Research

2024

1. JMIS

   Discovery of Technological Innovation Systems: Implications for Predicting Future Innovation

   Junho Yoon , Gautam Pant , and Shagun Pant

   Journal of Management Information Systems, 2024

   Abs HTML

   In contrast with the accelerating trend of boundary-spanning (horizontal) technological innovation, the current Cooperative Patent Classification (CPC) scheme applies a hierarchical (vertical) structure to innovation output in terms of patents. For this reason, we argue that the CPC can be complemented with dynamic technological innovation system (TIS) discovery through machine learning that accounts for horizontal relationships across seemingly disparate technologies. Using a design science approach, we propose a framework to discover boundary-spanning TISs by leveraging the textual information from millions of patents. We validate our framework in terms of the ability of discovered relationships to predict future innovation quantity and quality in different technology classes. Our novel TIS-based innovation metrics that leverage patenting activity in related technology classes are significantly associated with future innovation intensity in focal technologies. We conduct experiments with machine learning models to further tease out the predictive utility of our TIS discovery framework.

2. Working

   Predicting Firm Alliances: Leveraging Relational Pluralism in Innovation with Graph Neural Networks

   Junho Yoon , and Gautam Pant

   Working Paper, Available at SSRN 4643882, 2024

   Abs HTML

   Interfirm alliances in high-tech industries are a synergistic resource-sharing mechanism that can lead to efficient innovation. As an initial critical step in forming alliances, firms conduct partner search, which involves finding other firms that possess complementary technological resources and capabilities. This study proposes an automated alliance prediction framework that can simplify partner search as well as provide valuable intelligence to third parties such as analysts and investors. Our graph neural network-based framework utilizes a key alliance theory on relational pluralism, which refers to multitudes of relationships that exist between firms that can provide an understanding of how firms interact and collaborate. To operationalize our prediction framework, we compile a rigorous firm-level network data set derived from 8,739 alliances between 11,499 firms in 11 high-tech industries through the period of 1990-2018. Our theory-driven predictive models incorporate multiple innovation-based relations—interfirm collaborations, human capital flow, and knowledge spillovers—into graph neural networks (GNNs). Our prediction results show that the plurality of interfirm relations collectively contributes to superior predictive performance across varying evaluation metrics, highlighting the practical utility of our predictive models as a partner search instrument. We also discuss the stakeholders who can benefit from our prediction framework in practice, as well as several contributions to the alliance literature.

3. Working

   Individual Skill Flexibility and Turnover: Empirical Evidence from Hotel Employees

   Hyoeun Kim , Junho Yoon , Juan Luis Nicolau , and 1 more author

   Working Paper, Available at SSRN 4668400, 2024

   Abs HTML

   In an effort to reduce exorbitant employee turnover, the hospitality industry has recently offered career development programs to their employees in pursuit of longer retention. Such educational human resource (HR) practices are expected to increase the skill flexibility of individual employees (ie, individual skill breadth) across a wide range of skill categories, leading to lower turnover through improved job satisfaction. However, the empirical association between employee skill flexibility and turnover at the individual level has remained unexplored in the HR literature. This study fills in this research gap by drawing on the theoretical framework of employee skill flexibility in the field of strategic human resource management (SHRM). Building on a unique data set from over 10,000 LinkedIn profiles among hotel employees in major brands across the United States, we operationalize their skill flexibility and find its association with turnover. For this purpose, we first identify seven hotel employee-specific skill categories using an unsupervised machine-learning method and subsequently quantify skill flexibility at the individual level. Our results show that the association between skill flexibility and turnover is moderated by skill categories. This study contributes to the HR literature as a data-driven implementation of human capital analytics (HCA).

4. The Sustainable Rhythm of Destination Popularity: A Song of Local Well-Being and Lasting Charm

   Hyoeun Kim , Junho Yoon , and Juan Luis Nicolau

   Journal of Hospitality & Tourism Research, 2024

2023

1. Unveiling technological innovation in hospitality and tourism through patent data: Development perspective and competition landscaping

   Hyoeun Kim , Junho Yoon , and Juan Luis Nicolau

   International Journal of Hospitality Management, 2023

2017

1. Multivariate time-series classification of sleep patterns using a hybrid deep learning architecture

   Jeonghan Hong , and Junho Yoon

   In 2017 IEEE 19th international conference on e-Health networking, applications and services (Healthcom) , 2017