Understanding machine learning-based forecasting methods: A decomposition framework and research opportunities

Machine learning (ML) methods are gaining popularity in the forecasting field, as they have shown strong empirical performance in the recent M4 and M5 competitions, as well as in several Kaggle competitions. However, understanding why and how these methods work well for forecasting is still at a very early stage, partly due to their complexity. In this paper, I present a framework for regression-based ML that provides researchers with a common language and abstraction to aid in their study. To demonstrate the utility of the framework, I show how it can be used to map and compare ML methods used in the M5 Uncertainty competition. I then describe how the framework can be used together with ablation testing to systematically study their performance. Lastly, I use the framework to provide an overview of the solution space in regression-based ML forecasting, identifying areas for further research.     

Exploring the representativeness of the M5 competition data

The main objective of the M5 competition, which focused on forecasting the hierarchical unit sales of Walmart, was to evaluate the accuracy and uncertainty of forecasting methods in the field to identify best practices and highlight their practical implications. However, can the findings of the M5 competition be generalized and exploited by retail firms to better support their decisions and operation? This depends on the extent to which M5 data is sufficiently similar to unit sales data of retailers operating in different regions selling different product types and considering different marketing strategies. To answer this question, we analyze the characteristics of the M5 time series and compare them with those of two grocery retailers, namely Corporación Favorita and a major Greek supermarket chain, using feature spaces. Our results suggest only minor discrepancies between the examined data sets, supporting the representativeness of the M5 data.     

Metaverse as a disruptive technology revolutionising tourism management and marketing

Metaverse is the next disruptive technology that will impact society in the coming decades, by enabling immersive experiences in both virtual and physical environments. Although still conceptual, Metaverse converges the physical and digital universe, allowing users to seamlessly traverse between them. Digital immersion offers opportunities for people to travel in time, supporting users to experience virtually ancient encounters, space explorations or dangerous natural phenomena, such as volcano eruptions. Users can explore immersive environments for working, learning, transacting, exploring interests and socialising with others. This is already evident in gaming ecosystems, where gamers effectively interact in the metaverse. Although still experimental, Metaverse is expected to revolutionize travel and tourism management and marketing. It empowers destination awareness, positioning and branding, as well as coordination and management, through digital twins. Metaverse provides opportunities to support trip planning, interaction and engagement, effectively transforming consumer behaviour. Visiting and engaging with destinations virtually is expected to motivate real travel, rather than replace it. This paper provides a vision of how Metaverse can revolutionize tourism experiences and transform tourism management and marketing. Drawing on a systematic review of scholarly works, articles from media and industry reports, this study defines and conceptualizes the Metaverse ecosystem for tourism and travel. It explores the foundations of the disruptions that Metaverse brings to tourism destinations and organisations and identifies the building blocks of Metaverse tourism. The study outlines research directions so that the tourism industry can take full advantage of the Metaverse capabilities and opportunities emerging as well as identify challenges for the future.     

The impact of influencers' multi-SNS use on followers’ behavioral intentions: An integration of cue consistency theory and social identity theory

The considerable marketing potential brought by the rapid growth of social media has been extensively examined in the literature, particularly in terms of the impact of influencers' recommendations on their followers' decisions. However, little attention has been given to how the individual influencers' use of multiple social networking sites affects their followers' behavioral intentions. Hence, this academic gap warrants further exploration. Drawing on cue consistency theory, social identity theory, and stimulus-organism-response framework, this research proposes three research questions and constructs an integrated research model to explore how the influencers' cue consistency affects the social identification of their followers, subsequently influencing their behavioral intentions. A structural equation modeling technique is performed to analyze the data of 510 valid respondents. The findings show that influencers' consistent cues (i.e., information and image consistency) across social media have positive impacts on followers' cognitive and affective identification toward the influencers. Furthermore, the determinants for followers' purchase intention and electronic word-of-mouth intention are affirmed to serve as both cognitive and affective identification. Especially, the results indicate that the relationships between followers’ social identifications and behavioral intentions are moderated by the type of influencer (i.e., lifestyle vs. review). Accordingly, the results indicate how the use of multiple social networking sites by influencers impacts the behavioral intentions of their followers. The findings offer new insights into influencer marketing and provide important lessons for marketers.     

Direct intervention or indirect support? The effects of cooperative control measures on farmers’ implementation of quality and safety standards

In recent years, labor-intensive agricultural products from developing countries have exhibited inferior performance in international trade due to quality and safety incidents, among which pesticide residue is a major issue. Aiming to improve food quality and safety in the context of cooperatives, we introduced three categories of control measures: outcome control, process control and social control. Based on the Pre-Harvest Interval Standard (PHIS), we selected three indices, farmers’ implementation rate of PHIS, absolute distance to PHIS and relative distance to PHIS, to evaluate appropriateness of pesticides use, reduction of pesticide residue and safety improvements of agricultural products. By using random sampling survey data, we empirically analyzed the marginal effects of control measures and their combinations on food quality and safety standards. The empirical results show that implementing process control, namely, unified production standards or supply of unified agricultural inputs, can comprehensively improve farmers’ implementation rate of PHIS, absolute distance and relative distance to PHIS respectively by 34.9%, 3.2 days and 46.0% on average. While the effects of outcome control (safety inspection) and social control (bonus-penalty incentive or training) are restricted to other measures. Therefore, we suggest cooperatives should take farmers’ features, implementation conditions and the effects of control measures into consideration in order to make a sustainable management plan for improving food quality and safety and enhancing competitiveness in international markets.     

The process of entrepreneurial action at the base of the pyramid in developing countries: a case of vegetable farmers in Benin

The assumption that entrepreneurship is a critical factor in expanding employment, creating wealth and contributing to poverty alleviation at the base of the pyramid (BoP) in developing countries has led to the development of many initiatives to strengthen the entrepreneurial activities of poor people. Despite the fact that entrepreneurship is seen as a strategy in combatting poverty, the process that leads to entrepreneurial action in a BoP context is still unclear. In this paper, we illustrate the possibilities a multi-layered perspective offers to understand the complexity of entrepreneurship in poverty settings. Based on five focus group discussions and 36 in-depth interviews with vegetable farmers in Benin, we examined the entrepreneurship of poor people. We learned that entrepreneurial action is the nexus of individual and exogenous factors in complex relationships. Based on this, we elaborate on the characteristics of the process model of entrepreneurial action. We provide a process-based view of entrepreneurship at the BoP, suggesting a need for consistency between individual, behavioural strategies and contextual elements. We discuss the implications of our findings for BoP practice and provide a framing perspective that we hope will encourage a greater focus on the complexity of entrepreneurship phenomenon.     

The impact of research collaboration on academic performance: An empirical analysis for some European countries

The aim of this paper is to investigate the impact of internal and external research collaborations on the scientific performance of academic institutions. The data are derived from the international SCOPUS database. We consider both quantity (the number of publications) and quality indicators (the field-weighted citation impact and the share of publications in the 10% most-cited articles) to evaluate universities' performance in some European countries (Germany, France, Italy, the UK and Russia). To this end, we develop a non-overlapping generations model to evidence the theoretical idea of research externalities between academic institutions. Moreover, we implement an empirical model to determine the extent to which the impact of internal and external collaborations on universities' performance is sensitive to the geographical dimension of the data.     

Is corporate social responsibility (CSR) participation the pathway to foster meaningful work and helping behavior for millennials?

This study examines how corporate social responsibility (CSR) participation affects organizational citizenship behavior (OCB) through meaningful work. This work is significant for three reasons: the joint examination of CSR, meaningful work, and OCB is novel; the comparative effects of CSR perception versus CSR participation have not been examined previously; and this is the first examination of such relationships for different generations of employees. Data from 245 employees of four-star hotels were analyzed using a partial least squares structural equation modelling (PLS-SEM) approach and multigroup analysis (MGA). Results reveal that CSR participation has a strong influence over work-related outcomes. The strongest effect of CSR participation on helping behavior is in Generation Y whereas CSR perception has a strong indirect effect on helping behavior through meaningful work in Generation X. These findings offer managerial implications to hotel managers on how best to manage generational differences in predicting helping behavior at workplace.     

海南城乡居民消费水平差异性分析和预测

从1985-2018年海南城乡居民收入、消费数据出发，分别建立消费关于收入、消费差距关于收入差距的自回归模型，结果表明农村居民当期消费更易受近期收入和消费水平的影响，具有不稳定性。再利用GM(1,1)模型预测城乡居民收入差距，结合自回归模型，完成未来10年海南城乡消费差距的预测：收入差距和消费差距将呈直线递增趋势，收入差距的增幅高于消费差距增幅。缩小海南城乡居民消费差距的根本途径在于缩小收入差距，应因地制宜，切实提高农民收入水平。     

Going abroad to play: Motivations,challenges, and support of sports expatriates

Professional athletes moving abroad for their career is a novel phenomenon in international human resource management (IHRM). This exploratory article charts the motivations of sports expatriates to move abroad to play, as well as adjustment challenges and sources of support. A survey was conducted with 77 professional athletes in 10 different sports. The main motivations to move abroad were interest to experience life abroad, followed by the search for new challenges. In terms of challenges, different coaching style and communication issues were most often mentioned. Support was mainly informal, through team mates rather than professional providers. Our article contributes to the literature because it is one of the first studies focusing on sports expatriates from an international HR perspective. Our study provides information on a vulnerable group of expatriates; they are young in age and under extreme performance pressure. Sports expatriates need all the support they can get, and yet, little professional support is offered.