Werner Kießling

Foundations of preferences in database systems

Personalization of e-services poses new challenges to database technology, demanding a powerful and flexible modeling technique for complex preferences. Preference queries have to be answered cooperatively by treating preferences as soft constraints, attempting a best possible match-making. We propose a strict partial order semantics for preferences, which closely matches peoples intuition. A variety of natural and of sophisticated preferences are covered by this model. We show how to inductively construct complex preferences by means of various preference constructors. This model is the key to a new discipline called preference engineering and to a preference algebra. Given the Best-Matches-Only (BMO) query model we investigate how complex preference queries can be decomposed into simpler ones, preparing the ground for divide & conquer algorithms. Standard SQL and XPATH can be extended seamlessly by such preferences (presented in detail in the companion paper [15]). We believe that this model is appropriate to extend database technology towards effective support of personalization.

Preference SQL: design, implementation, experiences

Current search engines can hardly cope adequately with fuzzy predicates defined by complex preferences. The biggest problem of search engines implemented with standard SQL is that SQL does not directly understand the notion of preferences. Preference SQL extends SQL by a preference model based on strict partial orders (presented in more detail in the companion paper [Kie02]), where preference queries behave like soft selection constraints. Several built-in base preference types and the powerful Pareto operator, combined with the adherence to declarative SQL programming style, guarantees great programming productivity. The Preference SQL optimizer does an efficient re-writing into standard SQL, including a high-level implementation of the skyline perator for Pareto-optimal sets. This pre-processor approach enables a seamless application integration, making Preference SQL available on all major SQL platforms. Several commercial B2C portals are powered by Preference SQL. Its benefits comprise cooperative query answering and smart customer advice, leading to higher e-customer satisfaction and shorter development times of personalized search engines. We report practical experiences ranging from m-commerce and comparison shopping to a large-scale performance test for a job portal.

Preference Mining: A Novel Approach on Mining User Preferences for Personalized Applications

Advanced personalized e-applications require comprehensive knowledge about their user’s likes and dislikes in order to provide individual product recommendations, personal customer advice and custom-tailored product offers. In our approach we model such preferences as strict partial orders with “A is better than B” semantics, which has been proven to be very suitable in various e-applications. In this paper we present novel Preference Mining techniques for detecting strict partial order preferences in user log data. The main advantage of our approach is the semantic expressiveness of the Preference Mining results. Experimental evaluations prove the effectiveness and efficiency of our algorithms. Since the Preference Mining implementation uses sophisticated SQL statements to execute all data-intensive operations on database layer, our algorithms scale well even for large log data sets. With our approach personalized e-applications can gain valuable knowledge about their customers’ preferences, which is essential for a qualified customer service.

Situated Preferences and Preference Repositories for Personalized Database Applications

Advanced personalized web applications require a carefully dealing with their users’ wishes and preferences. Since such preferences do not always hold in general, personalized applications also have to consider the user’s current situation. In this paper we present a novel framework for modeling situations and situated preferences. Our approach consists of a general meta model for situations, which can be applied as foundation for situation models in a wide range of applications. Furthermore, an XML-based preference repository for the storage and management of situated preferences is developed. Long-term and situated preferences can easily be accessed with the preference repository interface. Particularly, preferences best-matching to a given situation can be queried. This approach allows web applications to react flexibly and personalized to the changing situations of their users.

Preference XPATH:A Query Language for E-Commerce

We present a new XML-based search technology that enables users to formulate complex customer or vendor preferences which typically occur within e-commerce applications. Preferences are modeled in a natural way by partial orders. Since our semantics of multi-attribute preferences implements the Pareto-optimality principle Preference XPATH queries avoid both the unwanted “emptyresult”-effect and the flooding-effect with lots of irrelevant query results. If perfect matches are not available best possible alternatives are found instead. We have extended the XML query language XPATH by the capability to formulate preferences as soft selection conditions. As our extensions are fully compatible with the XPATH standard both hard and soft selection conditions become now available to any XML-based e-commerce application. Several e-shopping examples show how easy and elegant it is to transform customer wishes into Preference XPATH queries. Our prototype implementation is smoothly integrated with the XML database system Tamino of Software AG. Moreover we show how Preference XPATH can be used within the XML query language QUILT. It even merges with XML style sheets (XSLT) and the XML pointer language (XPointer). Thus with Preference XPATH powerful personalized search engines and match-making processes for B2C and B2B can be implemented completely inside the XML framework.

New direction for uncertainty reasoning in deductive databases

This paper contributes a novel approach to nonmonotonic uncertainty reasoning, which is ubiquitous in many real-life applications. Founded on the paradigm of conditional probabilities we develop a rule-based calculus and prove that it is sound, even in the presence of incomplete information. Thus the merits of doing consistent judgments in uncertain domains and the advantages of modularity and incrementality of rulebased application development come together. We also can offer mechanisms to trace down inconsistencies that may be hidden in very large collections of uncertain rules. As next-generation applications will have to handle vast amounts of uncertain data, an integration into databases is mandatory. We give a direct implementation of our calculus on top of a database system with a DATALOG-interface. In this way we extend current database technology towards providing new applications with new suitable primitives and with a database platform for coping with uncertainty.

Towards precision of probabilistic bounds propagation

The DUCK-calculus presented here is a recent approach to cope with probabilistic uncertainty in a sound and efficient way. Uncertain rules with bounds for probabilities and explicit conditional independences can be maintained incrementally. The basic inference mechanism relies on local bounds propagation, implementable by deductive databases with a bottom-up fixpoint evaluation. In situations, where no precise bounds are deducible, it can be combined with simple operations research techniques on a local scope. In particular, we provide new precise analytical bounds for probabilistic entailment.

Database Support for Problematic Knowledge

Recently substantial research efforts have been spent on extending database technology in various ways towards a better support of applications of the nineties. In contrast, the tough problems of adding the right uncertainty reasoning capabilities have received relatively modest attention despite evident importance. Among the many faces of uncertainty we focus on what we call problematic knowledge, which is — e. g. — inherent in what-if decision scenarios. Based on a rule calculus with probability intervals introduced lately [GKT 91] we show how to do rule chaining under independence and how to add comparative probability. Also a method for reasoning with uncertain facts, founded on the notions of maximal context and detachment, is given. Full database support can be given to the calculus. We discuss some aspects of the optimization problem and how to deliver uncertainty reasoning to the users application by interoperability in a heterogeneous database environment.

A preference-based recommender system

The installation of recommender systems in e-applications like online shops is common practice to offer alternative or cross-selling products to their customers. Usually collaborative filtering methods, like e.g. the Pearson correlation coefficient algorithm, are used to detect customers with a similar taste concerning some items. These customers serve as recommenders for other users. In this paper we introduce a novel approach for a recommender system that is based on user preferences, which may be mined from log data in a database system. Our notion of user preferences adopts a very powerful preference model from database systems. An evaluation of our prototype system suggests that our prediction quality can compete with the widely-used Pearson-based approach. In addition, our approach can achieve an added value, because it yields better results when there are only a few recommenders available. As a unique feature, preference-based recommender systems can deal with multi-attribute recommendations.

DECLARE and SDS: early efforts to commercialize deductive database technology

The Smart Data System (SDS) and its declarative query language, Declarative Reasoning, represent the first large-scale effort to commercialize deductive database technology. SDS offers the functionality of deductive reasoning in a distributed, heterogeneous database environment. In this article we discuss several interesting aspects of the query compilation and optimization process. The emphasis is on the query execution plan data structure and its transformations by the optimizing rule compiler. Through detailed case studies we demonstrate that efficient and very compact runtime code can be generated. We also discuss our experiences gained from a large pilot application (the MVV-expert) and report on several issues of practical interest in engineering such a complex system, including the migration from Lisp to C. We argue that heuristic knowledge and control should be made an integral part of deductive databases.