Otto R. Koppius

Predictive analytics in information systems research

textabstractThis research essay highlights the need to integrate predictive analytics into information systems research and shows several concrete ways in which this goal can be accomplished. Predictive analytics include empirical methods (statistical and other) that generate data predictions as well as methods for assessing predictive power. Predictive analytics not only assist in creating practically useful models, they also play an important role alongside explanatory modeling in theory building and theory testing. We describe six roles for predictive analytics: new theory generation, measurement development, comparison of competing theories, improvement of existing models, relevance assessment, and assessment of the predictability of empirical phenomena. Despite the importance of predictive analytics, we find that they are rare in the empirical IS literature. Extant IS literature relies nearly exclusively on explanatory statistical modeling, where statistical inference is used to test and evaluate the explanatory power of underlying causal models, and predictive power is assumed to follow automatically from the explanatory model. However, explanatory power does not imply predictive power and thus predictive analytics are necessary for assessing predictive power and for building empirical models that predict well. To show that predictive analytics and explanatory statistical modeling are fundamentally disparate, we show that they are different in each step of the modeling process. These differences translate into different final models, so that a pure explanatory statistical model is best tuned for testing causal hypotheses and a pure predictive model is best in terms of predictive power. We convert a well-known explanatory paper on TAM to a predictive context to illustrate these differences and show how predictive analytics can add theoretical and practical value to IS research.

Emerging multiple issue e-auctions

We review the emerging field of multiple issue e-auctions and discuss their design features and performance criteria. We primarily consider B2B transactions in a reverse auction, that is, a procurement setting. In traditional auctions, the matching of buyers and sellers is typically based just on price. However, when there are quality and other differences in the merchandise and differences in the terms of the transaction, which are common in Request for Quotes, additional issues besides price should be considered. Such multiple issue, multiple unit e-auctions/negotiations, and their characteristics are the focus of our paper. We also discuss the role that OR has played and undoubtedly will play in the design and implementation of such e-auctions.

The importance of product representation online: empirical results and implications for electronic markets

We investigate the effects of online product representation at a large Dutch flower auction that implemented screen auctioning. In screen auctioning, flowers are not physically shown to the buyers anymore; instead, an image is presented on a screen to buyers in the auction hall. This online product representation entailed a decrease in information about flower quality compared to the physical product representation. Analysis of the transaction data before and after screen auctioning revealed lower prices after the introduction of screen auctioning. We conclude that deficient product representation may be a partial explanation for reduced prices in electronic markets.

Implementing packaged enterprise software in multi-site firms: intensification of organizing and learning

Packaged enterprise software, in contrast with custom-built software, is a ready-made mass product aimed at generic customer groups in a variety of industries and geographical areas. The implementation of packaged software usually leads to a phase of appropriation and customization. As the associated processes remain ill understood, particularly for multi-site implementations, the objective of this paper is to understand the impact of packaged software in a multi-site organization. Adopting a case study method, this paper reports on a multi-site project that was analyzed at the group, site, and corporate level. Our findings suggest that as organizational units face the unsettling experience of having to implement a single source code across globally distributed sites, packaged software intensifies organizing and learning processes across these levels. The paper identifies specific processes for these levels and concludes with implications for research and practice. Our research extends IS research on packaged software implementation with an emphasis on multi-site firms.

Dimensions of intangible goods

Despite the ever-growing importance of intangible goods in todays economy, little is known about the underlying structural characteristics of intangible goods. This article will address this issue by analyzing some of the dimensions in which one intangible good can differ from another. Several dimensions are identified and they are grouped into three categories: buyer dimensions, seller dimensions and dimensions of the delivery process. These perspectives can be further subdivided into twelve different dimensions in total. This lends to a framework for analyzing intangible goods along the following dimensions: value determination, perishability, recipient, complexity of product use, externalities, specificability, customizability, substitutability, intensity in use, existence of a tangible equivalent, transfer mode and the options for tangible support.

Rich Ties and Innovative Knowledge Transfer within a Firm

We show that contacts in formal, informal and especially multiplex networks explain transfer of innovative knowledge in an organization. The contribution of informal contacts has been much acknowledged, while that of formal contacts did not receive much attention in the literature in recent decades. No study thus far has included both these different kinds of contacts in a firm, let alone considered their combined effect. The exact overlap between formal as well as informal contacts between individuals, forming multiplex or what we call rich ties because of their contribution, especially drives the transfer of new, innovative knowledge in a firm. Studying two cases in very different settings suggests these rich ties have a particularly strong effect on knowledge transfer in an organization, even when controlling for the strength of ties. Some of the effects on knowledge transfer in an organization previously ascribed to either the formal network or the informal network may actually be due to their combined effect in a rich tie.

Why are customers coming back to buy their airline tickets online? theoretical explanations and empirical evidence

The objective of this study is to clarify the theoretical and practical problem of continuance intention (CI) of purchasing airline tickets online. Based on an in-depth literature study factors were identified that could explain the level of continuance intention. The first set of factors relate to the expectation-confirmation theory (ECT) in the consumer behavior literature. Based on ECT, continuance intention can be theoretically explained by satisfaction, confirmation, web site quality, and loyalty incentives. The second set of factors relate to the technology acceptance model (TAM) which states that the actual system use - such as using online web sites to purchase airline tickets - is determined by the behavioral intention and the attitude towards usage, which in turn can be explained by perceived usefulness and perceived ease of use. The third factor is the price sensitivity of the consumer. The research model combines the different factors to explain continuance intention. Empirical research was carried out via an online survey among customers of a web-based airline ticket agency in the Netherlands in 2004. The online survey was pretested and refined and sent to 1770 customers at the time they purchased an online ticket. In total 715 customers answered the questionnaire and 492 of these were returning customers. The results of the empirical research support the following conclusions. Customer are coming back to purchase online tickets primarily because of the satisfaction of the online booking process and a positive attitude towards using the online booking system. Loyalty incentives and price sensitivity only play a marginal role. This by and large confirms the ECT model. The satisfaction with the service is explained by the confirmation of pre-purchase expectations as well as the quality of the website. The attitude toward usage was explained by the perceived usefulness and ease of use, in accordance with the TAM model. Somewhat surprisingly, trust and perceived risk played no significant role. Conclusions are formulated and implications for practice and research are presented.

Network horizon: An information-based view on the dynamics of bridging positions

We propose an information-based view of the dynamics of network positions and use it to explain why bridging positions become stronger. We depart from previous network dynamics studies that implicitly assume that firms have homogenous information about the network structure. Using network experiments with both students and managers, we vary a firms network horizon (i.e., how much information a firm has about the network structure) and the network horizon heterogeneity (i.e., how this information is distributed among the firms within the network). Our results indicate that firms with a higher network horizon occupy a stronger bridging position, especially under conditions of high network horizon heterogeneity. At a more general level, these results provide an indirect validation of what so far has been an untested assumption in interfirm network research, namely that firms are aware of their position in the overall network and consciously attempt to improve their position.

Degree-preserving trees

We consider the degree-preserving spanning tree (DPST) problem: Given a connected graph G, find a spanning tree T of G such that as many vertices of T as possible have the same degree in T as in G. This problem is a graph-theoretical translation of a problem arising in the system-theoretical context of identifiability in networks, a concept which has applications in, for example, water distribution networks and electrical networks. We show that the DPST problem is NP-complete, even when restricted to split graphs or bipartite planar graphs, but that it can be solved in polynomial time for graphs with a bounded asteroidal number and for graphs with a bounded treewidth. For the class of interval graphs, we give a linear time algorithm. For the class of cocomparability graphs, we give an O(n4) algorithm. Furthermore, we present linear time approximation algorithms for planar graphs of a worst-case performance ratio of 1 - e for every e > 0.

Information technology and the internationalization of the firm

A key concern for all multinationals is where to find a suitable location for their business activities, bearing in mind that they must find the right balance between global integration and local responsiveness. This article contributes to the internationalization debate by asking: in what sense will information technology enable globalization? We focus on the sourcing process, an area where globalization is often claimed to be the case. Re-examination of empirical evidence shows that global sourcing is not as generally predominant as is claimed. Consequently inhibitors to global integration exist and we classify these inhibitors into three categories: geographical, relational and environmental inhibitors. We then analyze the role information technology plays in reducing these inhibitors and formulate propositions that are then illustrated in two case studies. Information technology is proposed to reduce the geographical and relational inhibitors, but it will have no effect on environmental inhibitors. However, the latter category of inhibitors will become more prominent in the future. Information technology thus shifts the balance towards global integration, but simultaneously creates new problems in managing internationalization.