Recommendation is not a new phenomenon arising from the digital era, but an existing social behavior in real life. Recommendation systems facilitate such natural social recommendation behavior and alleviate information overload facing individuals. Among different recommendation techniques proposed in the literature, the collaborative filtering approach is the most successful and widely adopted recommendation technique to date. However, the traditional collaborative filtering recommendation approach ignores proximities between items. That is, all user ratings on items are deemed identically important and given an equal weight in neighborhood formation process. In this study, we proposed a cluster-based collaborative filtering recommendation approach that takes into account the content similarities of items in the collaborative filtering process. Our empirical evaluation results show that the cluster-based collaborative filtering approach improves the prediction accuracy without sacrificing the prediction coverage, using those achieved by the traditional collaborative filtering approach as performance benchmarks. Due to the sparsity problem, when a prediction is made based on few neighbors, the cluster average method could achieve a better prediction accuracy than the proposed approach. Thus, we further proposed an enhanced cluster-based collaborative filtering approach that combines our approach and the cluster average method. The empirical results suggest that the enhanced approach could result in a prediction accuracy comparable to or even better than that accomplished by the cluster average method.

Die vorliegende Dissertation setzt sich damit auseinander, wie das Zusammenspiel von essensbezogener Umwelt und Kognition Ernährungsentscheidungen beeinflusst. Im ersten Manuskript, “When Diets Last: Lower Cognitive Complexity Increases Diet Adherence” wird die Bedeutung der kognitiven Komplexität von Ernährungsregeln für das Einhalten einer Diät untersucht. Können Diäten scheitern, weil sie aus kognitiver Perspektive zu komplex sind, z.B. weil sich Diäthaltende nicht alle wichtigen Informationen merken oder verarbeiten können? 1136 Diäthaltende nahmen an einer längsschnittlichen Onlinestudie teil. Vorangegangenes Diätverhalten, Selbstwirksamkeit, Planung und wahrgenommene Regelschwierigkeit erhöhten das Risiko, die Diät vorzeitig aufzugeben, wobei Selbstwirksamkeit und wahrgenommene Regelschwierigkeit die einflussreichsten Faktoren waren. Im zweiten Manuskript „Meat Label Design: Effects on Stage Progression, Risk Perception, and Product Evaluation” wird der Einfluss gesundheitsrelevanter Information auf Labeln für Produktbewertung und Intention, Tierhaltung und Inhaltsstoffe von Lebensmitteln in die Kaufentscheidung einzubeziehen, untersucht. Es wurde betrachtet, wie Inhalt und Kontext (separate versus conjoint Darbietung) der Labelinformation die Bewertung von Fleischprodukten beeinflusst. Die Ergebnisse zeigen, dass sich bei einer conjoint im Gegensatz zur separaten Darbietung die Bewertung der Produkte umkehrt. Darüber hinaus hatten Personen, die zuvor nicht motiviert waren gesundheitsrelevante Aspekte in ihr Einkaufsverhalten einzubeziehen, nach Betrachten der Label eine höhere Intention diese zu berücksichtigen. Im dritten Manuskript, „Predicting Children’s Meal Preferences: How Much Do Parents Know?“, wurden Präferenzvorhersagen bezüglich der Essensentscheidungen Anderer erforscht. Es wurde untersucht, wie gut und mit Hilfe welcher Information Eltern die Mittagessenpräferenzen ihrer Kinder vorhersagen. Die Vorhersagegenauigkeit der Eltern entsprach der Stabilität der Essenspräferenzen ihrer Kinder, d.h. dass die Eltern so genau waren, wie möglich. Die Ergebnisse suggerieren, dass Eltern vor allem spezifisches Wissen über die Präferenzen ihrer Kinder und Projektion ihrer eigenen Vorlieben für die Vorhersagen nutzten. / This dissertation focuses on food-related decision making, in particular, how food related environments and cognition interact to determine people’s food choices. The first manuscript, “When Diets Last: Lower Cognitive Complexity Increases Diet Adherence,” investigates the role of the cognitive complexity in diet adherence. Can weight loss diets fail because they are too complicated from a cognitive point of view, meaning that dieters are not able to recall or process the diet rules? The impact of excessive cognitive demands on diet adherence were investigated with 1,136 dieters in a longitudinal online-questionnaire. We measured perceived rule complexity controlling for other factors known to influence adherence. Previous diet behavior, self-efficacy, planning and perceived rule complexity predicted an increased risk to quit the diet prematurely, with self-efficacy and diet complexity being the strongest factors. The second manuscript, “Meat Label Design: Effects on Stage Progression, Risk Perception, and Product Evaluation,” presents two studies which tested the impact of health-related meat labels on product evaluation and intention. Specifically, the studies examined how informational content and the context (separate vs. conjoint evaluation) in which labels are assessed influence the evaluation of meat products. The results showed that conjoint assessment of labels can lead to contrary product rankings compared to separate evaluations. Moreover, the results suggest that being exposed to food labels containing specific health-relevant information can increase motivation to consider health aspects in those consumers without previous intention to do so. The third manuscript, “Predicting Children’s Meal Preferences: How Much Do Parents Know?” investigated prediction behavior concerning other people’s food choices. In particular, it asked how accurately and what cues parents use to predict their children’s meal choices. Overall, parents’ prediction accuracy matched the stability of children’s meal choices, implying that accuracy was as high as can be expected. The results suggest parents were able to obtain high predictive accuracy by using specific knowledge about their child’s likes and projecting their own preferences.

Methodologies designed to support new product development are receiving increasing interest in recent literature. A significant percentage of new product failure is attributed to a mismatch between designed product features and consumer liking. A variety of methodologies have been proposed and tested for consumer liking or preference prediction, ranging from statistical methodologies e.g. multiple linear regression (MLR) to non-statistical approaches e.g. artificial neural networks (ANN), support vector machines (SVM), and belief rule-based (BRB) systems. BRB has been previously tested for consumer preference prediction and target setting in case studies from the beverages industry. Results have indicated a number of technical and conceptual advantages which BRB holds over the aforementioned alternative approaches. This thesis focuses on presenting further advantages and applications of the BRB methodology for consumer liking prediction. The features and advantages are selected in response to challenges raised by three addressed case studies. The first case study addresses a novel industry for BRB application: the fast moving consumer goods industry, the personal care sector. A series of challenges are tackled. Firstly, stepwise linear regression, principal component analysis and AutoEncoder are tested for predictors’ selection and data reduction. Secondly, an investigation is carried out to analyse the impact of employing complete distributions, instead of averages, for sensory attributes. Moreover, the effect of modelling instrumental measurement error is assessed. The second case study addresses a different product from the personal care sector. A bi-objective prescriptive approach for BRB model structure selection and validation is proposed and tested. Genetic Algorithms and Simulated Annealing are benchmarked against complete enumeration for searching the model structures. A novel criterion based on an adjusted Akaike Information Criterion is designed for identifying the optimal model structure from the Pareto frontier based on two objectives: model complexity and model fit. The third case study introduces yet another novel industry for BRB application: the pastry and confectionary specialties industry. A new prescriptive framework, for rule validation and random training set allocation, is designed and tested. In all case studies, the BRB methodology is compared with the most popular alternative approaches: MLR, ANN, and SVM. The results indicate that BRB outperforms these methodologies both conceptually and in terms of prediction accuracy.