Multi-Objective Optimization of Itinerary Planning Based on Weather Changes and User Preferences

Existing travel planning systems lack user participation in itinerary scoring and apply coarse, binary weather treatment that risks excluding high-quality outdoor attractions under mild precipitation. This paper presents a multi-objective genetic algorithm (GA)-based itinerary planning system addressing both limitations. A rule-based weather-adaptive POI scoring framework maps nine weather conditions to three strategies, applying intensity-proportional rain penalties and a geographic flexibility bonus; this deterministic design requires no training data and is fully interpretable. User preferences are encoded via three integer sliders whose normalised values directly set GA fitness weights for POI quality, traveling efficiency, and preference satisfaction. Evaluated on 142 attractions in Macao, outdoor POI representation decreases progressively with precipitation—from 2.88 per itinerary under clear conditions to 1.58 under extreme weather alerts—while itinerary quality is preserved. Slider experiments confirm direction-correct improvements across 30 independent runs: amplifying the quality weight increases average POI score from 0.811 to 0.908 (+12.0%, p<0.001); the efficiency weight reduces mean detour ratio from 1.332 to 1.132 (p<0.001); and the preference weight increases preferred POI count from 2.48 to 4.09 (+64.9%, p<0.001), without degrading non-target objectives. These findings confirm that graduated weather treatment and user weight control together yield a more responsive and robust planning system.