English

Large-Scale Data-Driven Airline Market Influence Maximization

Machine Learning 2021-06-01 v1

Abstract

We present a prediction-driven optimization framework to maximize the market influence in the US domestic air passenger transportation market by adjusting flight frequencies. At the lower level, our neural networks consider a wide variety of features, such as classical air carrier performance features and transportation network features, to predict the market influence. On top of the prediction models, we define a budget-constrained flight frequency optimization problem to maximize the market influence over 2,262 routes. This problem falls into the category of the non-linear optimization problem, which cannot be solved exactly by conventional methods. To this end, we present a novel adaptive gradient ascent (AGA) method. Our prediction models show two to eleven times better accuracy in terms of the median root-mean-square error (RMSE) over baselines. In addition, our AGA optimization method runs 690 times faster with a better optimization result (in one of our largest scale experiments) than a greedy algorithm.

Keywords

Cite

@article{arxiv.2105.15012,
  title  = {Large-Scale Data-Driven Airline Market Influence Maximization},
  author = {Duanshun Li and Jing Liu and Jinsung Jeon and Seoyoung Hong and Thai Le and Dongwon Lee and Noseong Park},
  journal= {arXiv preprint arXiv:2105.15012},
  year   = {2021}
}

Comments

Accepted by KDD 2021

R2 v1 2026-06-24T02:39:49.170Z