Search results

Although risk culture is a key determinant for an effective risk management, identifying the risk culture of a firm can be challenging due to the abstract concept of culture. This paper proposes a novel approach that uses unsupervised machine learning techniques to identify significant features needed to assess and differentiate between different forms of risk culture.

To convert the unstructured text in our sample of banks' 10K reports into structured data, a two-dimensional dictionary for text mining is built to capture risk culture characteristics and the bank's attitude towards the risk culture characteristics. A principal component analysis (PCA) reduction technique is applied to extract the significant features that define risk culture, before using a K-means unsupervised learning to cluster the reports into distinct risk culture groups.

The PCA identifies uncertainty, litigious and constraining sentiments among risk culture features to be significant in defining the risk culture of banks. Cluster analysis on the PCA factors proposes three distinct risk culture clusters: good, fair and poor. Consistent with regulatory expectations, a good or fair risk culture in banks is characterized by high profitability ratios, bank stability, lower default risk and good governance.

The relationship between culture and risk management can be difficult to study given that it is hard to measure culture from traditional data sources that are messy and diverse. This study offers a better understanding of risk culture using an unsupervised machine learning approach.

The target of this research is to develop a mathematical model which combines the Resource-Constrained Multi-Project Scheduling Problem (RCMPSP) and the Multi-Skilled Resource-Constrained Project Scheduling Problem (MSRCPSP). Due to the importance of resource management, the proposed formulation comprises resource leveling considerations as well. The model aims to simultaneously optimize: (1) the total time to accomplish all projects and (2) the total deviation of resource consumptions from the uniform utilization levels.

The K-Means (KM) and Fuzzy C-Means (FCM) clustering methods have been separately applied to discover the clusters of activities which have the most similar resource demands. The discovered clusters are given to the scheduling process as priori knowledge. Consequently, the execution times of the activities with the most common resource requests will not overlap. The intricacy of the problem led us to incorporate the KM and FCM techniques into a meta-heuristic called the Bi-objective Symbiosis Organisms Search (BSOS) algorithm so that the real-life samples of this problem could be solved. Therefore, two clustering-based algorithms, namely, the BSOS-KM and BSOS-FCM have been developed.

Comparisons between the BSOS-KM, BSOS-FCM and the BSOS method without any clustering approach show that the clustering techniques could enhance the optimization process. Another hybrid clustering-based methodology called the NSGA-II-SPE has been added to the comparisons to evaluate the developed resource leveling framework.

The practical importance of the model and the clustering-based algorithms have been demonstrated in planning several construction projects, where multiple water supply systems are concurrently constructed.

Reviewing the literature revealed that there was a need for a hybrid formulation that embraces the characteristics of the RCMPSP and MSRCPSP with resource leveling considerations. Moreover, the application of clustering algorithms as resource leveling techniques was not studied sufficiently in the literature.

In this study, supervision and control of the possible problems among people over a large area with a limited number of drone cameras and security staff is established.

These drones, namely unmanned aerial vehicles (UAVs) will be adaptively and automatically distributed over the crowds to control and track the communities by the proposed system. Since crowds are mobile, the design of the drone clusters will be simultaneously re-organized according to densities and distributions of people. An adaptive and dynamic distribution and routing mechanism of UAV fleets for crowds is implemented to control a specific given region. The nine popular clustering algorithms have been used and tested in the presented mechanism to gain better performance.

The nine popular clustering algorithms have been used and tested in the presented mechanism to gain better performance. An outperformed clustering performance from the aggregated model has been received when compared with a singular clustering method over five different test cases about crowds of human distributions. This study has three basic components. The first one is to divide the human crowds into clusters. The second one is to determine an optimum route of UAVs over clusters. The last one is to direct the most appropriate security personnel to the events that occurred.

This study has three basic components. The first one is to divide the human crowds into clusters. The second one is to determine an optimum route of UAVs over clusters. The last one is to direct the most appropriate security personnel to the events that occurred.

For a better understanding of the preferences and differences of young consumers in emerging wine markets, this study aims to propose a clustering method to segment the super-new generation wine consumers based on their sensitivity to wine brand, origin and price and then conduct user profiles for segmented consumer groups from the perspectives of demographic attributes, eating habits and wine sensory attribute preferences.

We first proposed a consumer clustering perspective based on their sensitivity to wine brand, origin and price and then conducted an adaptive density peak and label propagation layer-by-layer (ADPLP) clustering algorithm to segment consumers, which improved the issues of wrong centers' selection and inaccurate classification of remaining sample points for traditional DPC (DPeak clustering algorithm). Then, we built a consumer profile system from the perspectives of demographic attributes, eating habits and wine sensory attribute preferences for segmented consumer groups.

In this study, 10 typical public datasets and 6 basic test algorithms are used to evaluate the proposed method, and the results showed that the ADPLP algorithm was optimal or suboptimal on 10 datasets with accuracy above 0.78. The average improvement in accuracy over the base DPC algorithm is 0.184. As an outcome of the wine consumer profiles, sensitive consumers prefer wines with medium prices of 100–400 CNY and more personalized brands and origins, while casual consumers are fond of popular brands, popular origins and low prices within 50 CNY. The wine sensory attributes preferred by super-new generation consumers are red, semi-dry, semi-sweet, still, fresh tasting, fruity, floral and low acid.

Young Chinese consumers are the main driver of wine consumption in the future. This paper provides a tool for decision-makers and marketers to identify the preferences of young consumers quickly which is meaningful and helpful for wine marketing.

In this study, the ADPLP algorithm was introduced for the first time. Subsequently, the user profile label system was constructed for segmented consumers to highlight their characteristics and demand partiality from three aspects: demographic characteristics, consumers' eating habits and consumers' preferences for wine attributes. Moreover, the ADPLP algorithm can be considered for user profiles on other alcoholic products.

This study aims to validate a model to assess the level of lean maturity of Brazilian hospitals based on the adaptation of the SAE J4000/2021 standard.

The methodology was divided: (1) adaptation of the standard to the health context, (2) application of the questionnaire through a survey, and (3) comparison of the results of the level of maturity in the standard and by the clustering technique, using Minitab.

The research presents two contributions: (1) validation of a model to assess the level of lean maturity based on the SAE J4000/2021; (2) insights into the level of maturity of Brazilian hospitals. It was observed that only 10% of the sample was classified at maturity level 3 and 75% at level 2. Private and large hospitals showed greater maturity compared to the others.

This includes the limited number of hospitals that participated in the survey, given the difficulty of adherence to due constraints of time and staffing from hospitals, during the COVID-19 pandemic.

This article presents a lean maturity assessment proposal, adapting a consolidated standard in the automobile industry to the health context. Insights on the lean maturity of Brazilian hospitals can contribute to the development of policies to encourage the implementation of the lean philosophy directed to each specific environment.

This study serves as a guide for public agents interested in monitoring the quality of hospital indicators through the SAE J4000/2021 standard. From this lean maturity analysis, hospital managers can understand their opportunities for improvement in both human and organizational aspects. This favors the improvement of service delivery to society that depends on health services.

Due to the lack of research that validates lean maturity level assessment models in Brazilian hospitals, this study can be considered a pioneer in this Brazilian research by validating the SAE J4000/2021 standard in its updated version in the health context.

The COVID-19 pandemic has posed many challenges in almost all sectors around the globe. Because of the pandemic, government entities responsible for managing health-care resources face challenges in managing and distributing their limited and valuable health resources. In addition, severe outbreaks may occur in a small or large geographical area. Therefore, county-level preparation is crucial for officials and organizations who manage such disease outbreaks. However, most COVID-19-related research projects have focused on either state- or country-level. Only a few studies have considered county-level preparations, such as identifying high-risk counties of a particular state to fight against the COVID-19 pandemic. Therefore, the purpose of this research is to prioritize counties in a state based on their COVID-19-related risks to manage the COVID outbreak effectively.

In this research, the authors use a systematic hybrid approach that uses a clustering technique to group counties that share similar COVID conditions and use a multi-criteria decision-making approach – the analytic hierarchy process – to rank clusters with respect to the severity of the pandemic. The clustering was performed using two methods, k-means and fuzzy c-means, but only one of them was used at a time during the experiment.

The results of this study indicate that the proposed approach can effectively identify and rank the most vulnerable counties in a particular state. Hence, state health resources managing entities can identify counties in desperate need of more attention before they allocate their resources and better prepare those counties before another surge.

To the best of the authors’ knowledge, this study is the first to use both an unsupervised learning approach and the analytic hierarchy process to identify and rank state counties in accordance with the severity of COVID-19.

The hospitality industry values segmentation and loyalty programs (LPs), but there is limited research on new methods for segmenting loyalty program members, so managers often rely on conventional techniques. This study aims to use big data-driven segmentation methods to cluster customers and provide a new solution for customer segmentation in hotel LPs.

Using the k-means algorithm, this study examined 498,655 profiles of guests enrolled in a multinational hotel chain’s loyalty program. The objective was to cluster guests according to their consumption behavior and monetary value and compare data-driven segments based on brand preferences, demographic data and monetary value with loyalty program tiers.

This study shows that current tier-based LPs lack features to improve customer segmentation, and some high-tier members generate less revenue than low-tier members. Therefore, more attention should be given to truly valuable customers.

Hotels can segment LP members to develop targeted campaigns and uncover new insights. This will help to transform LPs to make them more valuable and profitable and use differentiated rewards and strategies.

As not all guests or hotel brands benefit equally from LPs, additional segmentation is required to suit varying guest behaviors. Hotel managers can use data mining techniques to develop more efficient and valuable LPs with personalized strategies and rewards.

This paper defines and assesses student learning patterns under the influence of problem-based learning (PBL) and their classification into a reasonable minimum number of classes. Study utilizes PBL implemented in an undergraduate Statistics and Operations Research course for techno-management students at a private university in India.

Study employs an in situ experiment using a conceptual model based on learning theory. The participant's end-of-semester GPA is Performance Indicator. Integrating PBL with classroom teaching is unique instructional approach to this study. An unsupervised and supervised data mining approach to analyse PBL impact establishes research conclusions.

The administration of PBL results in improved learning patterns (above-average) for students with medium attendance. PBL, Gender, Math background, Board and discipline are contributing factors to students' performance in the decision tree. PBL benefits a student of any gender with lower attendance.

This study is limited to course students from one institute and does not consider external factors.

Researchers can apply learning patterns obtained in this paper highlighting PBL impact to study effect of every innovative pedagogical study. Classification of students based on learning behaviours can help facilitators plan remedial actions.

1. Clustering is used to extract student learning patterns considering dynamics of student performances over time. Then decision tree is utilized to elicit a simple process of classifying students. 2. Data mining approach overcomes limitations of statistical techniques to provide knowledge impact in presence of demographic characteristics and student attendance.

This research aims to comprehend the factors that impact the emerging inclination of consumers toward mobile finance technology (fintech) services over banking institutions. The study focuses on users' demographics and psychographics to delineate their unique segments and profiles.

The study proposes a segmentation and profiling framework that includes variance analysis, two-step cluster analysis and pairwise statistical tests. This framework is applied to a dataset of customers using a range of mobile fintech services, specifically robo-investment, peer-to-peer (P2P) payments, robo-advisory and digital savings. The analysis creates distinct customer profile clusters, which are later validated using pairwise statistical tests based on segmentation output.

Empirical results reveal that P2P payment service users exhibit a higher frequency of usage, proficiency and intention to continue using the service compared to users of robo-investment or digital savings platforms. In contrast, individuals utilizing robo-advisory services are identified to have a significantly greater familiarity and intention to sustain engagement with the service compared to digital savings users.

The findings provide financial institutions, especially traditional banks with actionable insights into their customer base. This information enables them to identify specific customer needs and preferences, thereby allowing them to tailor products and services accordingly. Ultimately, this understanding may strategically position traditional banks to maintain competitiveness amidst the increasing prominence of fintech enterprises.

This research provides an in-depth examination of customer segments and profiles within the mobile fintech services sphere, thus giving a nuanced understanding of customer behavior and preferences and generating practical recommendations for banks and other financial institutions. This study thereby sets the stage for further research and paves the way for developing personalized products and services in the evolving fintech landscape.

The purpose of this paper is to examine the existence and profile consumer segments based on dissonance in Indian apparel fashion retail market.

This study is based on cognitive dissonance theory (CDT) and analyses data using cluster and discriminant analysis on a sample (n = 354) from India.

The findings revealed three dissonance segments among consumers based on the intensity of dissonance experienced. This study also validated the clusters and profiled each segment. In doing so, the three clusters exhibited unique differences with respect to purchase and socio-demographic characteristics. Moreover, high dissonance segments were found to inversely impact customer’s satisfaction, loyalty and overall perceived value and positively impact tendency to switch.

Understanding the existence of cognitive dissonance (CD) patterns among consumers is critical for fashion apparel retailers. This paper offers unique insights into the specialties of each dissonance segment that assists the marketers to frame appropriate strategies to target them.

This paper advances knowledge on consumer behavior by highlighting the significance of CD.