Michael Jeran

Toward the Next Generation of Recommender Systems: Applications and Research Challenges

Recommender systems are assisting users in the process of identifying items that fulfill their wishes and needs. These systems are successfully applied in different e-commerce settings, for example, to the recommendation of news, movies, music, books, and digital cameras. The major goal of this book chapter is to discuss new and upcoming applications of recommendation technologies and to provide an outlook on major characteristics of future technological developments. Based on a literature analysis, we discuss new and upcoming applications in domains such as software engineering, data and knowledge engineering, configurable items, and persuasive technologies. Thereafter we sketch major properties of the next generation of recommendation technologies.

Basic Approaches in Recommendation Systems

Recommendation systems support users in finding items of interest. In this chapter, we introduce the basic approaches of collaborative filtering, content-based filtering, and knowledge-based recommendation. We first discuss principles of the underlying algorithms based on a running example. Thereafter, we provide an overview of hybrid recommendation approaches which combine basic variants. We conclude this chapter with a discussion of newer algorithmic trends, especially critiquing-based and group recommendation.

Counteracting Serial Position Effects in the CHOICLA Group Decision Support Environment

Decisions are often suboptimal due to the fact that humans apply simple heuristics which cause different types of decision biases. CHOICLA is an environment that supports decision making for groups of users. It supports the determination of recommendations for groups and also includes mechanisms to counteract decision biases. In this paper we give an overview of the CHOICLA environment and report the results of a user study which analyzed two voting strategies with regard to their potential of counteracting serial position (primacy/recency) effects when evaluating decision alternatives.

WE-DECIDE: a decision support environment for groups of users

Group recommendation technologies are becoming increasingly popular for supporting group decision processes in various domains such as interactive television, music, and tourist destinations. Existing group recommendation environments are focusing on specific domains and do not include the possibility of supporting different kinds of decision scenarios. The We-Decide group decision support environment advances the state of the art by supporting different decision scenarios in a domain-independent fashion. In this paper we give an overview of the We-Decide environment and report the results of a first user study which focused on system usability and potentials for further applications.

Conflict Detection and Diagnosis in Configuration

The widespread industrial application of configuration technologies triggers an increasing demand for intelligent techniques that efficiently support anomaly management operations for configuration knowledge bases. Examples of such operations are the testing and debugging of faulty knowledge bases (see Chapter 11) and the detection of redundancies in configuration knowledge bases (see Chapter 12). The goal of this chapter is to discuss techniques and algorithms that form the technological basis for the aforementioned anomaly management operations.

Cluster-Specific Heuristics for Constraint Solving

In Constraint Satisfaction Problems (CSP), variable ordering heuristics help to increase efficiency. Applying an appropriate heuristic can increase the performance of CSP solvers. On the other hand, if we apply specific heuristics for similar CSPs, CSP solver performance could be further improved. Similar CSPs can be grouped into same clusters. For each cluster, appropriate heuristics can be found by applying a local search. Thus, when a new CSP is created, the corresponding cluster can be found and the pre-calculated heuristics for the cluster can be applied. In this paper, we propose a new method for constraint solving which is called Cluster Specific Heuristic (CSH). We present and evaluate our method on the basis of example CSPs.

Recommendation Technologies for IoT Edge Devices

Abstract The AGILE project aims to create Internet of Things (IoT) gateway technologies that support many devices, protocols, and corresponding management and development activities. In the context of this project there are scenarios that require the support of recommendation technologies. The major goal of this paper is to provide an overview of recommendation approaches and to discuss their relevance for AGILE.

Automated Learning Content Generation from Knowledge Bases in the STUDYBATTLES Environment

E-learning environments provide an orthogonal approach to transfer relevant knowledge. For example, sales representatives can improve their sales knowledge more independently from related courses offered. Major challenges for successfully establishing e-learning technologies in a company are to develop learning content in an efficient fashion, to recommend only relevant content to system users, and to motivate them to utilize the learning environment in a sustainable fashion. In this paper, we present the gamification-based e-learning environment STUDYBATTLES. We provide an overview of STUDYBATTLES functionalities including content creation, gamification techniques, learning performance analysis, and automated question generation. We show how STUDYBATTLES can be utilized for different learning purposes in academic and professional environments. In addition, we introduce an approach to automatically generate product and sales domain learning content from recommender knowledge bases to be exploited in STUDY...

Knowledge-based Learning Content Generation in the STUDYBATTLES Environment.

E-learning environments provide an orthogonal approach to transfer relevant knowledge. For example, sales representatives can improve their sales knowledge more independently from related courses offered. Major challenges for successfully establishing elearning technologies in a company are to develop learning content in an efficient fashion, to recommend only relevant content to system users, and to motivate them to utilize the learning environment in a sustainable fashion. In this paper, we present the gamification-based e-learning environment STUDYBATTLES. We provide an overview of STUDYBATTLES functionalities including content creation, gamification techniques, learning performance analysis, and automated question generation. We show how STUDYBATTLES is and can be utilized for different learning purposes in academic and professional environments. In addition, we introduce an approach to automatically generate product and sales domain learning content from recommender knowledge bases to be exploited in STUDYBATTLES. Finally, we report the results of an initial qualitative study related to the applicability of STUDYBATTLES in different domains, the potential improvements that STUDYBATTLES can achieve, and additional functionalities that should be integrated. Keywords– gamification-based e-learning; automated question generation; knowledge-based recommender systems; constraint satisfaction problem; knowledge acquisition