Title Mašininio mokymosi algoritmų taikymas kelionių planavime /
Translation of Title Machine learning algorithm application in trip planning.
Authors Gadliauskas, Grantas
Full Text Download
Pages 55
Keywords [eng] travelling salesman problem ; flight search ; combinatorial optimization ; neural network
Abstract [eng] This paper describes a software system module for a travel trip planning solution and the research conducted into how machine learning can be applied to optimally generate trip deals. The solution is a unique one, since it requires no direct input from the user to generate the trip results and is solely driven by the created algorithm. It allows for its end users to save time and hassle of manually searching for flights between multiple destinations by offering attractive prepared trip offers. The research part of the work explores how machine learning can be applied in efficiently solving a variation of the Travelling Salesman Problem (TSP) in the context of air travel tourism. Large number of cities create too many trip route combinations to be efficiently evaluated in real time. The method proposed uses a feedforward neural network to narrow down the number of trip route combinations, while a more traditional algorithm based on dynamic programming is then able to select the best trip offers. It was shown that the method can be applied in practice to achieve almost real-time generation of best possible trip offers while evaluating a large amount of real-world flight data.
Dissertation Institution Kauno technologijos universitetas.
Type Master thesis
Language English
Publication date 2022