Classical Machine Learning For Airline Passenger Satisfaction : Evaluative Study
Ness Ichhaporia
12๐กโ Grade, Delhi Public School Surat Surat, India
47-53
Vol: 14, Issue: 4, 2024
Receiving Date:
2024-09-23
Acceptance Date:
2024-11-01
Publication Date:
2024-11-08
Download PDF
http://doi.org/10.37648/ijrst.v14i04.005
Abstract
In the highly competitive aviation industry Customer satisfaction is key to building brand loyalty and reputation. The airline therefore gives importance to every touchpoint. From booking to baggage collection to exceed passenger expectations and stand out in the market. We have used 4 best-known classical machine learning models: Random Forest, LightGBM, Catboost, XGBoost and compared them in order to find the best model. To further investigate we used SHAP for qualitative analysis. In our research we found out that the most important feature contributing to customer satisfaction is type of travel.
Keywords:
customer satisfaction; classical machine learning; SHAP
References
- https://www.kaggle.com/datasets/teejmahal20/airline-passenger- satisfaction
- Mosca, E., Szigeti, F., Tragianni, S., Gallagher, D. and Groh, G., 2022, October. SHAP-based explanation methods: a review for NLP interpretability. In Proceedings of the 29th international conference on computational linguistics (pp. 4593-4603).
- Josephat, Peter, and Abbas Ismail. 'A logistic regression model of customer satisfaction of airline.' International Journal of Human Resource Studies 2.4 (2012): 197.
- Park, E., Jang, Y., Kim, J., Jeong, N.J., Bae, K. and Del Pobil, A.P., 2019. Determinants of customer satisfaction with airline services: An analysis of customer feedback big data. Journal of Retailing and Consumer Services, 51, pp.186-190.
- Apampa, Olatunji. 'Evaluation of classification and ensemble algorithms for bank customer marketing response prediction.' Journal of International Technology and Information Management 25, no. 4 (2016):
- A. Ghatnekar and A. D. Shanbhag, 'Explainable, Multi-Region Price Prediction,' 2021 International Conference on Electrical, Computer and Energy Technologies (ICECET), Cape Town, South Africa, 2021, pp. 1-7, doi: 10.1109/ICECETS2533.2021.9698641.
- Ali, Peshawa Jamal Muhammad, Rezhna Hassan Faraj, Erbil Koya, Peshawa J. Muhammad Ali, and Rezhna H. Faraj. 'Data normalization and standardization: a technical report.' Mach Learn Tech Rep 1, no. 1 (2014):
- Patel, Krish, and Aakash Shanbhag. 'Exploring ML for Predictive Maintenance Using Imbalance Correction techniques and SHAP.' In 2022 International Conference on Electrical, Computer and Energy Technologies (ICECET), pp. 1-10. IEEE, 2022.
Back
