Mordechai Gal-Or

Using data mining to profile TV viewers

Mining thousands of viewing choices and millions of patterns, advertisers and TV networks identify household characteristics, tastes, and desires to create and deliver custom targeted advertising.

Targeted Advertising Strategies on Television

The personal video recorder (PVR) facilitates the use of targeted advertising by allowing companies to monitor television viewing behavior and to build demographic profiles of viewers from the data that are collected. Our research explores the extent to which an advertiser should allocate resources to increase the quality of its targeting. We present a game-theoretic model that extends the conventional measurement of targeting quality by exploring the trade-off between two measures: accuracy and recognition. Accuracy measures the likelihood that any target segment prediction is correct, while recognition conversely measures the likelihood that any member of the target segment is identified. We find that the relative resources allocated to improving accuracy and recognition depend upon the size of the population of viewers, the propensity of viewers to skip commercials, the overall cost of airing commercials, and the competitive environment. Furthermore, the incentives to improve accuracy are markedly different from those to improve recognition. Although improving accuracy does not affect the extent of price competition, improving recognition leads to intensified price competition and reduced profitability in the product market. Thus, when facing a competitor that pursues a strategy to improve its recognition of potential customers, an advertiser should choose to reduce its investment in recognition and increase its investment in accuracy.

An enquiry into the ethical efficacy of the use of radio frequency identification technology

This paper provides an in-depth analysis of the privacy rights dilemma surrounding radio frequency identification (RFID) technology. As one example of ubiquitous information system, RFID has multitudinous applications in various industries and businesses across society. The use of this technology will have to lead to a policy setting dilemma in that a balance between individuals’ privacy concerns and the benefits that they derive from it must be drawn. After describing the basic RFID technology some of its most prevalent uses, a definition of privacy is derived in the context of information systems. To illustrate current attempts at controlling the undesirable side effects of RFID, Lessig’s cyberspace framework is presented. It is found that each of Lessig’s components is inadequate at preventing individual privacy violations in RFID. The main focus within this framework is on the norms of society. The social norm mechanism that addresses privacy issues in cyberspace is the Fair Information Practices Principles (FIPP). After an analysis of these principles, it is posited that the FIPP only deal with procedural justice issues related to data collection and omit distributive and interactional justice reasoning related to the actual beneficial and detrimental outcomes to the individuals whose data is being obtained. Thus, RFID is presented in the context of the tension between the many benefits that are provided by the technology in social exchanges, and the risk it carries of the loss of privacy. The new, expanded framework recognizes both sides of the issue with the ultimate goal of providing a greater understanding of how privacy issues can be addressed with RFID technology.

Exploring the privacy implications of addressable advertising and viewer profiling

Collecting consumer viewing habits will come back to bite advertisers who do not understand or appreciate how consumers feel about privacy infringement.

Assessing the predictive accuracy of diversity measures with domain-dependent, asymmetric misclassification costs

We explore the relationship between diversity measures and ensemble performance, for binary classification with simple majority voting, within a problem domain characterized by asymmetric misclassification costs. Extending the work of Kuncheva and Whitaker [Machine Learning 51(2) (2003) 181], we compare a set of diversity measures within two different data representations. The first is a direct representation, which explicitly allows for consideration of asymmetric costs by indicating the specific values of the predictions––which in turn allows for a distinction between more costly misclassifications in this domain (i.e., actual 0 predicted as 1) and less costly ones (i.e., actual 1 predicted as 0). The second is an oracle representation, which indicates predictions as either correct or incorrect, and therefore does not allow for asymmetric costs. Within these representations we identified and manipulated certain situational factors, including the percentage of target group members in the population and the designed accuracy and sensitivity of each constituent model. Based on a neural network comparison of diversity measures and ensemble performance, we found that (1) diversity measure association with ensemble performance is contingent on the data representation, with Yule’s Qstatistic and the coincident failure measure (CFD) as the best indicators in the direct representation and CFD alone as best indicator in the oracle representation, and (2) diversity measure association with ensemble performance varies as situational factors are manipulated; that is, diversity measures are differentially effective at different factor levels. Thus, the choice of a diversity measure in assessing ensemble classification performance requires an examination of both the nature of the task domain and the specific factors that comprise the domain. � 2004 Elsevier B.V. All rights reserved.

When to choose an ensemble classifier model for data mining

This study empirically explores the use of a group, or ensemble, of classifiers to support managerial decision making in domains characterised by asymmetric misclassification costs. The approach developed in this study is intended to assist a decision maker in determining whether a current situation warrants the choice of an ensemble over an individual classifier. The decision is based primarily on misclassification costs in the decision context and the associated basis on which performance is assessed. We show that the criteria for evaluating classifier performance are fundamentally dependent on the symmetry or asymmetry of misclassification costs. The result of this study is a set of heuristics for identifying highly- and poorly-performing ensembles.

Using decision tree models and diversity measures in the selection of ensemble classification models

This paper describes a contingency-based approach to ensemble classification. Motivated by a business marketing problem, we explore the use of decision tree models, along with diversity measures and other elements of the task domain, to identify highly-performing ensemble classification models. Working from generated data sets, we found that 1) decision tree models can significantly improve the identification of highly-performing ensembles, and 2) the input parameters for a decision tree are dependent on the characteristics and demands of the decision problem, as well as the objectives of the decision maker.

Facilitating Consumer Acceptance of RFID and Related Ubiquitous Technologies

The issue of consumer acceptance in the implementation of RFID and related ubiquitous technologies, driven primarily by privacy concerns, is a complex social problem involving consumers, companies, advocacy groups and government agencies – each of whom has different and often incompatible goals. This research decomposes the problem and explores it from the perspective of one of these stakeholders, that is, a company seeking to implement RFID in order to achieve specific business objectives. The authors establish a theoretical framework, based on social justice theory in business ethics that identifies the factors contributing to consumer and societal resistance to an RFID implementation. Within this framework, they outline the technical and managerial elements of an implementation plan, and relate those elements to the underlying components of social justice theory. The result is a strategy for technology managers that 1) considers the complex mix of consumer, societal and governmental concerns hindering adoption of the technologies, and 2) indicates areas of potential compromise.

Best Practices for Online Procurement Intermediaries

Industrial buyers who seek to procure inputs have the option of contracting the process out to procurement intermediaries. Many of these intermediaries now operate using Internet-based software to enhance the efficiency of their services. We develop a theoretical model of a buyer who wishes to procure an input from one of many differentiated suppliers. The buyer chooses between conducting the procurement herself and hiring a procurement intermediary. We use the model to investigate how and when such procurement intermediaries can be profitable, and to generate insight for the design of the online procurement process with regard to bidder recruitment and information revelation. The model suggests that the profitability of the intermediary relies crucially, on its ability to administer and evaluate quotes from potential suppliers more efficiently than the buyer can herself.