INFORMS 2021 Program Book

INFORMS Anaheim 2021

WD10

prescriptive analytics methods to enhance airline planning and operations decisions. 3 - Airline Network Planning: Mixed-integer Non-convex Optimization with Demand-supply Interactions Mattia Cattaneo, University of Bergamo, Salmine, Italy, Alexandre Jacquillat, Sebastian Birolini, António Pais Antunes Airlines routinely use analytics tools to support flight scheduling, fleet assignment, revenue management, crew scheduling, and many other operational decisions. However, decision support systems are less prevalent to support strategic planning. This paper fills that gap with an original mixed-integer non- convex optimization model, named Airline Network Planning with Supply and Demandinteractions (ANPSD). The ANPSD optimizes network planning (including route selection, flight frequencies and fleet composition), while capturing interdependencies between airline supply and passenger demand. We first estimate a demand model as a function of flight frequencies and network configuration, using a two-stage least-squares procedure fitted to historical data, and then formalize the ANPSD by integrating the empirical demand function into an optimization model. The model is formulated as a non-convex mixed-integer program. To solve it, we develop an exact cutting plane algorithm, named 2 ECP, which iteratively generates hyperplanes to develop an outer approximation of the non-linear demand functions. Computational results show that the 2 ECPalgorithm outperforms state-of-the-art benchmarks and generates tight solution quality guarantees. A case study based on the network of a major European carrier shows that the ANPSD provides much stronger solutions than baselines that ignore—fully or partially—demand-supply interactions. 4 - Long-term Crew Planning For Airlines Burak Cankaya, Assistant Professor, Embry Riddle Aeronautical University, Daytona Beach, FL, United States Pilots and aircrafts are the most valuable assets of an airline company. Union rules, pilot shortage/surplus, cost of employing an excessive number of pilots are existing constraints for airline operator companies almost all around the world. Under these harsh circumstances, many companies cannot plan the allocating of pilotsto aircraft strategically to meet near-future goals and mid/long future company objectives. In this study, we are optimizing the required crew to fleet allocation over the years with a dynamicapproach that the company both protects the most senior pilots and minimizes the pilot costs with a hybrid MIP and Heuristic apprach. WD14 CC Room 201B In Person: Statistical Learning and Decision Making General Session Chair: Yunzong Xu, Massachusetts Institute of Technology, Cambridge, MA, 02139-4204, United States Co-Chair: Yunbei Xu, Columbia Business School, Columbia Business School, New York, NY, 10027-6945, United States 1 - Towards Optimal Problem Dependent Generalization Error Bounds in Statistical Learning Theory Yunbei Xu, Columbia Business School, New York, NY, 10027-6945, United States, Assaf Zeevi We study problem-dependent rates, i.e., generalization errors that scale near- optimally with the variance, the effective loss, or the gradient norms evaluated at the “best hypothesis.” We introduce a principled framework dubbed “uniform localized convergence,” and characterize sharp problem-dependent rates for central statistical learning problems. From a methodological viewpoint, our framework resolves several fundamental limitations of existing uniform convergence and localization analysis approaches. It also provides improvements and some level of unification in the study of localized complexities, one-sided uniform inequalities, and sample-based iterative algorithms. 2 - Estimating Mixture Models in Consumer Segmentation Yiqun Hu, Massachusetts Institute of Technology, Cambridge, MA, United States, Zhenzhen Yan, David Simchi-Levi Mixture models are used in various fields to capture different sources of uncertainties. In the setting of revenue management, market demand is an aggregate of each individual’s choice probabilities. Consumers with different preferences will be driven by different choice models. To predict market demand accurately, the key is to accurately estimate the underlying mixture choice models, which remains an open research question. We propose a non-parametric estimation method based on the Frank-Wolfe algorithm to segment consumers and further apply the calibrated consumer segmentation to price optimization problem an important application in revenue management. Convergence result and sample complexity is provided for the proposed estimation method and numeric tests are conducted to demonstrate the efficiency of the proposed algorithms.

WD10 CC Room 304B In Person: Auction Markets General Session Chair: Martin Bichler, Technical University of Munich, Garching B. München, 85748, Germany 1 - Revenue Maximization for Consumer Software: Subscription or Perpetual License? Ludwig Dierks, University of Zurich, Binzmühlestrasse 14, Zurich, CH-8050, Switzerland, Sven Seuken We study the revenue maximization problem of a publisher selling consumer software. We assume that the publisher sells either traditional perpetual licenses, subscription licenses, or both. For our analysis, we employ a game-theoretic model, which enables us to derive the users’ equilibrium strategies and the publisher’s optimal pricing strategy. Via extensive numerical evaluations, we then demonstrate the sizable impact different pricing strategies have on the publisher’s revenue, and we provide comparative statics for the most important settings parameters. Although in practice, many publishers still only sell perpetual licenses, we find that offering a subscription license in addition to a perpetual license typically (but not always) leads to significantly higher revenue than only selling either type of license on its own. 2 - Core-Stability in Assignment Markets with Financially Constrained Buyers Martin Bichler, Technical University of Munich, Boltzmannstr. 3, Garching, 85748, Germany We consider auctions of indivisible items to unit-demand bidders with budgets. Without financial constraints and pure quasilinear bidders, this assignment model allows for a simple ascending auction format that maximizes welfare and is incentive-compatible and core-stable. Introducing budget constraints, the ascending auction requires strong additional conditions on the unit-demand preferences to maintain its properties. We show that without these conditions, there does not exist an incentive-compatible and core-stable mechanism. Even if bidders reveal their valuations and budgets truthfully, the allocation and pricing problem becomes an NP-hard optimization problem. The analysis complements complexity results for more complex valuations and raises doubts on the efficiency of simple auction designs in the presence of financially constrained buyers. WD11 CC Room 304C In Person: Airline Operations Management General Session Chair: Burak Cankaya, Embry Riddle Aeronautical University, Lake Mary, FL, 32746, United States 1 - Sortation Network in Cargo Airlines Chieh-hsien Tiao, Amazon, Dallas, TX, 75235, United States Cargo airlines differ from passenger airlines in many aspects, among them, how packages connect through the transportation network is most significant. Sortation provides a guidance to the connecting process. However, sorting for destinations too far out creates too many small “channels” that waste resources; while sorting for destinations too close by provides chance to consolidate but each sorting slow down the entire transportation process. We present a solution to select sortation strategies so maximal number of packages can flow through the network while maintain satisfiable performance. 2 - Enhancing Day-ahead Airline Planning with Data-driven Flight Delay Predictions Sebastian Birolini, University of Bergamo, Dalmine (BG), 24044, Italy, Alexandre Jacquillat, Stephanie Franklin, Gabrielle Rappaport Flight delays are the major drivers of disruptions and unexpected costs in airline operations. It is therefore of paramount importance to get visibility into flights’ delays as early as possible and as accurately as possible, in order to minimize their overall impact. In this paper, we collaborate with Vueling Airlines to build predictive models of flight delays and enhance day-ahead planning decisions accordingly. We first assemble a large-scale database of flight-level observations, using airline-specific features, system-wide features, and environmental features. Using a quantile regression model, we estimate minimum turnaround times for each pair of flights and reconstruct each flight’s primary (as opposed to propagated) delay. We then develop machine learning models to predict primary delays. Our best model, based on extreme gradient boosting, achieves a mean absolute error of 7-8 minutes—a significant improvement as compared to baseline models using simpler machine learning methods or simpler sets of predictors. Finally, we embed our data-driven delay predictions into a tail assignment model to support day-ahead planning. Out-of-sample results demonstrate that leveraging the proposed predictive model can reduce overall delay costs by 3-5%. Ultimately, this paper shows the potential of combining advanced predictive and

WD16

168