicitly segment regular geometrically shaped objects in an image, with the consequence that this restricts…
Abstract
Purpose
Existing shape‐based fuzzy clustering algorithms are all designed to explicitly segment regular geometrically shaped objects in an image, with the consequence that this restricts their capability to separate arbitrarily shaped objects. The purpose of this paper is to introduce a new detection and separation of generic‐shaped object algorithm.
Design/methodology/approach
With the aim of separating arbitrary‐shaped objects in an image, this paper presents a new detection and separation of generic‐shaped objects (FKG) algorithm that analytically integrates arbitrary shape information into a fuzzy clustering framework, by introducing a shape constraint that preserves the original object shape during iterative scaling.
Findings
Both qualitative and numerical empirical results analysis corroborate the improved object segmentation performance achieved by the FKG strategy upon different image types and disparately shaped objects.
Originality/value
The proposed FKG algorithm can be highly used in applications where object segmentation is necessary. Likewise, this algorithm can be applied in Moving Picture Experts Group‐4 for real object segmentation that is already applied in synthetic object segmentation.
Details
Keywords
Dang Luo and Zhang Huihui
The purpose of this paper is to propose a grey clustering model based on kernel and information field to deal with the situation in which both the observation values and the…
Abstract
Purpose
The purpose of this paper is to propose a grey clustering model based on kernel and information field to deal with the situation in which both the observation values and the turning points of the whitenization weight function are interval grey numbers.
Design/methodology/approach
First, the “unreduced axiom of degree of greyness” was expanded to obtain the inference of “information field not-reducing”. Then, based on the theoretical basis of inference, the expression of whitenization weight function with interval grey number was provided. The grey clustering model and fuzzy clustering model were compared to analyse the relationship and difference between the two models. Finally, the paper model and the fuzzy clustering model were applied to the example analysis, and the interval grey number clustering model was established to analyse the influencing factors of regional drought disaster risk in Henan Province.
Findings
The example analysis results illustrate that although the two clustering methods have different theoretical basis, they are suitable for dealing with complex systems with uncertainty or grey characteristic, solving the problem of incomplete system information, which has certain feasibility and rationality. The clustering results of case study show that five influencing factors of regional drought disaster risk in Henan Province are divided into three classes, consistent with the actual situation, and they show the validity and practicability of the clustering model.
Originality/value
The paper proposes a new whitenization weight function with interval grey number that can transform interval grey number operations into real number operations. It not only simplifies the calculation steps, but it has a great significance for the “small data sets and poor information” grey system and has a universal applicability.
Details
Keywords
Mohamed Yacine Haddoud, Malcolm J. Beynon, Paul Jones and Robert Newbery
The purpose of this paper is to analyse the determinants of small and medium-sized enterprises’ (SMEs) propensity to export using data from a North African country, namely…
Abstract
Purpose
The purpose of this paper is to analyse the determinants of small and medium-sized enterprises’ (SMEs) propensity to export using data from a North African country, namely Algeria. Drawing on the extended resource-based view, the study examines the role of firms’ resources and capabilities in explaining the probability to export.
Design/methodology/approach
The study employs the nascent fuzzy c-means clustering technique to analyse a sample of 208 Algerian SMEs. The sample included both established and potential exporters operating across various sectors. A combination of online and face-to-face methods was used to collect the data.
Findings
While a preliminary analysis established the existence of five clusters exhibiting different levels of resources and capabilities, further discernment of these clusters has shown significant variances in relation to export propensity. In short, clusters exhibiting combinations that include higher levels of export-oriented managerial resources showed greater export propensity, whereas clusters lacking such assets were less likely to display high export propensity, despite superior capabilities in marketing and innovation.
Practical implications
The findings provide a more comprehensive insight on the critical resources shaping SMEs’ internationalisation in the North African context. The paper holds important implications for export promotion policy in this area.
Originality/value
The study makes a twofold contribution. First, the use of the fuzzy c-means clustering technique to capture the joint influence of discrete resources and capabilities on SMEs’ export propensity constitutes a methodological contribution. Second, being the first study bringing evidence on SMEs’ internationalisation from the largest country in the African continent, in terms of landmass, constitutes an important contextual contribution.
Details
Keywords
Mohammad Reza Taghizadeh Yazdi
The purpose of this paper is to illustrate the application of statistical tools and techniques for quantitative assessment of spiritual capital (SC) based on a questionnaire…
Abstract
Purpose
The purpose of this paper is to illustrate the application of statistical tools and techniques for quantitative assessment of spiritual capital (SC) based on a questionnaire survey in the organizations which undergo large-scale organizational change projects.
Design/methodology/approach
A sample of 65 individuals from three organizations were interviewed. The paper uses the 12 principles of transformation available to spiritual intelligence (referred to as SQ characteristics) to assess SC in a two-phase integrated algorithm of principal component analysis (PCA) and fuzzy clustering.
Findings
The paper proposes a two-phase integrated algorithm. In the first phase, PCA is used to reduce the scores of items related to each of SQ characteristics and aggregate them into a single and unique measure. In the second phase, PCA is applied for total SQ quantification. For verification and validation, fuzzy clustering is employed along with PCA to cluster the people in the survey into different classes, which may possess different stocks of SC and rank them based on their level of SQ. The results of PCA are verified and validated by fuzzy clustering revealing the applicability and usefulness of PCA for SC quantification.
Research limitations/implications
The paper is based on individual judgments about their own SQ characteristics hence the results of questionnaire survey may be biased by individual personal characteristics. Future research can apply the proposed algorithm and check for its reliability using other psychometric instruments available in the field.
Originality/value
The paper contributes by filling a gap in the quantitative management tools literature, in which empirical studies on validated multivariate analysis of spirituality have been scarce until now.
Details
Keywords
The purpose of this paper is to propose a data mining approach for mining valuable markets for online customer relationship management (CRM) marketing strategy. The industry of…
Abstract
Purpose
The purpose of this paper is to propose a data mining approach for mining valuable markets for online customer relationship management (CRM) marketing strategy. The industry of coffee shops in Taiwan is employed as an empirical case study in this research.
Design/methodology/approach
Via a proposed data mining approach, the study used fuzzy clustering algorithm and Apriori algorithm to analyze customers for obtaining more marketing and purchasing knowledge of online CRM systems.
Findings
The research found three hard markets and one fuzzy market. Furthermore, the study discovered two association rules and two fuzzy association rules.
Originality/value
However, industry of coffee shops has been always a fast-growing and competitive business around the world. Thus, marketing strategy is important for this industry. The results and the proposed data mining approach of this research can be used in the industry of coffee shop or other retailers for their online CRM marketing systems.
Details
Keywords
Zhengbing Hu, Yevgeniy V. Bodyanskiy and Oleksii K. Tyshchenko
Ghizlane El bok and Abdelaziz Berrado
Categorizing projects allows for better alignment of a portfolio with the organizational strategy and goals. An appropriate project categorization helps understand portfolio’s…
Abstract
Purpose
Categorizing projects allows for better alignment of a portfolio with the organizational strategy and goals. An appropriate project categorization helps understand portfolio’s structure and enables proper project portfolio selection (PPS). In practice, project categorization is, however, conducted in intuitive approaches. Furthermore, little attention has been given to project categorization methods in the project management literature. The purpose of this paper is to provide researchers and practitioners with a data-driven project categorization process designed for PPS.
Design/methodology/approach
The suggested process was modeled considering the main characteristics of project categorization systems revealed from the literature. The clustering analysis is used as the core-computing technology, allowing for an empirically based categorization. This study also presents a real-world case study in the automotive industry to illustrate the proposed approach.
Findings
This study confirmed the potential of clustering analysis for a consistent project categorization. The most important attributes that influenced the project grouping have been identified including strategic and intrinsic features. The proposed approach helps increase the visibility of the portfolio’s structure and the comparability of its components.
Originality/value
There is a lack of research regarding project categorization methods, particularly for the purpose of PPS. A novel data-driven process is proposed to help mitigate the issues raised by prior researchers including the inconsistencies, ambiguities and multiple interpretations related to the taken-for-granted categories. The suggested approach is also expected to facilitate projects evaluation and prioritization within appropriate categories and contribute in PPS effectiveness.
Details