Due to the vast amount of user data tracked online, the use of data-based analytical methods is becoming increasingly common for e-businesses. Recently the term analytical eCRM has been used to refer to the use of such methods in the online world. A characteristic of most of the current approaches in eCRM is that they use data collected about users' activities at a single site only and, as we argue in this paper, this can present an incomplete picture of user activity. However, it is possible to obtain a complete picture of user activity from across-site data on users. Such data is expensive, but can be obtained by firms directly from their users or from market data vendors. A critical question is whether such data is worth obtaining, an issue that little prior research has addressed. In this paper, using a data mining approach, we present an empirical analysis of the modeling benefits that can be obtained by having complete information. Our results suggest that the magnitudes of gains that can be obtained from complete data range from a few percentage points to 50 percent, depending on the problem for which it is used and the performance metrics considered. Qualitatively we find that variables related to customer loyalty and browsing intensity are particularly important and these variables are difficult to derive from data collected at a single site. More importantly, we find that a firm has to collect a reasonably large amount of complete data before any benefits can be reaped and caution against acquiring too little data.
This paper reports on conceptual development in the areas of database mining and knowledge discovery in databases (KDD). The authors' efforts have also led to a prototype implementation, called MOTC, for exploring hypothesis space in large and complex data sets. Their KDD conceptual development rests on two main principles. First, they use the crosstab representation for working with qualitative data. This is by now standard in on-line analytical processing (OLAP) applications, and the authors reaffirm it with additional reasons. Second, and innovatively, they use prediction analysis as a measure of goodness for hypotheses. Prediction analysis is an established statistical technique for analysis of associations among qualitative variables. It generalizes and subsumes a large number of other such measures of association, depending on specific assumptions the user is willing to make. As such, it provides a very useful framework for exploring hypothesis space in a KDD context. The paper illustrates these points with an extensive discussion of MOTC.
This paper motivates the need for system-level message management software. It begins by considering information flows in the workplace as a source of potential gains in efficiency. We next investigate work-flow automation and electronic data interchange (EDI) as indicative of current technologies applied to work processes and message management. Having described current technology and our vision of work processes, we propose an alternative, general-purpose, software technology for supporting application-to-application communication. Problems of EDI, of process-to-process communication, and of describing information items are discussed in terms of the communication problems they present. We then justify the need for this kind of software and lay out the criteria (or plausibility conditions) for evaluating a proposal for this sort of system software. The use of a formal communication language is proposed as a common solution to these problems. This proposal is examined in the context of the EDI problem, in order to demonstrate how the proposal might work in practice. Practical benefits of the proposal are discussed that highlight the impact such a technology might have on business practices. The proposed solution is measured against the plausibility conditions presented earlier in the paper; it is found to be sufficient in some cases and in need of further investigation in others. We then discuss the industrial-organizational implications of the availability of such a technology, and hypothesize that it would affect the number and form of cooperative business relationships as well as their scope and depth. We also hypothesize that it would provide advantages to those firms that quickly adopt the technology.
Hypertext has quickly become an established paradigm in the design of information systems. The success of products in the software market, evident benefits as reported by users, and the flowering of related research activity all attest to the significance and staying power of hypertext-rich information systems. Although standard hypertext has a number of unquestioned benefits, the concept also has a number of well-known problems and limitations. This article reviews the main problems and limitations of basic (standard) hypertext that constrain the use of hypertext in practical applications. Further, this article presents and discusses our "generalization" of the basic hypertext concept, which we call generalized hypertext. These generalizations encompass, among other things, automatic creation of hypertext elements. Generalized hypertext promises to be more powerful than standard hypertext as well as less expensive to implement and maintain. To illustrate these concepts, we describe the implementation of a decision support system currently in use by the U.S. Coast Guard.