Search results

This study aims to predict customer churn in resort hotels by calculating the churn probability of repeat customers for future stays in the same hotel brand.

Based on the recency, frequency, monetary (RFM) paradigm, random forest and logistic regression supervised machine learning algorithms were used to predict churn behavior. The model with superior performance was used to detect potential churners and generate a priority matrix.

The random forest algorithm showed a higher prediction performance with an 80% accuracy rate. The most important variables were RFM-based, followed by hotel sector-specific variables such as market, season, accompaniers and booker. Some managerial strategies were proposed to retain future churners, clustered as “hesitant,” “economy,” “alternative seeker,” and “opportunity chaser” customer groups.

This study contributes to the theoretical understanding of customer behavior in the hospitality industry and provides valuable insight for hotel practitioners by demonstrating the methods that facilitate the identification of potential churners and their characteristics.

Most customer retention studies in hospitality either concentrate on the antecedents of retention or customers’ revisit intentions using traditional methods. Taking a unique place within the literature, this study conducts churn prediction analysis for repeat hotel customers by opening a new area for inquiry in hospitality studies.

The present study aims to investigate the relationship between institutional influence and performance, mediated through transformational leadership (TL) and moderated by barriers, situational factors, communication and implementation.

Using a structured survey instrument, data were collected from 370 faculty members from 31 higher educational institutions in southern India. After checking the psychometric properties of the instrument, the authors used Hayes’s PROCESS to test the direct hypotheses and three-way interactions.

The results revealed that TL mediated the relationship between institutional influence and performance. Further, the findings supported the three-way interactions between (1) institutional influence, barriers and communication positively affecting TL; and (2) TL, situational factors and implementation affecting the performance of faculty members.

This study underscores the importance of TL for the smooth functioning of higher educational institutions and achieving superior performance, especially in the new normal context after the global pandemic.

This study makes several significant recommendations to administrators in higher educational institutions, in addition to contributing to the vast literature on TL. The study suggests that administrators must invest resources in developing TL skills so that employees reach their fullest potential and contribute to achieving organizational goals. In addition, leaders in organizations need to exercise a transformational style to combat the new normal post-pandemic academic environment.

This study provides new insights into the importance of TL style and institutional influence to enhance performance. To the best of our knowledge, the conceptual model developed and tested the first of its kind in India, significantly contributing to theory and practice.

While travelling, tourists like to use mobile technology to share their travel experiences. This study aims to understand how the social value gained by tourists from sharing a travel experience with mobile technology affects their satisfaction with the travel experience through onsite mobile sharing behaviour.

A second-order hierarchical model is constructed to examine the moderated mediating role of onsite mobile sharing behaviour in improving tourists’ travel satisfaction. Through systematic sampling, 304 responses were collected at ten attraction points in Guangzhou and Shenzhen, China.

The results show that, compared with self-centred values (self-presentation and self-identification), other-centred values (building social connection and reciprocity) contribute more to forming social values of sharing. In addition, onsite mobile sharing behaviour partially mediates and moderates the effect of social values on travel satisfaction.

This study applies the social capital theory to identify the value gained by sharing travel experiences and empirically evaluates the impact of these values on the overall value of sharing travel experiences. This study also contributes to tourism research by examining the moderated mediating role of onsite mobile sharing behaviour in improving travel satisfaction. This study helps destination marketing to make strategies to motivate tourists to use mobile technology to share their travel experiences while travelling.

Studies have shown that customer orientation has a substantial impact on a business's success. This study examines the effects of positive personality on salespeople's proactive customer orientation (PCO) and responsive customer orientation (RCO) by incorporating the effects of job enthusiasm and transformational leadership.

A questionnaire survey is conducted. A total of 511 questionnaires are received from Taiwan's life insurance salespeople. Partial least squares (PLS) regression is used to test the hypotheses.

The results show that positive personality influences PCO and RCO both directly and indirectly through job enthusiasm. The effect of transformational leadership is also found to be significant. Financial service companies should be concerned about the important role of positive personality and transformational leadership in promoting job enthusiasm, PCO and RCO among salespeople.

Previous studies mostly focused on the direct relationship between customer orientation and organizational outcomes, neglecting the role of individual personality. This gap leaves us wondering how a positive personality influences a salesperson's proactive and responsive customer orientation. To the authors' knowledge, this is the first study to examine the mechanisms of a positive personality, job enthusiasm, and transformational leadership on salespeople's PCO and RCO.

The paper aims to tackle the classification of Remote Sensing Images (RSIs), which presents a significant challenge for computer algorithms due to the inherent characteristics of clustered ground objects and noisy backgrounds. Recent research typically leverages larger volume models to achieve advanced performance. However, the operating environments of remote sensing commonly cannot provide unconstrained computational and storage resources. It requires lightweight algorithms with exceptional generalization capabilities.

This study introduces an efficient knowledge distillation (KD) method to build a lightweight yet precise convolutional neural network (CNN) classifier. This method also aims to substantially decrease the training time expenses commonly linked with traditional KD techniques. This approach entails extensive alterations to both the model training framework and the distillation process, each tailored to the unique characteristics of RSIs. In particular, this study establishes a robust ensemble teacher by independently training two CNN models using a customized, efficient training algorithm. Following this, this study modifies a KD loss function to mitigate the suppression of non-target category predictions, which are essential for capturing the inter- and intra-similarity of RSIs.

This study validated the student model, termed KD-enhanced network (KDE-Net), obtained through the KD process on three benchmark RSI data sets. The KDE-Net surpasses 42 other state-of-the-art methods in the literature published from 2020 to 2023. Compared to the top-ranked method’s performance on the challenging NWPU45 data set, KDE-Net demonstrated a noticeable 0.4% increase in overall accuracy with a significant 88% reduction in parameters. Meanwhile, this study’s reformed KD framework significantly enhances the knowledge transfer speed by at least three times.

This study illustrates that the logit-based KD technique can effectively develop lightweight CNN classifiers for RSI classification without substantial sacrifices in computation and storage costs. Compared to neural architecture search or other methods aiming to provide lightweight solutions, this study’s KDE-Net, based on the inherent characteristics of RSIs, is currently more efficient in constructing accurate yet lightweight classifiers for RSI classification.

The Internet has changed consumer decision-making and influenced business behaviour. User-generated product information is abundant and readily available. This paper argues that user-generated content can be efficiently utilised for business intelligence using data science and develops an approach to demonstrate the methods and benefits of the different techniques.

Using Python Selenium, Beautiful Soup and various text mining approaches in R to access, retrieve and analyse user-generated content, we argue that (1) companies can extract information about the product attributes that matter most to consumers and (2) user-generated reviews enable the use of text mining results in combination with other demographic and statistical information (e.g. ratings) as an efficient input for competitive analysis.

The paper shows that combining different types of data (textual and numerical data) and applying and combining different methods can provide organisations with important business information and improve business performance.

The paper shows that combining different types of data (textual and numerical data) and applying and combining different methods can provide organisations with important business information and improve business performance.

The study makes several contributions to the marketing and management literature, mainly by illustrating the methodological advantages of text mining and accompanying statistical analysis, the different types of distilled information and their use in decision-making.

During the past few years, social media has faced the challenge of maintaining its user base. Reports show that the social media giants such as Facebook and Twitter experienced a decline in their users. Taking WhatsApp's recent change of its terms of use as the case of this study and using the push-pull-mooring model and a configurational perspective, this study aims to identify pathways for switching intentions.

Data were collected from 624 WhatsApp users recruited from Amazon Mechanical Turk and analyzed using fuzzy set qualitative comparative analysis (fsQCA).

The findings identify seven configurations for high switching intentions and four configurations for low intentions to switch. Firm reputation and critical mass increase intention to switch, while low firm reputation and absence of attractive alternatives hinder switching.

This study extends extant literature on social media migration by identifying configurations that result in high and low switching intention among messaging applications.

The study identifies factors the technology service providers should consider to attract new users and retain existing users.

This study complements the extant literature on switching intention that explains the phenomenon based on a net-effect approach by offering an alternative view that focuses on the existence of multiple pathways to social media switching. It further advances the authors’ understanding of the relevant importance of switching factors.

Sharing patient health information (PHI) among hospitals has been much slower than the adoption of health record systems. This paper aims to investigate if privacy regulation (PR) or security measures (SMs) influence hospitals’ use of health information exchange (HIE) to share PHI with other providers (e.g. physicians, labs, hospitals). The study specifically focuses on how multiple PRs can impede and a strong national security infrastructure (NSI) can support HIE.

The study uses secondary data from a multi-national and multi-hospital survey administered by the European Union. The multi-level structure of the cross-sectional panel data is used to test the influence of both hospital-level (e.g. PR) and national-level variables (e.g. NSI) on HIE. A total of nine types of HIE, three types of PRs, nine SMs and other relevant control variables are considered. This study uses a two-level random intercept generalized linear model to test the hypothesis proposed in the study.

The study finds that national-level PRs (NLPR) have the strongest positive influence on HIE in comparison to regional (RLPR) and hospital-level (HLPR) PRs. Moreover, the study finds evidence that the presence of RLPR and HLPR, on average, decreases the positive impact of NLPR by 264%. The SMs also have a significant and positive impact on HIE. Adoption of an additional SM can increase the odds of engaging in a certain type of HIE between 21% and 61%. On the other hand, a strong NSI can also amplify the positive impact of SM on certain types of HIE.

This study extends prior research on the role of PRs in enabling HIE by considering the complexities brought up by adopting multiple PRs. NLPRs have the strongest impact on HIE in comparison to RLPRs or HLPRs. Moreover, public infrastructure initiatives such as those related to secure communications can also complement SMs adopted by the providers by encouraging HIE.

Although digital content marketing (DCM) research and industry-wide expenditure is growing very rapidly owing to the positive outcomes associated with this new pull marketing strategy, research has not completely mapped how DCM activities can be optimized in the social media brand community context. This paper seeks to understand how social media DCM activities can be optimized to achieve greater relational and monetary outcomes for different products.

A structural equation modeling procedure was used to analyze 416 survey responses obtained from members of Facebook brand communities in South Africa.

The results reveal that social media DCM consumption motives exert significant differential effects on both relational and monetary marketing outcomes in search and experience product contexts while also demonstrating the mechanism through which social media DCM consumption motives lead to contributing social media engagement behaviors.

The study findings call for the need for firms to understand the motives that drive the consumption of DCM in social media brand communities. Specifically, marketers of search products should deploy more of hedonic contents such as images while simultaneously keeping highly textual DCM to a minimum in Facebook brand communities as this works better for experience products. Finally, more authentic SM-DCM activities that effectively address the authenticity SM-DCM consumption motive can result from the DCM activities of social media opinion leaders and genuine consumer–brand interactions in the context of Facebook brand communities.

This paper broke new grounds in three unique directions in terms of: (1) the relative salience of SM-DCM consumption motives in enhancing WTP and different aspects of SMBE; (2) the contextual influence of product type on SM-DCM activities optimization and (3) the mechanisms that underlie the effects of SM-DCM consumption motives on contributing SMBE in the Facebook brand community context.

Surface acoustic wave (SAW) sensors have attracted great attention worldwide for a variety of applications in measuring physical, chemical and biological parameters. However, stability has been one of the key issues which have limited their effective commercial applications. To fully understand this challenge of operation stability, this paper aims to systematically review mechanisms, stability issues and future challenges of SAW sensors for various applications.

This review paper starts with different types of SAWs, advantages and disadvantages of different types of SAW sensors and then the stability issues of SAW sensors. Subsequently, recent efforts made by researchers for improving working stability of SAW sensors are reviewed. Finally, it discusses the existing challenges and future prospects of SAW sensors in the rapidly growing Internet of Things-enabled application market.

A large number of scientific articles related to SAW technologies were found, and a number of opportunities for future researchers were identified. Over the past 20 years, SAW-related research has gained a growing interest of researchers. SAW sensors have attracted more and more researchers worldwide over the years, but the research topics of SAW sensor stability only own an extremely poor percentage in the total researc topics of SAWs or SAW sensors.

Although SAW sensors have been attracting researchers worldwide for decades, researchers mainly focused on the new materials and design strategies for SAW sensors to achieve good sensitivity and selectivity, and little work can be found on the stability issues of SAW sensors, which are so important for SAW sensor industries and one of the key factors to be mature products. Therefore, this paper systematically reviewed the SAW sensors from their fundamental mechanisms to stability issues and indicated their future challenges for various applications.