How constraints and preferences shape travel planning actions
How Constraints and Preferences Shape Travel Planning: Implications for AI Planning Support
Human-Computer Interaction
Summary
Planning trips is complicated because people have different limits and likes that can change over time. The authors studied travelers and travel agents to see how these limits and preferences arise and evolve during planning. They found that planning involves many back-and-forth steps to balance these factors instead of just setting fixed goals at the start. The study identified 11 common actions around constraints and preferences that guide how planning happens. They suggest ways to design AI tools that better help people by supporting this flexible and ongoing process.
What this means in practice
- •For travel app developers: Design travel planning tools that adapt to changing user goals and constraints throughout the trip planning process.
- •For customer service teams: Train travel agents to use dynamic approaches for handling client preferences and constraints during itinerary creation.
Authors
Fuling Sun, Yining Cao, Peiling Jiang, Mingyi Li, Haijun Xia
Abstract
Planning is a common yet complex activity shaped by constraints to satisfy and preferences to balance. Travel planning, as both an everyday activity and a frequent benchmark for evaluating intelligent systems, offers a rich context for examining how constraints and preferences emerge and evolve. While recent AI systems have achieved impressive results in generating personalized itineraries, they often assume that users can articulate stable goals upfront. To understand how real-world planning unfolds, we conducted a two-part interview study: one with eight travelers reflecting on their planning experiences, and one with nine travel agents sharing professional practices. We trace the dynamics of constraints and preferences as they are surfaced, refined, and coordinated throughout the planning process, and identified 11 actions revolving around constraints and preferences, which shaped the planning process. We offer design heuristics for planning tools that better support human-AI collaborative actions to support the fluid, contingent nature of planning.