Personalized Travel Recommendation and AI Itinerary Planning for Mobile Applications: A Literature Review

Planning a trip is not just choosing a place. A traveller also has to think about interests, number of days, budget, weather, travel time and the order of places to visit. Today, people check these things on different websites and apps, which takes time. This paper reviews existing research on personalized travel recommendation, selection of tourist places, itinerary making, route planning and the use of large language models (LLMs) for trip planning. The studies use methods such as collaborative filtering, machine learning, neural networks and optimization. One common finding is that suggestions are better when the user's preferences are used along with current details like location, season, weather and budget. Another finding is that a plan must be practical, which means distance, time limits and the order of visits must be checked. LLMs let users ask for a trip in simple language, but their answers must still be checked with correct data. Most studies solve only one part of travel planning. So this paper points out the need for one mobile app that combines destination search, itinerary help, budget estimate, weather, maps, trip saving and a chatbot.