J. Ben Schafer

Recommender systems in e-commerce

Recommender systems are changing from novelties used by a few E-commerce sites, to serious business tools that are re-shaping the world of E-commerce. Many of the largest commerce Web sites are already using recommender systems to help their customers find products to purchase. A recommender system learns from a customer and recommends products that she will find most valuable from among the available products. In this paper we present an explanation of how recommender systems help E-commerce sites increase sales, and analyze six sites that use recommender systems including several sites that use more than one recommender system. Based on the examples, we create a taxonomy of recommender systems, including the interfaces they present to customers, the technologies used to create the recommendations, and the inputs they need from customers. We conclude with ideas for new applications of recommender systems to E-commerce.

E-Commerce Recommendation Applications

Recommender systems are being used by an ever-increasing number of E-commerce sites to help consumers find products to purchase. What started as a novelty has turned into a serious business tool. Recommender systems use product knowledge—either hand-coded knowledge provided by experts or “mined” knowledge learned from the behavior of consumers—to guide consumers through the often-overwhelming task of locating products they will like. In this article we present an explanation of how recommender systems are related to some traditional database analysis techniques. We examine how recommender systems help E-commerce sites increase sales and analyze the recommender systems at six market-leading sites. Based on these examples, we create a taxonomy of recommender systems, including the inputs required from the consumers, the additional knowledge required from the database, the ways the recommendations are presented to consumers, the technologies used to create the recommendations, and the level of personalization of the recommendations. We identify five commonly used E-commerce recommender application models, describe several open research problems in the field of recommender systems, and examine privacy implications of recommender systems technology.

Collaborative filtering recommender systems

One of the potent personalization technologies powering the adaptive web is collaborative filtering. Collaborative filtering (CF) is the process of filtering or evaluating items through the opinions of other people. CF technology brings together the opinions of large interconnected communities on the web, supporting filtering of substantial quantities of data. In this chapter we introduce the core concepts of collaborative filtering, its primary uses for users of the adaptive web, the theory and practice of CF algorithms, and design decisions regarding rating systems and acquisition of ratings. We also discuss how to evaluate CF systems, and the evolution of rich interaction interfaces. We close the chapter with discussions of the challenges of privacy particular to a CF recommendation service and important open research questions in the field.

Meta-recommendation systems: user-controlled integration of diverse recommendations

In a world where the number of choices can be overwhelming, recommender systems help users find and evaluate items of interest. They do so by connecting users with information regarding the content of recommended items or the opinions of other individuals. Such systems have become powerful tools in domains such as electronic commerce, digital libraries, and knowledge management. In this paper, we address such systems and introduce a new class of recommender system called meta-recommenders. Meta-recommenders provide users with personalized control over the generation of a single recommendation list formed from a combination of rich data using multiple information sources and recommendation techniques. We discuss experiments conducted to aid in the design of interfaces for a meta-recommender in the domain of movies. We demonstrate that meta-recommendations fill a gap in the current design of recommender systems. Finally, we consider the challenges of building real-world, usable meta-recommenders across a variety of domains.

Agents in their midst: evaluating user adaptation to agent-assisted interfaces

This paper presents the results of introducing an agent into a real-world work situation - production of the online edition of a daily newspaper. Quantitative results show that agents helped users accomplish the task more rapidly without increasing user error and that users consistently underestimated the quality of their own performance. Qualitative results show that users accepted agents rapidly and that they unknowingly altered their working styles to adapt to the agent.

Implementations of the CC′01 human – computer interaction guidelines using Bloom's taxonomy

In todays technology-laden society human – computer interaction (HCI) is an important knowledge area for computer scientists and software engineers. This paper surveys existing approaches to incorporate HCI into computer science (CS) and such related issues as the perceived gap between the interests of the HCI community and the needs of CS educators. It presents several implementations of the HCI subset of the CC′01 curricular guidelines, targeting CS educators with varying degrees of HCI expertise. These implementations include course/module outlines from freshman to graduate levels, suggested texts, and project ideas and issues, such as programming languages and environments. Most importantly, each outline incorporates Blooms taxonomy to identify the depth of knowledge to be mastered by students. This paper condenses collaborative contributions of 26 HCI/CS educators aiming to improve HCI coverage in mainstream CS curricula.

In-person grading: an evaluative experiment

In this paper, we discuss in-person or face-to-face grading: what it is, a rationale for its use, our use of it, and an experiment we conducted to evaluate its use. While no statistically significant differences in instructional outcome effects were found, several interesting affective results were seen. Additionally, a number of research methodological suggestions arose from the study.

Recommender Systems for the Web

Recommender systems already provide substantial user value by personalizing a number of sites on the Web. The Semantic Web brings forward rich opportunities for improving these interfaces, and for striking a better balance between content and collaborative personalization methods.

Human Performance with Multiple Devices Influencing a Single Cursor

The goal of this study is to better understand how collaborative influence upon a single cursor may impact the performance of simple tasks like movement and selection. Two techniques for combining input from multiple devices are compared to an individual controller using a Fitts’s selection task. The results suggest that it is possible for multiple users to collaboratively move a single pointer without significant degradation in performance.