TY - GEN
T1 - Large-Scale Data-Driven Airline Market Influence Maximization
AU - Li, Duanshun
AU - Liu, Jing
AU - Jeon, Jinsung
AU - Hong, Seoyoung
AU - Le, Thai
AU - Lee, Dongwon
AU - Park, Noseong
N1 - Funding Information:
Noseong Park is the corresponding author. This work of Jinsung Jeon, Seoyoung Hong, and Noseong Park was supported by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2020-0-01361, Artificial Intelligence Graduate School Program (Yonsei University)). The work of Thai Le and Dongwon Lee was in part supported by NSF awards #1909702, #1940076, #1934782, and #2114824.
Publisher Copyright:
© 2021 ACM.
PY - 2021/8/14
Y1 - 2021/8/14
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85114949266&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85114949266&partnerID=8YFLogxK
U2 - 10.1145/3447548.3467423
DO - 10.1145/3447548.3467423
M3 - Conference contribution
AN - SCOPUS:85114949266
T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
SP - 914
EP - 924
BT - KDD 2021 - Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
PB - Association for Computing Machinery
T2 - 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2021
Y2 - 14 August 2021 through 18 August 2021
ER -