Tobias Keim

Matching People and Jobs: A Bilateral Recommendation Approach

Recommendation systems are widely used on the Internet to assist customers in finding the products or services that best fit with their individual preferences. While current implementations successfully reduce information overload by generating personalized suggestions when searching for objects such as books or movies, recommendation systems so far cannot be found in another potential field of application: the personalized search for subjects such as applicants in a recruitment scenario. Theory shows that a good match between persons and jobs needs to consider both, the preferences of the recruiter and the preferences of the candidate. Based on this requirement for modeling bilateral selection decisions, we present an approach applying two distinct recommendation systems to the field in order to improve the match between people and jobs. Finally, we present first validation test runs from a student experiment showing promising results.

Decision support for team staffing: An automated relational recommendation approach

Selecting individuals for teams is only rarely supported by IS. Existing systems only consider whether a person has the required technical skills and abilities for a job. Another important aspect is neglected - the match between the person and the team members in terms of interpersonal compatibility. We present a decision support system based on a relational recommendation approach for providing an automated pre-selection of candidates that fit best with future team members. The relational recommender contributes to theory by proposing an IS-supported relational approach to team staffing and to practice by offering time and cost savings for HR professionals.

Extending the Applicability of Recommender Systems: A Multilayer Framework for Matching Human Resources

Recommender systems (RS) so far have been applied to many fields of e-commerce in order to assist users in finding the products that best meet their preferences. However, while the application of RS to the search for objects is well established, this is not the case for the search for subjects. This is astonishing as a growing number of people make personal and professional information digitally available to others by managing profiles in CV databases, social networking platforms and other online services. In order to address this new field of application for RS, we integrate own prior research into a unified multilayer framework supporting the matching of individuals for recruitment and team staffing processes. By this means we enhance RS research and make a next step towards the development of empirically and theoretically grounded decision support for the human resources function

An Integrated Approach to Online Partnership Building

Research in information sciences in recent years has dealt with how to support collaborative work across time, space and organizational boundaries. However, this research neglected the question of how information systems can contribute right at the beginning of virtual work in the design phase of the team. Team configuration can be modeled as a two-dimensional matching problem: individuals need to be brought together (1) with tasks for which they posses the competencies to carry them out and (2) with other individuals with whom they are able to collaborate successfully. It is understood that multiple dimensions of human as well as social capital and especially of trust play an important role in the underlying decision process. Based on research in multiple fields we develop an approach permitting to establish successful virtual partnerships. We present its implementation together with first promising validation results.

A Model-Based Approach to Recommending Partners

Searching for and selecting qualified partners is a core task in many business contexts. Empirical research among Germany’s top 1 000 firms discloses that internet-based platforms are effectively used as a personnel marketing channel but cannot increase the matching quality between jobs and candidates. Using e-recruitment as an example we show how the matching quality can be substantially improved by means of a probabilistic latent aspect model developed in this paper. The underlying method incorporates findings from collaborative filtering and hybrid approaches to automated recommendation and is based on a model of personal attributes derived from research on team building and work psychology.

Conflicts and Conflict Resolution Mechanisms in Remote Collaboration via Videoconferencing

Globally active organizations and many virtual team based work structures are facing the challenge of a physically distributed workplace despite the necessity to closely interact among team members. While videoconferencing (VC) promises to replace the need for face-to-face meetings, this new medium also implies new cultural challenges. But what are the problems inherent to the social dynamics of videoconferencing usage in remote collaboration and what are mechanisms to overcome such conflicts? Based on an intense review of literature as well as a total of three case studies with multinational enterprises we identify nine major problems in VC and propose an adopted conflict management method for videoconferencing