Current Market Outlook

Boeing

Boeing continues to look to the future with our Current Market Outlook (CMO) publication, which is Boeing’s long-term forecast of passenger and cargo traffic and the number of airplanes necessary to support that expected demand. Our Current Market Outlook is one of the longest-published forecasts in the aviation industry and has proven to be among the most accurate.  As the global economy and markets evolve, so must the focus of our industry forecasts. In 2017, Boeing expanded the CMO to include all of the services required to support the operation of commercial aviation products around the world. The outlook for the commercial support and services market is covered in depth in Boeing’s new Services Market Outlook (SMO). Both the CMO and SMO provide key forecast metrics as well as insights and supporting analysis. This presentation will review Boeing’s latest CMO and SMO forecasts and Boeing’s view of the current market environment and future of aviation and the importance of aviation services to the industry.

An Innovative and Efficient Solution Methodology to Integrated Fleet Assignment Problem

Sabre Inc.

Fleet assignment deals with assigning an equipment type to a leg to best match seat capacity with passenger demand and maximize profit. Two steps are involved. Demands are generated by airline's forecasting system based on an input schedule and are fed to Fleet Assignment Model (FAM) which changes the assignment on a leg or cancels a leg. The benefit to integrate the two systems is significant. Canceling or reducing capacity of a leg can have significant impact on other legs. Models that consider origin and destination effect and integrate other aspects of demand forecasting systems have been proven to be very hard to solve. In this presentation we explore the root cause of intractability of such problems and propose an efficient solution methodology to integrated FAM. Proposed method has been tested on O&D FAM and improvement compared to leg FAM is significant. This methodology provides a framework to fully integrate airline forecasting system and FAMs.

Models to Support Scheduling Decisions in a Complex Network: Fleet Assignment Model as an Example

American Airlines

After a merger with US Airways in 2013,  the new American Airlines, operating in 9 hubs and flying to 350 destinations in 50 countries, became the largest airline in the world by its fleet size and passenger carried. In the presentation, we discuss a set of new challenges to effective scheduling brought about by the broad scale of the combined network. One major challenge is to solve a big network problem efficiently given a set of complex constraints. Another important one is to build practical models that streamline and automate manual business processes, while fully integrating into the schedule generation process. It is essential to understand the difference between optimality of the model solution and effectiveness of the results from the business standpoint (“acceptable optimality”).  A certain level of gap to optimality is imperative for obtaining quick turnaround with a big problem.  

Forecasting passengers using designer machine learning

Air France - KLM

Predictions for the number of airline passengers that will board a particular flight have a variety of uses, including revenue management, fuel planning, the anticipation of no-shows or excess hand luggage, and catering supply chain management. In this talk, we outline the business requirements for a passenger forecast system, formalize the machine learning problem at hand, discuss ways to evaluate model candidates, and subsequently advance through a series of tailor-made algorithms with increasing complexity. From shortcomings of each model candidate, we introduce a new modular improvement to the algorithm, moving from a simple linear model to more sophisticated deep learning neural network architectures. We intersperse conceptual model design with snippets of Python code to provide practical handles. In conclusion, we briefly delineate some open modeling challenges associated with this use case.

Market Demand Stimulation

Boeing

Airlines evaluate existing networks and the demand across O&D markets unserved by a non-stop route to seek out new markets to serve.  When a new nonstop service is added, airlines assume capture of a certain percentage of the existing O&D demand.  Solely accounting for existing O&D demand underestimates the true demand an airline will realize.  New markets stimulate additional demand (e.g., BA’s AUS-LHR route commencing March 2014).  When helping an airline evaluate new markets, Boeing has a specific approach to estimate new market demand stimulation.  We will review Boeing’s approach and a few examples of new market demand stimulation.

Network Dependency Ratio

Air France - KLM

For airlines based on a hub system, the different routes of the network feed each other to generate connecting traffic flows. In Air France, the medium haul network has the key role to feed the long haul one. LH revenues from MH connections are very significant; therefore, they should be reflected in MH performances.

A model to compute the NDR (Network Dependency Ratio) value was created to achieve that. When a MH route is cut, some seats on LH flights will be vacated and generate available capacity to capture the LH demand that used to be spilled (from other connections LH-LH or LH-MH or Local LH). The idea of the NDR is to compute the ratio of the non-recapturable part of revenue and passengers with respect to the expected loss without recapture when a MH route or a MH flight gets cut. NDR can help ranking all MH routes and flights to understand to what extent the whole network depends on them.

Regulation of Frequent Flyer Programs on an International Scale: A Pilot Study for Turkish Airlines

Embry Riddle Aeronautical University

Airline alliances work perfectly for paid flight segments, but there are difficulties for passengers who want to redeem flight miles. Airlines mostly decline requests for award mile seats, not only from their partner airline’s customers but also from their own customers. To overcome the problems associated with redeeming award seats on flights requires a global regulation of the system. In this pilot study, we propose a new quantitative approach, Frequent Flyer Money Saver (FFMS) analysis, that can be used to identify obstacles to redeeming award seats for Turkish Airlines. After obtaining  the study results , the FFMS analysis will be used for to find the optimum system that has the best FFMS ratio for all flag carrier aviation companies under airline alliances. Then I will propose standardizing global frequent flyer redemption system regarding to the properties of this airline. Because of this the business volume of aviation-related industries might increase.

Airline Timetable Development and Fleet Assignment Incorporating Passenger Choice

Dartmouth College, Carnegie Mellon University

We present an original integrated optimization approach to comprehensive timetabling and fleet assignment. Passenger choice is captured by a linearized version of a multinomial logit model integrated into our modeling framework. The resulting model, despite being a mixed-integer linear (rather than a nonlinear) optimization model, is still highly intractable by commercial solvers due to its extremely large size. We develop an original set of multi-phase solution approaches to optimize the network-wide timetable of a major airline carrier within a realistic computational budget. From a practical standpoint, our framework provides decision-support for airlines interested in generating their timetables from scratch, evaluating or enhancing their existing timetables, or analyzing various business strategies such as contemplating or executing mergers and acquisitions, etc. Furthermore, we demonstrate the value of integrating timetabling decisions with other important planning steps, such as frequency planning, to improve the overall profitability of the airline. 

Balancing Commercial and Operational KPIs in Aircraft Routing for GOL

Jeppesen

Most airlines use standard flight scheduling products to generate aircraft routings, also for the monthly planning. At Jeppesen, we regard aircraft routing as a process of its own. The standard process of treating aircraft routing as a special case of the scheduling process, and applying the same tools as used for the long-term planning leads to that opportunities for bot increased revenue and improved operational performance are overlooked. Jeppesen has worked together with GOL to use a dedicated aircraft routing optimizer to optimize its operation. The results show both increased sat capacity in key markets and improved operational performance. This presentation describes the process together with results from GOL.

New Market Ramp Up

American Airlines

When a carrier introduces a new nonstop service, especially an international market; it is often believed that it will take some time for the new service to achieve its full revenue potential, as public awareness will increase over time through advertisements, and relationships with travel agents may take time to mature. The ramp up effect is considered in many analyses including revenue performance estimates and new market selection studies, but has been mostly a subjective, based on anecdotal evidence. Our study is an attempt to construct an objective, data driven model for the ramp up effect.

Joint Session, SSP and Airline Ops - Wednesday, May 23rd:

Resilient Airline Scheduling and Operations - Optimizing on-time performance based on delay risk prediction

Lufthansa Systems

Flight schedules regularly get disrupted on the day of operations by events that were unforeseeable at the time when the schedule was built. While this can hardly be avoided, we aim to minimize delay risks on a standard day of operations. Delays caused by special events or irregularities (e.g. major technical defects, thunderstorms) cannot be taken into account by scheduling, they have to be addressed in a later process phase by ops control. Scheduling can aim at reducing the impact of minor disruptions by allocating buffer times in the right places in order to avoid propagation of delays in a rotation.

Scheduling requires block- and ground times balancing productivity and punctuality. These planning parameters should be as long as needed to be punctual, but should not be too generous thus influencing negatively the profitability of an airline. Based on historic operations data most suitable block- and ground times are defined. In addition typical constellations leading to systematic delays are identified and buffered by applying appropriate buffer on the ground.

Using operations data from different airlines over several years, we predict the lengths of ground and block times of typical operations days. Based on simulation results we assess the delay risk for each leg in a given rotation to support the scheduler in his daily work, thus enabling him to reduce the number of situations with high delay risks.

To further support scheduling in reducing delay critical situations we developed different optimizers using metaheuristic methods from the field of artificial intelligence. Starting from a given flight schedule, the aircraft routing is changed in order to improve the delay resilience as predicted by the simulation. With reasonable computation time, a significant improvement of the optimization objective can be achieved after a few iterations. By allowing small time shifts of flights, the delay risks of a schedule can be significantly decreased further.

Robust Airline Scheduling with Optimal Block and Ground Times

Optym

Airlines solve their schedule planning problem considering a little or no stochasticity and to maximize their profitability. Highly optimized schedules show an opposite trend in terms of operational metrics such as On Time Performance (OTP). We develop a simulation-based approach to measure the operability of a given schedule under various uncertainties. Schedule optimizers try to balance tradeoff between the time allocated on ground vs. flying time. Insufficient or excess ground time and block time can cause expensive delays or under-utilization of assets respectively. We aim to distribute right contingency at right places so that optimal OTP can be achieved at minimal cost. We apply an iterative framework using a mixed integer programming formulation and updating its parameters based on the simulation results. We test our approach using a major U.S. airline's daily schedule and obtain 1.81% increase in OTP without a significant decrease in profit.

Improving On-Time Performance through Robust Routing

JetBlue Airways

The talk will focus on explaining how the on-time performance and maintenance requirements can be improved with the help of robust aircraft routing. A mixed integer problem is formulated and solved which prioritizes the routes with higher buffer time in the ground turn around leg while adhering to maintenance requirements. Application of the model to the airline's schedules shows that at average 8% of the ground turn legs can be relaxed from having the minimum turn around time and can be provided an additional 10 to 20 minutes of buffer time. The maintenance schedule of the aircrafts also improves as the aircrafts touch the maintenance base more frequently with ground time long enough to carry out the periodic maintenances. All these benefits are realized without changing the schedule times therefore not requiring reduction to the aircraft utilization ratio.

Human Plus Artificial Intelligence for Robust Block Time Forecasting

FICO

Accurate block time forecasts are critical to building a reliable and profitable schedule. However, as these two metrics are opposing in nature, the planner has to balances the tradeoffs between reliability and profitability in the plan. In this talk, we present a different and novel approach to forecasting block times using Machine Learning. FICO uses historical on-time performance data and external data such as weather and airport operations to build out a feature set. Using this, we build, tune, and evaluate multiple Machine Learning models. We provide levers to the planner to then analyze the results and find the sweet spot that balances the tradeoffs between OTP and utilization before coming up with the final planned block time. As this is not a one-time exercise, we will present a decision support platform that allows the planner to work collaboratively with the ML algorithms and their human colleagues to rapidly iterate towards optimal planned schedules

Misconnect Passenger Analysis using a Visual Platform

United Airlines

Misconnecting passengers cause difficulties for our hub locations resulting in rebooking costs, protection issues, over sale situations, and reputation damage.  With a constantly moving schedule, irregular operations, and multiple connection opportunities, it is difficult to consume the large amounts of data to identify the problem(s) in misconnections.  As a result, we have developed an interactive and visual tool to help stations track progress, find most critical misconnecting city pairs, analyze past events, and recommend realistic minimum connection times based on history, location, time of day, and domestic/international types of connections.  This tool not only focuses on the immediate problem, but also the larger solution of adequately using data visualization to help identify, explain, and solve complex problems.

Leveraging Data Science to Find Punctuality Quick Wins

Air France - KLM

Punctuality has always been a major issue for carriers. Multiple business objectives tend to create and propagate delays such as decreased aircraft turn-around times to improve aircraft usage, or peaked hub activities to improve the intrinsic connectivity of networks. Our study aimed at comprehensively using Air France historical data to make out best practices that could be shared broadly. Using state-of-the-art data science techniques, we ended up following two tracks that lead us to determine simple operational levers to enhance punctuality (or at least theoretically).