BEGIN:VCALENDAR VERSION:2.0 PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4// BEGIN:VEVENT UID:20260529T190756EDT-8059BfEZtK@132.216.98.100 DTSTAMP:20260529T230756Z DESCRIPTION:\n\nFares Belkhiria\, a doctoral student at 91ºÚÁÏÍø i n the Marketing area will be presenting his thesis defense entitled:\n\nTh ree Essays on Precision Retailing Across Scales:\n Habits\, Recommendation Systems and Synthetic Population\n\nThursday\, June 4\, 2026\, at 11:00 AM \n (The defense will be conducted in hybrid mode)\n\nStudent Committee Chai r: Prof. Laurette Dubé\n\nPlease note: Thesis Defences are only open to me mbers of the 91ºÚÁÏÍø community (Students\, Professors and Staff) and not th e general public. Members of the 91ºÚÁÏÍø community may participate in-perso n. Due to limited space availability\, please contact the PhD office and w e will provide you with the room number.\n\n\nAbstract\n\nFood retail func tions as a central choice infrastructure in daily life\, shaping health\, affordability and well-being under conditions of bounded rationality\, lim ited time\, and marketing complexity. Despite this significance\, health-o riented retail interventions often produce modest behavioral change. This dissertation examines why such interventions underperform and proposes a f ramework for precision retailing that integrates behavioral science\, arti ficial intelligence (AI)\, and synthetic-population analytics to design mo re effective and equitable strategies. The research adopts the precision r etailing paradigm\, which treats food-system transformation as requiring c ross-disciplinary\, data-integrated\, and socially responsible innovation. The first essay investigates how multidimensional shopping habits\, repet itive\, context-dependent patterns of choice across items\, categories\, a nd stores shape responsiveness to healthy nudges. Using multi-year loyalty data and machine-learning-based habit measures\, the study uncovers stron g stickiness of purchases in typically unhealthy categories. It also demon strates that habitual customers are less likely to respond to healthy eati ng nudges than habitual ones\, revealing both opportunities and risks for public health-oriented retail design. The second essay introduces a Budget -Aware Next Basket Recommender (BANBR) that operationalizes precision reta iling as constraint-aware support. The system reframes personalization as a welfare-relevant intervention by reducing cognitive burden while preserv ing autonomy\, affordability\, and preference fit. The third essay extends the analysis to the neighborhood level by constructing a synthetic retail ecosystem that combines census-anchored synthetic populations\, georefere nced loyalty transactions\, neighborhood food-environment healthfulness\, and financial capability indicators. This integration produces privacy-pre serving mosaic agents that make it possible to examine how healthier food environments are associated with revealed grocery purchasing under differe nt local economic conditions and across shopper segments. The results show that healthy access alone is not enough\; healthier retail environments b ecome more behaviorally consequential in specific combinations of neighbor hood opportunity\, financial capability\, and type of shopper. The three e ssays are presented to move from diagnosis (habit as a mechanism of interv ention failure)\, to prescription (algorithmic tools for constraint-sensit ive support)\, to contextual evaluation (synthetic-ecosystem analysis of m ultiscale inequality in retail behavior). The thesis advances precision re tailing as an empirically grounded framework for improving individual comm ercial and social outcomes within complex retail systems.\n DTSTART:20260604T150000Z DTEND:20260604T160000Z SUMMARY:PhD Thesis Defense Presentation: Fares Belkhiria URL:/dobson/channels/event/phd-thesis-defense-presenta tion-fares-belkhiria-373106 END:VEVENT END:VCALENDAR