Machine Learning Technique based Trip Planning System - TripMa

Abstract

Travel planning is a tedious task to engage from the perspective of travelers since it involves crucial and critical decision-making due to a lack of foreign geography and cultural knowledge. Initially, the concept of traveling through travel agencies was used and it was slowly diminishing due to the fact of freedom and exploration are too constant and bounded according to the organizer's perspective. The proposed model overcomes almost all existing challenges and removes the traveler's local knowledge gap by using the dynamic prediction and recommendation features. The proposed system has identified the importance of grouping or the sharing expectation of a traveler through mapping out the best matching companions along with identification of tourist attractions and the best time to visit those places, which also included safety precaution methodologies to the travelers, which provide them the capabilities of preparing and mitigating the potential risks along with the traveling areas. The inclusion of the user feedback analysis model will impact identifying the user's perspective of the system and ensures users' trust towards the system, The system has iteratively used location-based knowledge through third-party APIs such as GOOGLE MAP API. The below sections will describe and illustrate the modes of machine learning techniques used, weighted models, and the NLP data mining methodologies used to acquire the systems architecture.