Impact of Operational and Financial Efficiency on Aviation Stock Prices: A Machine Learning Model with SHAP Interpretability

Ahmet Akusta

doi:10.37880/cumuiibf.1560514

EN TR

Impact of Operational and Financial Efficiency on Aviation Stock Prices: A Machine Learning Model with SHAP Interpretability

Abstract

Using a machine learning approach, this study examines how operational and financial efficiency metrics influence stock prices in the aviation industry. A CatBoost regression model enhanced with SHapley Additive exPlanations (SHAP) was developed using data from 65 global aviation companies collected between 2015 and 2023. The model predicts stock prices based on various operational and financial indicators, including Total Revenue per Available Seat Mile (ASM), Passenger Load Factor, liquidity ratios, and debt-to-assets ratios. The findings suggest that operational efficiency metrics, particularly Total Revenue per ASM and Passenger Load Factor, play a significant role in predicting stock prices within the aviation sector. Financial metrics, such as the Quick Ratio and Debt-to-Assets Ratio, also contribute to the model but appear to have a secondary influence compared to operational factors. SHAP values provided interpretable insights into the model's predictions, allowing for a better understanding of the relative importance of different features. Furthermore, the study's findings offer support for the semi-strong form of the Efficient Market Hypothesis (EMH), demonstrating that operational and financial metrics are reflected in stock prices. These results indicate that aviation companies demonstrating higher operational efficiency may be better positioned for favorable stock market performance, although financial health remains important. This study contributes to the existing literature by integrating operational and financial metrics into a machine learning framework, offering a comprehensive and interpretable model for stock price prediction in the aviation industry.

Keywords

Operasyonel ve Finansal Verimliliğin Havacılık Hisse Senedi Fiyatları Üzerindeki Etkisi: SHAP Yorumlanabilirliğine Sahip Bir Makine Öğrenme Modeli

Öz

Bu çalışma, bir makine öğrenimi yaklaşımı kullanarak, operasyonel ve finansal verimlilik ölçütlerinin havacılık sektöründeki hisse senedi fiyatlarını nasıl etkilediğini incelemektedir. SHapley Additive exPlanations (SHAP) ile geliştirilmiş bir CatBoost regresyon modeli, 2015-2023 yılları arasında 65 küresel havacılık şirketinden toplanan veriler kullanılarak geliştirilmiştir. Model, Mevcut Koltuk Kilometre Başına Toplam Gelir (ASM), Yolcu Yük Faktörü, likidite oranları ve borç-varlık oranları dahil olmak üzere çeşitli operasyonel ve finansal göstergelere dayalı olarak hisse senedi fiyatlarını tahmin etmektedir. Bulgular, özellikle ASM başına Toplam Gelir ve Yolcu Yük Faktörü gibi operasyonel verimlilik ölçütlerinin havacılık sektöründeki hisse senedi fiyatlarının tahmininde önemli bir rol oynadığını göstermektedir. Hızlı oran ve borç varlık oranı gibi finansal ölçütler de modele katkıda bulunmakta ancak operasyonel faktörlere kıyasla ikincil bir etkiye sahip görünmektedir. SHAP değerleri, modelin tahminleri hakkında yorumlanabilir bilgiler sağlayarak farklı özelliklerin göreceli öneminin daha iyi anlaşılmasına olanak tanımıştır. Ayrıca çalışmanın bulguları, operasyonel ve finansal metriklerin hisse senedi fiyatlarına yansıdığını göstererek, Etkin Piyasa Hipotezi'nin (EPH) yarı-güçlü formunu desteklemektedir. Bu sonuçlar, finansal sağlık önemini korusa da, daha yüksek operasyonel verimlilik gösteren havacılık şirketlerinin olumlu borsa performansı için daha iyi konumlandırılabileceğini göstermektedir. Bu çalışma, operasyonel ve finansal ölçütleri bir makine öğrenimi çerçevesine entegre ederek havacılık sektöründe hisse senedi fiyat tahmini için kapsamlı ve yorumlanabilir bir model sunarak mevcut literatüre katkıda bulunmaktadır.

Anahtar Kelimeler

References

Aldabbas, M., Arabyat, Y. A., Al-Shawawreh, T. B., Alfalayeh, G. A., & Alqudah, M. Z. (2023). The role of information technology in raising the efficiency of Amman Stock Exchange mediated by the behavior of the stock prices. WSEAS Transactions on Business and Economics, 20, 1129–1143. https://doi.org/10.37394/23207.2023.20.101
Alici, A., Alici, A., & Sevil, G. (2022). Analysis of sector-specific operational performance metrics affecting stock prices of traditional airlines. Independent Journal of Management & Production, 13(2), 488–506. https://doi.org/10.14807/ijmp.v13i2.1777
Amankwah-Amoah, J. (2018). Why are so many African companies uncompetitive on the global stage? Insights from the global airline industry. Africa’s Competitiveness in the Global Economy, 195–216. https://doi.org/10.1007/978-3-319-67014-0_8
Arp, L., Baratchi, M., & Hoos, H. H. (2022). VPint: Value propagation-based spatial interpolation. Data Mining and Knowledge Discovery, 36(5), 1647–1678. https://doi.org/10.1007/s10618-022-00843-2
Astrup, R., Coates, K. D., & Hall, E. (2008). Finding the appropriate level of complexity for a simulation model: An example with a forest growth model. Forest Ecology and Management, 256(10), 1659–1665. https://doi.org/10.1016/j.foreco.2008.07.016
Babu, B. S., Venkat, K. M., Reddy, J. M., & Sai, K. R. (2022). Airline ticket price prediction. International Journal for Research in Applied Science and Engineering Technology.
Bhargav, B., & Prabu, R. T. (2023). Airline passenger satisfaction prediction using novel hybrid random forest model comparison with K-nearest neighbour model. 2023 Eighth International Conference on Science Technology Engineering and Mathematics (ICONSTEM), 1–6.
Bissessur, A., & Alamdari, F. (1998). Factors affecting the operational success of strategic airline alliances. Transportation, 25(4), 331–355. https://doi.org/10.1023/A:1005081621754

Briec, W., & Kerstens, K. (2004). A Luenberger-Hicks-Moorsteen productivity indicator: Its relation to the Hicks-Moorsteen productivity index and the Luenberger productivity indicator. Economic Theory, 23(4), 925–939. http://www.jstor.org/stable/25055794
Choudhary, A., Jagadeesh, R., Girija, E., Madhuri, M., & Shravani, N. (2023). Flyhigh: Machine learning-based airline fare prediction model. 2023 6th International Conference on Information Systems and Computer Networks (ISCON), 1–8.
De Myttenaere, A., Golden, B., Le Grand, B., & Rossi, F. (2016). Mean absolute percentage error for regression models. Neurocomputing, 192, 38–48. https://doi.org/10.1016/j.neucom.2015.12.114
Dewikristi Siallagan, S., & Prijadi, R. (2020). The impact of operational and financial hedging to the airline operating performance. KnE Social Sciences. https://doi.org/10.18502/kss.v4i6.6635
Dorogush, A. V., Ershov, V., & Gulin, A. (2017). CatBoost: Gradient boosting with categorical features support. Workshop on ML Systems at NIPS 2017. Retrieved from https://github.com/
Evans, A., & Schäfer, A. W. (2014). Simulating airline operational responses to airport capacity constraints. Transport Policy, 34, 5–13. https://doi.org/10.1016/j.tranpol.2014.02.013
Fama, E. F. (1970). Efficient capital markets: A review of theory and empirical work. The Journal of Finance, 25(2), 383–417.
Gimerská, V., Šoltés, M., & Mirdala, R. (2023). Improving operational efficiency through Quality 4.0 tool: Blockchain implementation and subsequent market reaction. Quality Innovation Prosperity, 27(2), 16–32. https://doi.org/10.12776/qip.v27i2.1877
Hancock, J. T., & Khoshgoftaar, T. M. (2020). CatBoost for big data: an interdisciplinary review. Journal of big data, 7(1), 94.
Hong, A. C. Y., Khaw, K. W., Chew, X., & Yeong, W. C. (2023). Prediction of US airline passenger satisfaction using machine learning algorithms. Data Analytics and Applied Mathematics (DAAM).
Huang, G. (2021). Missing data filling method based on linear interpolation and LightGBM. Journal of Physics Conference Series, 1754(1), 012187. https://doi.org/10.1088/1742-6596/1754/1/012187
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., ... & Liu, T. Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30.
Konar, J., Khandelwal, P., & Tripathi, R. (2020). Comparison of various learning rate scheduling techniques on convolutional neural network. 2020 IEEE International Students’ Conference on Electrical, Electronics and Computer Science (SCEECS 2020). https://doi.org/10.1109/SCEECS48394.2020.94
Köse, Y., & Yılmaz, E. (2023). An empirical research on the factors affecting profitability in air transportation. Sosyoekonomi, 31(58), 43–60. https://doi.org/10.17233/sosyoekonomi.2023.04.02
Kumar, D. S., Prem, S., Ashfaq, S. M., Rafiq, P. M., & Varma, C. N. (2023). Airline fare prediction using machine learning.
Labantová, L., & Begera, V. (2014). Financial, operational and economic indicators of airline operators. Faculty of Aeronautics, Technical University of Košice, 16(2).
Lee, B. L., Wilson, C., Pasurka, C. A., Fujii, H., & Managi, S. (2017). Sources of airline productivity from carbon emissions: An analysis of operational performance under good and bad outputs. Journal of Productivity Analysis, 47(3), 223–246. https://doi.org/10.1007/s11123-016-0480-4
Lee, J. (2019). Effects of operational performance on financial performance. Management Science Letters, 9(1), 25–32.
Lee, K. (2023). Airline operational disruptions and loss-reduction investment. Transportation Research Part B: Methodological, 177, 102817. https://doi.org/10.1016/j.trb.2023.102817
Lee, S., & Park, S.-B. (2013). A study on the association between operating leverage and risk: The case of the airline industry. International Journal of Economics and Finance, 6(3), 120. https://doi.org/10.5539/ijef.v6n3p120
Lee, S., Kim, H., & Lee, N. (2019). A comparative analysis of financial and operational performance pre-and post-IPO: With a focus on airline companies. Academy of Accounting and Financial Studies Journal, 23(3), 1–14.
Lopes, I. F., & Beuren, I. M. (2017). Comportamento dos custos e sua relação com medidas de eficiência operacional em companhias aéreas. BASE - Revista de Administração e Contabilidade Da Unisinos, 14(1), 30–46. https://doi.org/10.4013/base.2017.141.03
Lopes, I. T., Ferraz, D. P., & Rodrigues, A. M. G. (2016). The drivers of profitability in the top 30 major airlines worldwide. Measuring Business Excellence, 20(2), 26–37. https://doi.org/10.1108/mbe-09-2015-0045
Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems, 30 (pp. 4765–4774). Curran Associates, Inc.
Lundberg, S., Erion, G., & Lee, S.-I. (2018). Consistent individualized feature attribution for tree ensembles. ArXiv Preprint. https://doi.org/10.48550/arxiv.1802.03888
Mantin, B., & Wang, J.-H. (2012). Determinants of profitability and recovery from system-wide shocks: The case of the airline industry. Journal of Airline and Airport Management, 2(1), 1–33. https://doi.org/10.3926/jairm.2
McKinney, W. (2010). Data structures for statistical computing in Python. Proceedings of the 9th Python in Science Conference, 56–61. https://doi.org/10.25080/Majora-92bf1922-00a
McLean, D. (2005). Operational efficiency of commercial transport aircraft. Measurement and Control, 38(8), 243–248. https://doi.org/10.1177/002029400503800803
Nagesh, P., Naidu, K. B. J., Kowshik, P., & Sekhar, P. C. (2023). Airline ticket price prediction model. International Journal for Research in Applied Science and Engineering Technology.
Nohara, Y., Matsumoto, K., Soejima, H., & Nakashima, N. (2021). Explanation of machine learning models using Shapley additive explanation and application for real data in hospitals. ArXiv Preprint. https://doi.org/10.48550/arxiv.2112.11071
Okur, M., & Gurbuz, A. O. (2015). Behavioral finance in theory and practice. In Banking, Finance, and Accounting: Concepts, Methodologies, Tools, and Applications (pp. 18). IGI Global. https://doi.org/10.4018/978-1-4666-6268-1.ch016
Pamungkas, D. P., & Suhadak, S. (2017). The effect of jet fuel price and macroeconomics variables on profitability of airline industry in Asia (Study at airline companies in Indonesia, India, and China period 2006–2015). Jurnal Ekonomi Bisnis dan Kewirausahaan, 50(3), 208–217.
Panigrahi, R., Patne, N. R., Pemmada, S., & Manchalwar, A. D. (2022). Regression model-based hourly aggregated electricity demand prediction. Energy Reports, 8, 16–24. https://doi.org/10.1016/j.egyr.2022.10.004
Piranti, M. (2021). The impact of fuel price fluctuation and macroeconomic variables to airlines performance. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 12(3), 5486–5494.
Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V., & Gulin, A. (2018). CatBoost: unbiased boosting with categorical features. Advances in neural information processing systems, 31.
Putra, R. A. K., Persada, S. F., Kumalasari, R. D., Herdina, A. M., Sekardhani, M., & Razif, M. (2024). Operational cost efficiency and profitability effects on companies' distribution stock prices during COVID-19. Jurnal Manajemen Teknologi, 23(1), 76–90. https://doi.org/10.12695/jmt.2024.23.1.5
Rossi, M. (2015). The efficient market hypothesis and calendar anomalies: A literature review. International Journal of Managerial and Financial Accounting, 7(3/4), 285. https://doi.org/10.1504/IJMFA.2015.074905
Sachdeva, T. (2020). Managing shareholders in turbulent times: Evidence from Indian stock market. International Journal of Business and Globalisation, 25(3), 265. https://doi.org/10.1504/IJBG.2020.109005
Şahinbaş, K. (2022). Price prediction model for restaurants in Istanbul by using machine learning algorithms. Ekonomi İşletme ve Maliye Araştırmaları Dergisi, 4(2), 159–171.
Saranga, H., & Nagpal, R. (2016). Drivers of operational efficiency and its impact on market performance in the Indian airline industry. Journal of Air Transport Management, 53, 165–176. https://doi.org/10.1016/j.jairtraman.2016.03.001
Satter, S., Kwon, T.-H., & Kim, K.-D. (2023). A comparative analysis of various machine learning algorithms to improve the accuracy of HbA1c estimation using wrist PPG data. Sensors, 23(16), 7231. https://doi.org/10.3390/s23167231
Seufert, J. H., Arjomandi, A., & Dakpo, K. H. (2017). Evaluating airline operational performance: A Luenberger-Hicks-Moorsteen productivity indicator. Transportation Research Part E: Logistics and Transportation Review, 104, 52–68. https://doi.org/10.1016/j.tre.2017.05.006
Singh, J., Sharma, S. K., & Srivastava, R. (2019). What drives Indian airlines' operational expense: An econometric model. Journal of Air Transport Management, 77, 32–38. https://doi.org/10.1016/j.jairtraman.2019.03.003
Slater, P. J. (2023). Mind the GAAP: Determinants of U.S. airline operating cash flows. Journal of Academy of Business and Economics, 23(1), 74–84. https://iabe.org/IABE-DOI/article.aspx?DOI=JABE-23-1.6
Subramanian, R., Murali, M. S., Deepak, B., Deepak, P., Reddy, H. N., & Sudharsan, R. R. (2022). Airline fare prediction using machine learning algorithms. 2022 4th International Conference on Smart Systems and Inventive Technology (ICSSIT), 877–884.
Subramanyam, K. R., & Wild, J. J. (2016). Financial statement analysis (11th ed.). McGraw-Hill Education.
Sumerli Sarıgül, S., Ünlü, M., & Yaşar, E. (2023). Financial performance analysis of airlines operating in Europe: CRITIC-based MAUT and MARCOS methods. International Journal of Business and Economic Studies, 5(2), 76–97. https://doi.org/10.54821/uiecd.1257488
Sun, Y., Wong, A. K., & Kamel, M. S. (2009). Classification of imbalanced data: A review. International journal of pattern recognition and artificial intelligence, 23(04), 687-719.
Tanrıverdi, G., Merkert, R., Karamaşa, Ç., & Asker, V. (2023). Using multi-criteria performance measurement models to evaluate the financial, operational and environmental sustainability of airlines. Journal of Air Transport Management, 112, 102456. https://doi.org/10.1016/j.jairtraman.2023.102456
Wang, W.-K., Lu, W.-M., & Tsai, C.-J. (2011). The relationship between airline performance and corporate governance amongst U.S. listed companies. Journal of Air Transport Management, 17(2), 148–152. https://doi.org/10.1016/j.jairtraman.2010.06.005
Woo, K.-Y., Mai, C., McAleer, M., & Wong, W.-K. (2020). Review on efficiency and anomalies in stock markets. Economies, 8(1), 20. https://doi.org/10.3390/economies8010020
Wulansari, T., Suwardi, F., Firdaus, F., Purwanto, D., Hibatullah, Z., & Marganis, V. C. (2024). The influence of liquidity, productive asset quality and operational efficiency on company stock prices: Study of banks going public for the 2016–2020 period. International Journal of Economics and Management Sciences, 1(2), 19–28. https://doi.org/10.61132/ijems.v1i2.18
Xu, Y., & E, X. (2020). ARIMA based on linear interpolation for SO2 monitoring data’s calibration. Journal of Physics Conference Series, 1616(1), 012044. https://doi.org/10.1088/1742-6596/1616/1/012044
Yadav, D. K., & Goriet, M. O. (2022). An illustrative evaluation of external factors that affect performance of an airline. Journal of Aerospace Technology and Management, 14, 1122. https://doi.org/10.1590/jatm.v14.1253
Yilmaz, E., & Köse, Y. (2023). An empirical research on the factors affecting profitability in air transportation. Sosyoekonomi, 31(58), 43–60. https://doi.org/10.17233/sosyoekonomi.2023.04.02
Yongxin, L. (2009). Discussing on trend to efficient market hypothesis of securities and futures market. 2009 International Conference on Information Management, Innovation Management and Industrial Engineering, 3, 149–152.
Yüksel, B. (2023). Zaman serilerinde talep tahmini (Demand prediction in time series). YBS Ansiklopedi, 11(2), 1–18.
Zhang, Q., Koutmos, D., Chen, K., & Zhu, J. (2021). Using operational and stock analytics to measure airline performance: A network DEA approach. Decision Sciences, 52(3), 720–748. https://doi.org/10.1111/deci.12363
Zhao, Q., Wang, H., Luo, J.-C., Luo, M., Li, L., Yu, S.-J., Li, K., Zhang, Y., Sun, P., Tu, G.-W., & Luo, Z. (2021). Development and validation of a machine-learning model for prediction of extubation failure in intensive care units. Frontiers in Medicine, 8. https://doi.org/10.3389/fmed.2021.676343
Zou, L., Yu, C., & Dresner, M. (2015). Fleet standardization and airline performance. Journal of Transport Economics and Policy, 49(1), 149–166. https://www.jstor.org/stable/jtranseconpoli.49.1.0149

Details

Primary Language

English

Subjects

Finance

Journal Section

Research Article

Authors

Ahmet Akusta ^*
0000-0002-5160-3210
Türkiye

Early Pub Date

January 19, 2025

Publication Date

January 21, 2025

Submission Date

October 3, 2024

Acceptance Date

December 29, 2024

Published in Issue

Year 1970 Volume: 26 Number: 1

DOI

https://doi.org/10.37880/cumuiibf.1560514

IZ

https://izlik.org/JA65PU99XB

Cite

RIS / Bibtex

APA

Akusta, A. (2025). Impact of Operational and Financial Efficiency on Aviation Stock Prices: A Machine Learning Model with SHAP Interpretability. Cumhuriyet Üniversitesi İktisadi Ve İdari Bilimler Dergisi, 26(1), 167-182. https://doi.org/10.37880/cumuiibf.1560514

Cited By

POLİNOM REGRESYON KONTROLLÜ GERİLİM KİPLİ FLYBACK DÖNÜŞTÜRÜCÜ

Uludağ University Journal of The Faculty of Engineering

https://doi.org/10.17482/uumfd.1587544