Log in

Disclaimer: the agenda serves for orientation purpose and is still subject of change

All times are in Santiago local time.


Start time Details
19:00 Welcome Reception  DoubleTree by Hilton Santiago - Vitacura

Monday, 22May23

Start time Details 



*Joint session crew & SSP


Keynote by Mr. Hernan Pasman, Chief Operations Officer, Latam Airlines Group

*Joint session crew & SSP


Coffee break


Technical presentation: Leveraging Cloud Deployments

by Remy Gauthier

More and more airline organizations are deploying their airline operations and crew management software in a dematerialized (cloud) environment, or are considering to do so. Cloud deployments offer a more flexible infrastructure than traditional on-premise, or offsite physical servers that is not limited by the number of physical CPUs and memory.

We are developing a product infrastructure that leverages the flexible nature of the cloud which allows for on-demand vertical and horizontal scaling.

We will introduce this software landscape and show how we are pushing the concept of service-based architectures to offer a highly flexible deployment model coupled with compute-on-demand capabilities.


Sponsor presentation: OffBlock 


Technical presentation: Workflow-based optimization approach to Crew and Alert Based Recovery problems

By Jaroslaw Pyzik

Fast, multidomain and what-if scenario-based recovery optimization is crucial for managing daily operations disruptions. While separate optimization solutions for aircraft routing and crew recovery exist, generating and applying solutions independently creates the risk of producing schedules that are misaligned and undeployable in real-life scenarios, or may are difficult to coordinate between departments or systems. For Alert Based Recovery, where a user needs an ad-hoc, local, and operable solution, running full-fledged optimizations may be (in some cases) too time consuming and unnecessary, introducing changes to existing schedules that may be cost optimal, but which are hard to trace and maintain within the short timeframe recovery window.

To address these problems, we propose a workflow-based optimization process that has the capability of running arbitrary problems with designated micro-strategies, optimization engines and cooperation between them. This allows the system to provide solutions for alerts affecting multiple domains, considering their dependencies.

With nested workflow definitions and feedback loops it is possible to run simulations and negotiate common solutions for passengers, aircraft and crew recovery. This optimizer workflow structure allows also for running multiple what-if scenarios (simulations), returning partial solutions once available, benchmarking, parameters tuning, black-box optimization (BBO) approach, utilizing optimizer engines in ML training pipelines selection and strategies models, and run reinforcement learning or GAN schemes to produce balanced solutions across optimization domains.

We will present our workflow-based optimization framework used to build optimization pipeline for coordinated, scale agnostic, aircraft, crew and Alert Based Recovery optimization, and AI/ML approaches for dispatching, subproblem selection and optimization strategies


Sponsor presentation: NavBlue




Technical presentation: Workforce with career progression planning and training optimization

By Oliver Weide

As airlines face increased requirements and resource constraints, ensuring coverage of all crew tasks, including pairings, training, and more, workforce planning is critical to their operations. The workforce planning process strategically aligns crew tasks with crew capacity to know when happen hiring, training, and career progression should over time based on flying demand flying demand, attrition, fleet structure and growth. We developed a mathematical model to solve this problem. The model is a mixed integer linear program that minimizes the piecewise linear approximation of the quadratic difference between requirements and capacity. Our model creates an optimal training schedule with career progression across ranks and fleets. The model supports different levels of granularity (e.g., weekly or monthly), rules modeling, block hours, and credit limits. The model also considers resource constraints such as the availability of simulators and instructors. We will discuss the model's capabilities, limitations, and future evolution to support holistic workforce planning. Using our model, the workforce planner can focus on comparing many possible options rather than putting effort into constructing a scenario manually.




Technical presentation: FTL Effectiveness. How much lower risk? At what cost?

by Tomas Gustafsson (deputising Tomas Klemets)

Is it at all possible to measure how effective regulatory rules are? Such as the rules governing work and rest time for pilots coming from EASA, FAA and the CAAC? Jeppesen, in collaboration with SWISS, another prominent international airline operator, a large space agency, and the British Airline Pilots Association (BALPA) has set out to do so. In this presentation we will share our findings regarding the improvements made to the EASA rules when stepping over from Subpart Q to the current ones. We have constructed a vast data pool of realistic work patterns built from real flights schedules, using the typical production tools many operators use, and planned the production only governed by regulation. The work patterns that emerged have then been assessed in terms of both fatigue risk and crew efficiency to determine FTL Effectiveness - and the results are not entirely what the industry may have hoped for or expected. This is, to date, the largest and most detailed attempt at quantifying effectiveness of regulatory rules using the best representation of science available to us. The structured approach, and the vast amount of data now available, opens for several novel ways of improving regulatory rules going forward.

Tomas Klemets is a seasoned expert in airline crew management processes, with over 20 years of experience in the field. He currently serves as the Head of Scheduling Safety at Jeppesen, where he has consulted with over 100 airline operators worldwide. Tomas is responsible for the development of the Jeppesen fatigue risk management portfolio, which includes the pioneering R&D behind the Boeing Alertness Model. In his current role, Tomas leads a cross-functional DevOps team that is dedicated to bridging the gap between science, regulation, flight safety, and the integration of capabilities into the construction process for crew rosters. His focus is on reducing risk and improving crew wellbeing. Tomas is a frequent speaker at international conferences and has an impressive number of publications and news postings to his name. He is widely recognised for his expertise in the field and is a sought-after speaking partner for airlines seeking to improve their crew management processes.


Sponsor presentation: WePlan


Coffee break


Sponsor presentation: API


Technical presentation: A linear mixed-integer programming approach based on an event-activity network for personalized airline crew scheduling

By Marius Krömer and Cornelia Schön

We present an arc-based linear mixed-integer programming (MIP) approach to personalized airline crew scheduling that integrates the commonly sequential steps of crew pairing and crew assignment. In the sequential approach, global optimality can hardly be achieved, and crew preferences are considered only in the second step where the flexibility to take crew desires into account is very limited. Therefore, increasing attention has been paid to the integration of crew pairing and assignment in recent years, and a few promising path-based approaches have been developed; as centerpiece they embed column generation (CG) into a heuristic branch-and-bound search in a reduced, single-branch search tree. However, the CG subproblems are still hard to solve, and the CG master problem often suffers from degeneracy such that dynamic constraint aggregation techniques need to be applied.

Our arc-based model is based on an event-activity network in time and space, where flight legs and other activities are directly assigned to individual crew members, taking crew preferences (e.g., for vacation days, flights, etc.) and all common regulatory rules for flight time limitations into account. Despite these complexities, our MIP formulation still allows to preserve linearity of the relaxation, even if sophisticated and originally non-linear cost functions (e.g., including cost terms for (not) flying, waiting and deadheads) commonly used in North American markets are considered as an objective.

The model can be solved exactly for small instances with standard solvers, and we propose a rolling-planning heuristic for solving medium- to large-sized instances. Our approach can be used as a stand-alone alternative or as a complement to existing approaches, e.g., for generating good starting solutions for CG-based methods. Numerical experiments with published test instances show that our approach is promising in terms of solution time and quality. 


Sponsor presentation: CAE


Modeling Crew Itineraries and Delays in the National Air Transportation System

by Vikrant S. Vaze

We propose, optimize, and validate a methodological framework for estimating the extent of the crew-propagated delays and disruptions (CPDDs). We identify the factors that influence the extent of the CPDDs and incorporate them into a robust crew-scheduling model. We develop a fast heuristic approach for solving the inverse of this robust crew-scheduling problem to generate crew schedules that are similar to real-world crew-scheduling samples. We develop a sequence of exact and heuristic techniques to quickly solve the forward problem within a small optimality gap for network sizes that are among the largest in robust crew-scheduling literature. Computational results using four large real-world airline networks demonstrate that the crew schedules produced by our approach generate propagation patterns similar to those observed in the real world. Extensive out-of-sample validation tests indicate that the parameters calibrated for one network perform reasonably well for other networks. We provide new insights into the perceived trade-off between planned costs and delay costs as reflected by actual airline crew schedules. Finally, we present a general approach to estimate the CPDDs for any given network using our methodological framework under a variety of data availability scenarios.


Networking Dinner @ DoubleTree by Hilton Santiago - Vitacura

Tuesday, 23May23

 Start time Details 

Sponsor presentation: IBS Software


Crew Rosters Customization : How to replace a Crew Request System-based by a Preferential Bidding System-based after +20 years of habits ?

by Tristan Thiebaut and Stephen Bail

When listening to Crew Members, everyone loves more personalization in their rosters, but when you addressing more than +12.000 Cabin Crew Members with an average seniority of 20 years with a strong habits on current system then Change Management becomes a high challenges to tackle and one of the major stake in such a PBS deployment.

Since 2019, Air France has initiated the deployment of a new PBS System across its Cabin Crew Members and has put Change Management in the heart of this Transformation Program with a high crew-centric, and collaborative approach on top of usual technical and IT challenges.

We will be pleased to present how Air France is leading this Change Management Strategy and how key it is to enroll Crew Members in such a significant transformation program for their lifestyle.


Sponsor presentation: VeeOne


Coffee break


Technical presentation: Crew Scheduling & Fatigue Risk Management. How can we, as Crew Management, contribute to mitigate the Fatigue Risk in our operations?

By Hector Berrocal


Empowering your Manpower Planning Team Post-COVID: Must-Haves

by Franziska Burmester

Join us for an insightful discussion on the must-haves for empowering your manpower planning team post-COVID. We have onboarded various teams to use our WePlan platform for manpower planning and have observed similar challenges across our clients. These range from the continuous workload of simulating scenarios to staff shortages in the planning team, as well as inefficient digital fluency and procedural and organizational challenges.

We will delve into the solutions to these challenges and offer actionable steps to transform your manpower planning team. Discover how our WePlan platform can support this transformation and help your team become more efficient and effective in the post-COVID era. Don't miss this opportunity to learn from our experiences and take your manpower planning to the next level.

Franziska Burmester is co-founder of WePlan, a company based in Frankfurt. WePlan offers a web-based SAAS solution for Manpower Planning which enables the planning team to create cost-optimal plans and overcome planning silos.

Before founding WePlan, Franziska has broad experience in consulting in the TT&L industry where she supported clients in improving workforce productivity and digitalize their planning process for more than 8 years. Franziska holds a bachelor degree in Economics and Tourism. 


Technical presentation: study results in crew management training standards

By Selina Fothergill and Chrystal Zhang


Panel discussion: Have airlines given up on their digital business transformations?

Moderator: Daniel Stecher of IBS Software




Networking Event & Diner - Viñamar vineyard

Planned end around 22:00

Wednesday, 24May23

 Start time  Details

Sponsor presentation: Boeing


An evaluation of decision support systems to measure the effectiveness of software products for crew management in the aviation industry of India

By Vineet Kumar Saraswat

The aviation industry worldwide is an extremely competitive industry, and its most focused area is "making air travel as safe for consumers as possible" but at the same time managing crew resources optimally. Airlines procure various software solutions for their crew management that helps them to maintain all rules and regulations while managing crew for their duties and aims for cost saving for company.

Procuring or inducting a system for crew management without analyzing its relevance and completeness for the department and company that is also not strategically chosen can cause an unreasonable amount of pressure on key stakeholders such as crew, operation management and its users. Managing the operation with workarounds due to the gap in requirements and the procured solution results in many indirect costs for the company.

This presentation is on the study that analyzes how various solutions can be compared with airlines desired system and try to answer the golden question "Is this system the most suitable system for the crew resource management department of the airline”.


Technical presentation: Practical Applications of Machine Learning on Roster Data: Predicting Absences and Measuring Satisfaction

By Joao Batista (on behalf of Karim Maarouf)

Crew roster data in its raw form is quite challenging to make use of. However, transforming this data into an easily accessible format and combining that with the application of machine learning techniques unlocks its huge potential.

In this talk, we explore the application of machine learning algorithms on crew roster data. We will share some of the challenges and insights from our work on the OPSD project at Swiss. We will demonstrate how integrating crew roster data into a cloud analytical platform provides opportunities enabled by machine learning to improve operations. We focus on two use cases, namely predicting crew absences and measuring crew satisfaction. However, that is certainly not the end of the story. Once data is integrated and organized, this enables rapid ideation and prototyping of other use cases. The benefits are limited only by the creativity in applying some of these advanced techniques. We also discuss some considerations and lessons learned from this journey.


Sponsor presentation: TA Connections


Coffee break


Sponsor presentation: Lufthansa Systems 


Technical presentation: Innovation in crew rostering: standby’s, fairshare distribution and pre-assignments

by Steven Rushworth

We have developed a new crew rostering system that is now in production at several airlines. The pairing and rostering, typically separate steps in crew scheduling, are now calculated simultaneously in a single run. Our system generates personalized pairings for each crew member that take into account their preferences and preassigned activities. This leads to roster with a lower cost and a higher blockhour/duty hour ratio.

Based on these foundations we were able to continue to innovate and push the boundaries even further. Some of the recent innovations are:

  • The standby planning is now integrated in the calculation. If a crew member executes a standby, there is no snow-ball effect on the remainder of his/her schedule. A single plan that includes all duties and standby duties is calculated in one shot.
  • As a preprocessing step we can identify the critical pre-assignments, such as a training course, a meeting or SIM duty, that can cause challenges in the scheduling problem. By rapidly identifying these pre-assignments, we can suggest alternatives that will lead to a more efficient roster.
  • Having personalized pairings allows a better fair share distribution of the work. For example, the number of nights away from base or block hours / week can be better distributed amongst the available crew members. Similarly, we can also take better into account the crew duty history to distribute the work more evenly over longer periods of time

During this talk we will discuss the details of this approach and discuss the benefits it brings for the operations and crew.


Technical presentation: Otra: Fully Automated and Optimized Training Assignment at Qatar Airways

by Marcel Sol

This is a tale of a journey Qatar Airways embarked on to go from fully manual assignment of all the traininge for our pilots and cabin crew to a situation where the entire process and all trainings are assigned in a fully automated, but also fully optimized manner. 

This journey is full of rocks, brick walls and even football fields. We will see them all along the way... But Like any story, this too will (hopefully) have a happy end. 




Technical presentation: Balancing Risk and Cost: A Data-Driven Approach to Standby Scheduling

by Kitty Oosterveer and Youandi van der Tang

*Joint session crew & SSP

We are excited to present our findings on how to schedule standby crew members more effectively at the upcoming AGIFORS Crew Management Conference in Santiago, Chile. Our team at KLM Crew Planning and Assignment has utilized historical data to improve the determination of required standby crew members.

We understand the importance of having standby crew members available to handle unexpected situations, such as last-minute cancellations due to crew absence or aircraft-type swaps. However, we also recognize the significant cost associated with scheduling standby crew members who are not being used. Through our analysis of historical utilization of standby crew members and trends in crew absence, we have been able to more accurately estimate the need for standby crew members at specific days and times. This allows us to schedule standby crew members more precisely for future production, thereby reducing overall costs and increasing standby efficiency.

During this presentation, we will share our methodology and results, and provide insights on how other airlines can apply similar techniques to improve their own standby scheduling practices.


Technical presentation: Retiming for robustness

By Tomas Gustafsson

*Joint session crew & SSP

An airline schedule is a living thing evolving through several phases, with more or less changes. Traditionally Crew Planning has been done under the assumption that the schedule is fixed, with the discussion between Network and Crew Planning primarily being on whether it could be operated at all.

Some years ago we introduced a capability in Crew Pairing allowing the optimizer to suggest minor schedule changes in order to improve the solution, while taking most slot and aircraft routing related constraints into account. This has had significant positive impact for some airlines, being used both in strategic and tactical planning, and sometimes resulting in several percentages of efficiency improvements. More recently, we introduced an approach for using patterns in historical delay data to more surgically assign operational buffers in Crew Pairing, giving gains in productivity and/or robustness. Here, we will for the first time share results for what could be achieved by combining the two ideas. Will the added flexibility of retiming flights open up unexpected opportunities in increasing robustness, or will the two approaches combined give diminishing returns?


A Robust Pairing Model for Airline Crew Scheduling

By Vikrant S. Vaze

*Joint session crew & SSP

Delays and disruptions in airline operations annually result in billions of dollars of additional costs to airlines, passengers, and the economy. Airlines strive to mitigate these costs by creating schedules that are less likely to get disrupted or schedules that are easier to repair when there are disruptions. In this paper, we present a robust optimization model for the crew pairing problem, which generates crew schedules that are less likely to get disrupted. Our model allows adding robustness without requiring detailed knowledge of the underlying delay distributions. Moreover, our model allows us to capture in detail the delay propagation through crew connections and the complex cost structure of the pay-and-credit crew salary scheme, thus enabling us to find a good trade-off between the deterministic component of the planned costs on the one hand and the expected delay and disruption costs on the other hand. Our robust crew pairing model is based on a deterministic crew pairing model formulated as a mixed-integer linear program. The robust version that we propose retains the linearity of the constraints and objective function and thus can be handled by commercial solvers, which facilitates its implementation in practice. We propose and implement a new solution algorithm for solving our model to optimality. Several optimal solutions with varying robustness levels are compared for the network of a moderate-size airline in the United States. We test the model’s solutions in a simulation environment using real-world delay data. Our simulation results show that the robust crew pairing solutions lead to lower delays and fewer instances of operational infeasibilities, thus requiring fewer recovery actions to address them. We find that, with the inclusion of robustness, it is possible to generate crew pairing solutions that significantly reduce the delay and disruption costs with only a small increase in planned costs.


Technical presentation: Pilot Supply Challenges in the United States

By John Pepper and Josephine Dietrich

*Joint session crew & SSP

Our presentation would cover the current state of pilot supply challenges in the United States, provide our forecast for both pilot demand and pilot supply, provide context/data on the drivers of pilot supply / demand, and show the impact that the lack of pilot supply is having on both domestic and international recovery from COVID. We would also present proposed solutions for the various bottlenecks in the pilot supply pipeline. While our research is most applicable for US market the ramifications are being felt around the world.


Coffee break 


Awards for "best presentation" and "best innovation"

Conference recap and farewell 

*Joint session crew & SSP

Powered by Wild Apricot Membership Software