دامنه داده کاوی هدایت شده در مدیریت منابع انسانی: مروری بر تحقیقات جاری

An increasing number of publications concerning data mining in the subject of human resource management (HRM) indicate the presence of a prospering new research field. The current paper reviews this research on HR data mining to systematically uncover recent advancements and suggest areas for future work. Based on the approach of domain driven data mining, an initial framework with significant domain-specific requirements is elaborated. Relevant research contributions are identified and reviewed against the background of this framework. The review reveals that HRM constitutes a noteworthy new domain of data mining research that is dominated by method- and technology-oriented work. However, specific domain requirements, such as evaluating the domain success or complying with legal standards, are frequently not recognized or considered in current research. Therefore, the systematic consideration of domain-specific requirements is demonstrated here to have significant implications for future research on data mining in HRM.

Data mining refers to the non-trivial process of identifying novel, potentially useful and valid patterns in data (Fayyad, Piatetsky-Shapiro, & Smyth, 1996). There is a broad set of data mining application domains and corresponding research domains, including the management domain with well-established sub-domains, such as customer management (e.g. Ngai, Xiu, & Chau, 2009), manufacturing management (e.g. Choudhary, Harding, & Tiwari, 2008) or financial management (e.g. Ngai, Hu, Wong, Chen, & Sun, 2011). Recently, these sub-domains appear to be complemented by human resources management (HRM). In recent years, a quickly growing number of research contributions aim at supporting the practical adoption of HRM data mining. Research contributions refer to various HRM activities and processes, such as selecting employees (Aiolli, de Filippo, & Sperduti, 2009) and predicting employee turnover (Aviad & Roy, 2011) in the function of staffing, ascertaining competencies of employees ( Zhu, Goncalves, Uren, Motta, & Pacheco, 2005) and career planning ( Lockamy & Service, 2011) in the function of development, planning HR costs ( Juan, 2009) and predicting the acceptance of severance pay ( Ramesh, 2001) in the function of compensation, and predicting ( Thissen-Roe, 2005) and evaluating ( Zhao, 2008a and Zhao, 2008b) employee performance in the function of performance management. To support these functions, the entire spectrum of data mining methods – decision trees ( Sivaram & Ramar, 2010) cluster analysis ( Karahoca, Karahoca, & Kaya, 2008), association analysis ( Zhang & Deng, 2011), support vector machines ( Li, Xu, & Meng, 2009) and neural nets ( Ning, 2010) – is employed, while methodical advancements and innovations are presented ( Goonawardene, Subashini, Boralessa, & Premaratne, 2010). In summary, browsing the literature indicates a prospering new field of data mining research that provides ample insights in how to generate advanced information and decision support within the HR domain. This paper is the first comprehensive review of this new field of research, and it purposes to uncover recent advancements and suggest remaining tasks for future research. Given the growing doubts concerning the ability of conventional data mining research to meet the requirements of practice and the corresponding calls for more relevant data mining research (Adejuwon and Mosavi, 2010, Cao, 2010, Cao and Zhang, 2007, Puuronen and Pechenizkiy, 2010 and Weiss, 2009), the concept of domain driven data mining ( Adejuwon and Mosavi, 2010, Cao, 2010, Cao and Zhang, 2007 and Wang and Wang, 2009) is employed as a reference framework for the review. To provide a systematic review, the method of identifying relevant research contributions is described, and an initial framework of domain driven data mining research in HR is substantiated. Subsequently, this framework is employed to systematically review the discovered research contributions and to derive implications for future research.

4. Conclusions The current paper aimed at a review of research on HRM data mining against the background of a domain driven research perspective. The review revealed that HRM constitutes a new domain of data mining research, given the large number and broad variety of relevant research contributions. Besides the quite recent publication dates and the larger share of proceedings-based research contributions, the relative shortness of cross-referencing and the absence of cumulative research clearly hint at an emerging and still nascent research domain. Despite the domain’s interdisciplinary character, the field is currently dominated by method- and technology-oriented research; managerial research rarely participates. The review suggests that current research does not frequently recognize and consider domain-specific requirements. Elaborating and applying a domain driven framework revealed that critical aspects, such as ensuring functional relevance and success of data mining, ensuring the provision of suitable data and information systems, or ensuring the compliance with ethical and legal standards, have not received general consideration until now. However, it must be stressed that each domain-specific requirement was met by a smaller set of research contributions that offer valuable guidance for future research programs. Using a domain perspective in a comprehensive review was necessary for uncovering recent advancements and suggesting remaining tasks for future research. Finally, the review demonstrated that a domain perspective is a fruitful approach for future research. According to the implications elaborated within this review, future domain driven HRM data mining research needs to • elaborate a systematic overview of functional HR application areas, • substantiate the relevance and characteristics of the focused HR problem(s), • demonstrate domain success, in particular, compared to existing conventional HR methods, • evaluate existing mining methods and, if necessary, customize existing or develop new methods, • support the specification and provision of suitable HR data, • offer domain-specific data mining IS or, preferably, embed data mining in existing HRIS, • minimize and support remaining end-user tasks and • comply with respective ethical and legal standards. The above implications constitute a minimal list, which may need to be enlarged, depending on the research context. Adopting a domain driven perspective in the future is by no means an easy endeavor. A domain driven perspective will increase the required effort and complexity of research, given that multiple and interrelated requirement dimensions have to be considered. A domain driven perspective might also narrow the actual application range of data mining in HRM, given that certain domain restrictions, such as the existence of superior conventional HR methods, the lack of suitable HR data, or simply the legal prohibition of certain mining procedures, may persist. However, a domain driven perspective is indispensable when research aims to provide results that are relevant in the real world.