Miriam O’Callaghan^1,2*, Dineshkumar K Balasubramanian², Farahnaz Behgounia², Neha Shukla², Priyansha Jayaswal² and Bahman Zohuri^2,3,4

¹William Woods University, School of Business and Technology, Fulton, Missouri, USA
²Golden Gate University, Ageno School of Business, San Francisco, Business Analytics School, USA
³Galaxy Advanced Engineering, A Consulting Firm, Albuquerque, New Mexico, USA
⁴Computer Science and Electrical, Computer Engineering, International Technological University, San Jose, California, USA

*Corresponding Author: Miriam O’Callaghan, William Woods University, School of Business and Technology, Fulton, Missouri, USA.

Received: April 12, 2021; Published: June 03, 2021

Abstract

Airline industry worldwide, has reported significant losses as demand for air travel declined due to COVID 19 pandemic. In 2021, the situation seems to have improved a little and therefore airlines are expecting demand to increase. This is the time when airlines can restore their economic viability. For airlines to be profitable again, they need to maximize their profits while optimizing prices and charging the best price for each airline ticket. Pricing decisions can be highly time consuming and cumbersome since each day, you might need to adjust these prices depending upon the demand. Most of the times, demand cannot be accurately determined. Another challenge for profit maximization is cost estimation. Certain costs cannot be predicted, and cost is an important component of profit equation.

Considering all the pricing challenges and current situation, we have created two models for airlines. Model 1 can be used by airlines in situation where they do not have cost estimates. This model can be used in both uniform and variable demand situations. Model 2 on the other hand, is recommended to be used when the airline can estimate its costs. Both these models optimize prices, provide recommendations on best prices and how much revenue an airline can earn at each price point.

With Artificial Intelligence (AI) and its sub-systems, such as Machine Learning (ML) and Deep Learning (DL), this article of short review, is taking advantages of integration and augmentation of AI, ML and DL, by writing a simple Python algorithm to be able to predict certain cost of operation and considering for airline price optimization analytics. Using two proposed models in this research, airlines can still manage their profitability. This article was induced based on a class project at Golden Gate University under supervision of Prof. B. Zohuri and team of students named in above as participants and collaborators in this project.

Keyword: Airlines; Cost Effective; Artificial Intelligence; Machine Learning; Deep Learning; Price Optimization; Data Analytics and Predictive; Common Separated Value (CSV) Data

References

1. Zohuri B and Zadeh S. Artificial Intelligence Driven by Machine Learning and Deep Learning, Nova Science Pub Inc (October 22, 2020), first edition (2020).
2. Bohr A and Memarzadeh K. “The rise of artificial intelligence in healthcare applications”. Artificial Intelligence in Healthcare (2020): 25-60.
3. Ibid
4. Haydon D., et al. “Industries Most and Least Impacted by COVID19 from a Probability of Default Perspective” (2021).
5. Sabre Airline Solutions. “Why Airlines need to Let Their Pricing Strategies Tell Their Story” (2017).
6. Pande R (n.d.). “The Benefits of Price Optimization”.
7. Gargi N. “Wondered how airlines price their tickets? Optimizing Airline Revenue Management and Ticketing with Artificial Intelligence” (2018).
8. Abdella J A., et al. “Airline Ticket Price and Demand Prediction: A survey”. Journal of King Saud University - Computer and Information Sciences (2019).
9. Santos B F., et al. “Optimizing the prices for airline flight passes”. Transportation Research Procedia 37 (2019): 266-273.
10. Campbell P. “Why You Can’t Afford To Overlook To Optimizing Your Pricing” (2020).
11. Zoto G. “Kaggle Mini Courses - Airline Price Optimization Microchallenge” (2020).
12. Brons M., et al. “Price elasticities of demand for passenger air travel: a meta-analysis”. Journal of Air Transport Management 3 (2002): 165-175.

Citation

Citation: Miriam O’Callaghan., et al. “Prescriptive Analytics for Airline Price Optimization Driven by Artificial Intelligence and Machine Learning, and Excel Spread Sheet Algorithms". Acta Scientific Pharmaceutical Sciences 5.7 (2020): 20-29.

Copyright

Copyright: © 2021 Miriam O’Callaghan., et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.