Customer Groups Research Articles

A-VRPD: Automating Drone-Based Last-Mile Delivery Using Self-Driving Cars

Drone-based last-mile delivery is an emerging technology that uses drones loaded onto a truck to deliver parcels to customers. In this paper, we introduce a fully automated system for drone-based last-mile delivery through incorporation of autonomous vehicles (AVs). A novel problem called the autonomous vehicle routing problem with drones (A-VRPD) is defined. A-VRPD is to select AVs from a pool of available AVs based on crowd sourcing, assign selected AVs to customer groups, and schedule routes for selected AVs to optimize the total operational cost. We formulate A-VRPD as a Mixed Integer Linear Program (MILP) and propose an optimization framework to solve the problem. A greedy algorithm is also developed to significantly improve the running time for large-scale delivery scenarios. Extensive simulations were conducted taking into account real-world operational costs for different types of AVs, traveled distances calculated considering the real-time traffic conditions using Google Map API, and varying load capacities of AVs. We evaluated the performance in comparison with two different state-of-the-art solutions: an algorithm designed to address the traditional vehicle routing problem with drones (VRP-D), which involves human-operated trucks working in tandem with drones to deliver parcels, and an algorithm for the two echelon vehicle routing problem (2E-VRP), wherein parcels are first transported to satellite locations and subsequently delivered from those satellites to the customers. The results indicate a substantial increase in profits for both the delivery company and vehicle owners compared with the state-of-the-art algorithms.

CUSTOMER SEGMENTATION IN SUPERMARKET USING CLUSTER ANALYSIS

The research aims to understand the types of customer groups shopping in supermarkets, the segmentation of customers is based on the variables which impact the decision-making of their preference towards supermarkets. Cluster analysis is performed on a primary dataset collected in the form of a questionnaire. The questionnaire consists of the variables that can influence customers' preference towards supermarkets. In total 86 respondents did participate in data collection. The analysis of the data was piloted with hierarchal cluster analysis followed by K- Means cluster analysis. The finding of the analysis suggests that the customers can be segmented into 3 groups. The decisions related to offers, programs, priorities, promotion, place and other activities can be planned according to the target segment and market need. Keywords: Cluster Analysis, Supermarket, Consumer preference.

The technology is not the problem, but the people

We actually in printing-industrie have almost everything we could wish for in terms of printing technology. We have the possibility to match the colours to a large extent beforehand and to print in such a quality that the customers are satisfied. Everything is actually there. The problem, however, is the complexity of the solutions. Suppliers suggest the exact opposite of complexity. The common programmes that are used to create the PDF files that are then sent to the printers for printing, initially give the impression of being child’s play to use. The graphic agencies, the largest group of customers of the printers, also think that everything is very simple. In the courses for graphic designers, printing technology is often not even taught as a separate subject. The idea prevails: “If the file looks good on the screen, my job is done!” That this is only about half the job, is known to anyone who has to rework PDF files in the graphic arts industry. And so we have the problem that from the outside everything in the printing industry is quite simple, almost trivial. But if we look more closely, the enormous choices in prepress and production, ultimately create an enormous complexity of all processes, that is difficult to oversee and deal with. Colour management, for example, requires very extensive knowledge. CIP3 cannot be mastered without in-depth IT knowledge. The temptation is to buy in the knowledge from suppliers. As a result, printers have equipment that has been set up once by suppliers and is then only to be operated in a comparatively mindless manner. The slightest error means that technicians have to be called in. This article examines the real problems in the day-to-day work of printers, in opposite to the problems that manufacturers tell us are a problem. It gives principled suggestions on what should be changed in training, it formulates questions that responsible people in the printing industry should ask themselves. And finally he gives practical advice on what could be done differently in concrete terms.

Impact of a corporate social responsibility message on consumers' sustainable behaviours and purchase intentions

AbstractThis study investigates the impact of a water brand's CSR message highlighting the brand's environmental concerns on brand‐related variables (attitude towards the brand and CSR) and consumer‐related variables (consumer efforts to adopt sustainable behaviours and well‐being). A research model is proposed, and the relationships postulated are tested on 414 French consumers. The study establishes the effectiveness of this kind of CSR messaging in influencing French consumers to purchase and recommend a particular brand. It then shows the direct and indirect ways in which a brand's CSR messaging can improve consumers' behavioural intentions (i.e., intentions to purchase the brand's products and to recommend the brand and/or its products). It also underscores that brand‐related variables contribute to increasing brands', and thus companies', business performance, whereas consumer‐related variables contribute to increasing their social performance. Finally, the REBUS‐PLS method emphasises the existence of several consumer groups and identifies the core target customer groups on which companies should focus their communication efforts.

RETRACTED ARTICLE: A Computational Model for Predicting Customer Behaviors Using Transformer Adapted with Tabular Features

The recent decade has seen an explosion in the e-commerce industry with the support of modern technologies (e.g., artificial intelligence) to maximize conversion rates. Many recommendation systems, therefore, have been developed to predict the customer behaviors to take appropriate actions. Customization of promotions or items for distinct groups of online customers considerably contributes to enhancing the sales. The purchasing records are essential information that can be used to investigate the customer behaviors. These kinds of information, however, are mainly expressed in tubular forms. Several computational models were developed using conventional machine learning algorithms to deal with that data type. However, these approaches struggle with large-volume and high-dimensional data, feature engineering, and high computational cost. In our study, we propose a deep learning model based on the Feature Tokenizer Transformer architecture to predict the customer purchasing intention. This novel architecture is a simplified adaptive version of the Transformer tabular data. The results demonstrated that our model showed better performance compared to conventional machine learning models. Furthermore, the model’s stability was also confirmed by the results of multiple repeated experiments.

An Optimal Operation Strategy of Regenerative Electric Heating Considering the Difference in User Thermal Comfort

Regenerative electric heating has gradually become one of the main forms of winter heating with the promotion of “coal to electricity” project. By fully exploiting its regulating capacity, it can effectively achieve a win–win situation of “peak shaving and valley filling” on the grid side and “demand response” on the customer side. In order to meet the different heating demands of users, a regenerative electric heating optimization and control strategy is proposed, taking into account the difference in users’ thermal comfort. Firstly, the reasons for the difference in user thermal comfort are analyzed, and the differentiated preference factors are calculated based on the maximum likelihood estimation method to design differentiated heating schemes. Then, a dynamic optimization and control model for regenerative electric heating with comfort and economic evaluation indicators is established and solved by using quantum genetic algorithm. Finally, a numerical example is used for simulation analysis. The research results show that the strategy proposed in this paper can take into account the comfort of customers and the economy of peaking and low load shifting, so that the operation of regenerative electric heating can respond to the different needs of different customer groups, and realize flexible adjustment at any time of the day.

Predicting Critical Factors Impacting Hotel Online Ratings: A Comparison of Religious and Commercial Destinations in Saudi Arabia

User-generated online ratings have become a prominent tool for hotels to enhance overall customer satisfaction. Prior research on online ratings has mainly considered commercial destinations, whereas research on religious destinations is limited. This study uses the IPA technique and beta regression analysis to investigate the destination’s (commercial and religious) varying effects on the relationship between hotel service quality attributes and customer satisfaction. In total, data from 338 hotels representing 82,704 customer reviews in two Saudi Arabian cities (Alkhobar and Makkah) were collected from Booking.com and analyzed. Makkah was selected as a key religious heritage destination, whereas Alkhobar was chosen as a commercial destination as it hosts major sea resorts, recreational parks, and shopping destinations. The results indicate that commercial and religious destination tourists do not have similar perceptions of the selected eight hotel service quality attributes. While comfort, facilities, and value-for-money service quality attributes were considered important for commercial destination tourists, religious destination tourists viewed location, cleanliness, and breakfast as important. Since effective management of customer satisfaction is essential for hotels’ profitability and sustainability, therefore it is imperative to identify and prioritize service quality attributes related to each group of customers. This will enable the efficient application of limited resources.

ANALISIS PENGARUH LAYANAN I-BANKING, M-BANKING, DAN FASILITAS ATM TERHADAP KEPUASAN NASABAH (STUDI KASUS NASABAH BANK BTN KCP TULUNGAGUNG)

The pattern of human’s behavior in using electronic services to acquire various kinds of information is affected by the rapid technological advancement. This is beneficial for, particularly banking, industries, as evidenced by the fact that banks nowadays come up with cutting-edge services such as internet banking and mobile banking. The sample of this quantitative descriptive research was selected using non-probability sampling, while the data was examined using factor analysis in SPSS version 15.0 of 2023. The result of the F test (simultaneous) is 56.554, which is greater than the F table of 2.699, and therefore H0 is rejected, and H1 is accepted. As the significance value of 0.000 is smaller than 0.05, internet banking, mobile banking, and ATM facilities simultaneously have a significant effect on the satisfaction of customers at the sub-branch office of Bank BTN in Tulungagung. Despite the positive and significant effect of the three variables, mobile banking is more preferable for some customer groups. In addition to its practicality, the service is helpful when they are in a difficult condition. In the future, the bank will develop a service where facilities in the internet banking will be integrated into its mobile banking application for greater customer benefit and ease

Research on the Influencing Factors of Consumer Buying Behavior

Today's businesses depend greatly on the buying habits of its customers. Understanding consumer behavior is essential for businesses to optimize their marketing strategies and boost customer satisfaction in today's fiercely competitive industry. This study examines customer personalities and their influence on purchasing behavior by using the purchase histories and demographic information of 2,240 clients. 10 research sources from Google Scholar are used to analyze the key factors that affect consumer behavior and the effectiveness of different clustering algorithms in identifying distinct customer groups in order to improve the accuracy of the study. The study emphasizes how important lifestyle, psychographic, and demographic characteristics are for affecting customer behavior. Businesses may better understand their clients and create marketing strategies that are tailored to their requirements by utilizing these characteristics. The work also raises the possibility of using clustering techniques to improve marketing efforts and increase client loyalty. Businesses may more effectively target their marketing efforts and boost customer satisfaction by categorizing customers into several categories based on their preferences and behavior patterns. As a result, this research offers insightful information about customer purchase habits. Businesses may better understand their clients and target their marketing initiatives to fit their demands by employing demographic and behavioral data. In doing so, companies may boost client pleasure and loyalty, eventually leading to long-term success.

Dynamics of user-generated content and service failure recovery: evidence from millennials

PurposeThere is considerable interest in the value of user-generated content (UGC) and its antecedents. Despite its growing importance, existing studies have largely ignored the effects of UGC on customers’ responses to recovery efforts in the fashion industry. The aim of this paper is to examine the extent to which UGC influences customers’ responses to providers’ service failure and recovery efforts, particularly how millennials’ interactions impact recovery efforts.Design/methodology/approachThe study uses a phenomenological hermeneutics and adopts theoretical sampling to collect empirical data from three European countries (France, Italy and the UK). The authors interviewed 60 millennials who had online service failure experiences in online fashion. This methodological framework was designed to illustrate the close relationships between subject and object as well as identify that data analysis and collection are undertaken in relation to consistent iterative interpretations in an evolving process of study. Drawing on multi-theoretical lenses, using actor–network and social influence theories, this study advances understanding through the development of a new conceptual model relating to individual characteristics.FindingsUsing actor–network theory and social influence theory, this study developed a conceptual model of four customer groups’ responses to service failure based on the severity of service failure and the level of customers’ online response following service failure.Originality/valueThe authors suggest some pragmatic implications of their conceptual model and explain how awareness of different customer groups can lead to effective decision-making for marketers. This study provides a set of practical insights that brand managers can use to recover service failures.

Solution Of Capacitated Vehicle Routing Problem For A Food Delivery Company With Heuristic Methods

A food delivery company operates in Balıkesir performs to the distribution for the products of a certain brand from the central warehouse to the customers located in the central districts of Altıeylül and Karesi by using two vehicles with high capacity. The company visits customers on certain routes to meet their daily demands and is able to meet all demands at the end of the day. In this study, the distribution of the company's products was considered as a Vehicle Routing Problem, and it was aimed to reconstruct the distribution routes of the vehicles with the help of various algorithms and to provide cost savings in terms of the distance traveled. In order to solve the problem, first of all, an appropriate capacity assumption was made for the vehicles by considering the daily demand amounts of the customers. Under this assumption, first new customer groups to be visited in daily periods were created, and then new routes were obtained for the relevant customer groups. In this process, the problem was designed as a Capacity Constrained Vehicle Routing Problem, and the results obtained using Fisher and Jaikumar's Algorithm and Clarke and Wright's Savings Algorithm were evaluated. When the results obtained are compared with the current route status of the company, it has been determined that it is possible to achieve a high rate of improvement by using the routes determined by algorithms.

Shopping Mall Customers Clustering Based on LOF and K-means++

Effective customer analysis is vital for business success, and AI-based customer analysis can significantly improve its accuracy, particularly regarding customer grouping and labeling, enabling merchants to generate personalized marketing strategies. Theories on machine learning models for grouping data have been developed since the 1950s, including logistic regression, Support Vector Machine (SVM), decision tree, and random forest; however, computational limitations hindered their practical application. Recent advances in computer technology have led to the development of more accessible machine learning algorithms that generate high-value results. The K-means clustering algorithm is one such model that best fits the customer labeling requirements. As an unsupervised training model, the K-means algorithm clusters customer data into a predetermined number of clusters. In this paper, we apply the K-means algorithm to separately cluster data on male and female clients, while using the K-means++ model to keep initial cluster centers as far apart as possible. We also apply the LOF algorithm to remove any outliers and modify the dataset accordingly.

Does Thinking and Working Politically improve support for social business? Evidence from a water business in Cambodia

AbstractMotivationSocial business is business that aims primarily to achieve social ends, while at least covering its costs. Social business has been put forward as a means to achieve development aims, such as the Sustainable Development Goals (SDGs). Thinking and Working Politically (TWP) is an approach to ensure development interventions are politically feasible and not stymied by political opposition. Are the two approaches compatible?PurposeThe article asks whether social business can ally with TWP for more effective development, taking a social business for water provision in Cambodia as a case in point.Methods and approachA review of development policy literature on social business and TWP is combined with data we collected from fieldwork in Cambodia from November 2018 to February 2019. We interviewed key informants from social business, UNICEF, and government in the capital. At two water kiosks in eastern Cambodia, one successful the other less so, we interviewed 2 kiosk operators, 20 customers, and local leaders; we held four focus groups of customers; and we observed operations at the kiosks. Data was analysed using an ethnographic, or immersive, qualitative approach.FindingsIn this case, UNICEF intuitively used TWP to connect a social business to government departments. Water kiosks depended heavily on local political dynamics. We found Commune officials mindful of their standing in local society who often had the interests of the local community in their hearts, but the compatibility of TWP and social business at the local project level is variable.Policy implicationsTWP can potentially help development actors supporting social business to make political connections, in this case to appropriate government departments and local official. The key, however, is to understand context. The danger is to view social business as a turnkey intervention that can be used without adaptation to context, without consideration of local politics. Donors supporting social business need to appraise each business, case by case.Donors might also want to consider the motivations of international companies partnering with social business, particularly when different development objectives might be in conflict.

Contrasting the drivers of Islamic bank adoption in Indonesia

This study aims to determine Indonesia's Islamic Bank Adoption drivers, especially in some customer groups. PLS-SEM is an analytical method used to test hypotheses. The analysis results show that the mediation type is partial mediation, but the mediation type for East Java customers and Generation Z is complete mediation. Based on the results, Islamic Banks must maintain their excellence to attract more customers. The sense of security in using Islamic Bank products and services is the primary indicator for East Java, generation Z, and non-generation Z customers. The reliability of Islamic Bank products and services is the primary indicator for non-East Java customers. Islamic Banks must also be able to build customer intentions to use Islamic Bank products and services, especially for Generation Z East Java customers. This study finds that intention needs to be built to increase the Adoption of Islamic banking products and services.

A combination of forensic-based investigation algorithm and density peak-based fuzzy clustering for custom segmentation

Custom segmentation is a process of classifying potential customers based on their mutual features such as shopping habits, consumption trends, and demand to provide an effective marketing campaign for each customer group. Data clustering is one of the most common methods for custom segmentation. This study proposed a novel clustering method that employs density peak-based fuzzy c-means (DP-FCM) and forensic-based investigation (FBI) algorithms. The proposed method (denoted as DP-FBI-FCM) aims to provide an effective clustering technique that can exploit the global optimal solution for custom segmentation problems. Besides, the proposed DP-FBI-FCM is used to segment wholesale customer data of a supermarket. As a result, four distinct customer groups are classified. Businesses can implement different strategies in each cluster to retain and attract their customers.

Promoting customer loyalty through e-marketing communication at commercial banks

Purpose: The research aims to find out the relationship between e-marketing communication, customer satisfaction, and loyalty at Vietnamese commercial banks.
 Design/Methodology/Approach: Customers who use e-banking services in Ho Chi Minh City are surveyed to gather the data. Using Google Forms, the survey was first pretested on 10 people. There were 224 valid responses to the official survey. Following that, SmartPLS processed the data in two steps: evaluating the measurement model and the structural model.
 Findings: The results show that e-marketing communication has a positive relationship with customer satisfaction and loyalty. Besides, customer satisfaction mediates a positive relationship between e-marketing communication and customer loyalty.
 Conclusion: The outstanding advancement of information technology has facilitated digital transformation in all aspects of life, including the banking industry. As technology advanced, marketing was the industry that underwent the most change. E-marketing makes it possible to establish and maintain a close relationship with clients, which is essential for being successful in luring them. E-marketing must connect many people, particularly the target customer group, and is not just focused on the design, logo, and overall user interface.
 Research Limitations and Implications: The effectiveness of direct marketing is not combined or compared in this study. It only examines the effect of e-marketing.
 Practical Implications: The banks should identify, contact, and maintain regular contact with potential customers. They can incorporate unstructured data from social networks. Furthermore, the banks must develop methods for evaluating and measuring the efficacy of their marketing efforts. This study gives bank managers in Vietnam suggestions for an appropriate e-marketing strategy.

A dynamic predictive maintenance approach using probabilistic deep learning for a fleet of multi-component systems

Empowered by the ubiquitous sensing infrastructure, predictive maintenance (PdM) has received increasing attention. However, designing predictive maintenance for multiple systems remains a challenging problem as it requires effective integration of the prediction and scheduling under uncertainty and constraints. This paper proposes a dynamic PdM approach for a fleet of multi-component systems, which integrates deep learning-based (DL-based) probabilistic remaining useful life (RUL) prognostics into maintenance planning. First, a DL-based framework is designed for obtaining predictive distributions of RULs, and a probabilistic gated recurrent unit model is proposed for time series data. The Gaussian distribution is used to model prediction uncertainties, and the negative log-likelihood loss is used for model training, which inclines to emphasize the late degradation period. Then, an integer program is established and embedded in a rolling horizon approach for maintenance optimization. The concept of wasted residual values is proposed to quantify the impact of early retirement of components on total costs, which enables customized group maintenance planning under different cost settings. The applicability of the overall approach is illustrated for a fleet of aircraft based on a practical dataset. The experimental results show that our approach can provide accurate RUL prognostics and schedule maintenance flexibly to reduce costs.

Dynamic Interaction and Visualization Design of Database Information Based on Artificial Intelligence

With the explosive growth of data, people's demand for data analysis has become more intense. Although modern technology can collect a large amount of data, the collected original data is often useless and contains little information. How to extract useful information from massive amounts of data has become an urgent problem. Driven by artificial intelligence (AI) technology and personalized consumption demand of users, this article puts forward a dynamic interactive and visualization algorithm of e-business database information based on an improved collaborative filtering (CF) algorithm to help enterprises more efficiently mine the required potential customer groups from massive customer data and log data. Experiment results prove the effectiveness of the model and algorithm. Data mining (DM) technology is applied to the user access control model in this model. First, the maximum forward reference sequence of mobile e-business groups is mined by data technology. Then a user access control model is established according to this sequence to control user access so enterprises can formulate reasonable marketing strategies based on this knowledge.

Perceptions about FinTech: New evidences from the Middle East

The study aimed to analyze the perceptions of FinTech in the Middle East region, specifically its usage, and performance. To attain this objective, a strategy employed on surveys as the primary data acquisition method was implemented. The survey was conducted between November 2021 and February 2022, which allowed the researcher to gather comprehensive data from respondents during this period. In order to ensure the descriptive nature of the study, cross-sectional research was employed in its design. This design allowed the researcher to gather data at a single point in time, which was appropriate for the scope of this study. The researcher utilized a questionnaire during the inquiry to elicit information for data collection purposes. The questionnaire was designed to include semi-structured questions, which allowed the respondents to provide detailed information on their perceptions of FinTech. This study employed a survey-based technique to analyze the perceptions of FinTech in the Middle East region. Using a cross-sectional design and semi-structured questions allowed the researcher to achieve the descriptive nature of the research. Additionally, cross-tab analysis and SPSS provided an in-depth understanding of the data collected. The findings from the analysis suggest that FinTech enhances the performance of financial institutions and that digital banking is the best feature of FinTech across all customer groups.

Sustainable investment initiatives and the performance of stakeholders involved in multinational technology companies' supply chains: linear or nonlinear effects?

PurposeThis study aims to examine how environmental, social and governance (ESG) initiatives and ISO 14001, which is an internationally agreed standard to set out the requirements for an environmental management system, affect firm performance in the context of the Industry 4.0 supply chain.Design/methodology/approachThe authors develop a new chance-constrained network data envelopment analysis (DEA) in the presence of non-positive data to estimate innovation, operational and profitability performances for three main relation groups (suppliers, partners and customers) in Microsoft's supply chain.FindingsResults of this study show the following: (1) the application of ISO 14001 will reduce profitability but increase overall performance (OP); (2) ESG implementation has a convex U-shaped influence on profitability and OP, which means that firms will benefit when ESG investment goes beyond a particular level; (3) the nonlinear U-shape is presented in the E and G components, but not in the S of the individual ESG initiatives, and (4) only specific subcomponents of S and G in the subcomponent of individual ESG initiatives are nonlinearly connected to OP. Research's results reveal that the customer group has a higher performance value than the other two groups, which suggests that this group will create competitive advantages for Microsoft.Originality/valueOverall, the authors provide an insightful viewpoint into supply chain management by examining the ESG initiatives, ISO 14001 and performances of Microsoft's supply chain.