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

Aug 5, 2026

Using a machine learning framework, the study analyzes how operational and financial efficiency metrics affect stock prices in the aviation industry. A CatBoost regression model with SHAP (SHapley Additive exPlanations) interpretability is built from data covering 65 global aviation companies from 2015 to 2023. Predictions rely on operational indicators such as Total Revenue per Available Seat Mile (ASM) and Passenger Load Factor, alongside liquidity and leverage measures. Results show operational efficiency features dominate, while financial metrics contribute secondary effects, and SHAP provides interpretable feature importance. Findings support the semi-strong form of the Efficient Market Hypothesis by linking efficiency information to market prices.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Abstract

Introduction

Motivation and context

Related empirical evidence

Methodology

Model and interpretability approach

Data and variables

Operational efficiency indicators

Financial efficiency indicators

Results and findings

Feature importance via SHAP

Interpretation for stock price prediction

Conclusion

Implications for market efficiency

Journal of Economics and Administrative Sciences │ [esjournal.cumhuriyet.edu.tr](esjournal.cumhuriyet.edu.tr) │ Founded: 2000 Available online, ISSN: 1303-1279 Publisher: Sivas Cumhuriyet Üniversitesi Impact of Operational and Financial Efficiency on Aviation Stock Prices: A Machine Learning Model with SHAP Interpretability Ahmet Akusta1,a,* ¹ Rectorate, Konya Technical University, Konya, Türkiye *Corresponding author Research Article ABSTRACT History Received: 03/10/2024 Accepted: 29/12/2024 JEL Codes: G12, G32, C45 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: Aviation stock prices, machine learning, SHAP values, operational efficiency, CatBoost Operasyonel ve Finansal Verimliliğin Havacılık Hisse Senedi Fiyatları Üzerindeki Etkisi: SHAP Yorumlanabilirliğine Sahip Bir Makine Öğrenme Modeli Süreç Geliş: 03/10/2024 Kabul: 29/12/2024 Jel Kodları: G12, G32, C45 Copyright This work is licensed under Creative Commons AttributionNonCommercial 4.0 International License International License ÖZ Bu çalışma, bir makine öğrenimi yaklaşımı kullanarak, operasyonel ve finansal verimlilik ölçütlerinin havacılıksektöründeki hisse senedi fiyatlarını nasıl etkilediğini incelemektedir. SHapley Additive exPlanations (SHAP) ile geliştirilmiş bir CatBoost regresyon modeli, 2015-2023 yılları arasında 65 küresel havacılık şirketinden toplananveriler 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 roloynadığını göstermektedir. Hızlı oran ve borç varlık oranı gibi finansal ölçütler de modele katkıda bulun makta ancak operasyonel faktörlere kıyasla ikincil bir etkiye sahip görünmektedir. SHAP değerleri, modelin tahminlerihakkında 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

FAQs

What modeling approach does the paper use to link efficiency metrics to aviation stock prices?

It develops a CatBoost regression model enhanced with SHAP interpretability to predict stock prices from operational and financial indicators.

Which factors most strongly influence the model’s predictions according to the findings?

Operational efficiency metrics—especially Total Revenue per ASM and Passenger Load Factor—play a significant role, while financial metrics like Quick Ratio and Debt-to-Assets Ratio have secondary influence.

How does SHAP contribute to understanding the predictions?

SHAP values provide interpretable insights into which features matter most, enabling a clearer view of the relative importance of different operational and financial variables.

Aug 5, 2026

Upload by Genevieve