This paper analyzes the impact of the December 2022 winter storm on Southwest Airlines (SWA). The storm caused delays and cancellations for all airlines, but SWA was the only major airline that was unable to recover fully. The disruption was unique due to the higher volume of people traveling during the holiday season and the lack of good alternative transportation for stranded passengers. The paper explains SWA's point-to-point (PTP) model, which allows them to offer competitive ticket prices, and organizational factors that have helped them hold a significant market share. The paper also discusses previous failures of SWA's IT and aircraft maintenance management systems and the outdated crewing system, which were not addressed until after the storm. The paper uses AnyLogic agent based modeling to investigate why SWA was so affected and why it took them so long to recover.
Motivated by the need for efficient active learning strategies, this dissertation proposes new algorithms for batch-mode, pool-based active learning. The research considers the following questions: how can unsupervised knowledge of the input features (exploration) improve learning when incorporated with supervised learning (exploitation)? How to characterize exploration in active learning when data is high-dimensional? Finally, how to adaptively make a balance between exploration and exploitation?
The first contribution proposes a new active learning algorithm, Cluster-based Stochastic Query-by-Forest (CSQBF), which provides a batch-mode strategy that accelerates learning with added value from exploration and improved exploitation scores. CSQBF balances exploration and exploitation using a probabilistic scoring criterion based on classification probabilities from a tree-based ensemble model within each data cluster.
The second contribution introduces two more query strategies, Double Margin Active Learning (DMAL) and Cluster Agnostic Active Learning (CAAL), that combine consistent exploration and exploitation modules into a coherent and unified measure for label query. Instead of assuming a fixed clustering structure, CAAL and DMAL adopt a soft-clustering strategy which provides a new approach to formalize exploration in active learning.
The third contribution addresses the challenge of dynamically making a balance between exploration and exploitation criteria throughout the active learning process. Two adaptive algorithms are proposed based on feedback-driven bandit optimization frameworks that elegantly handle this issue by learning the relationship between exploration-exploitation trade-off and an active learner's performance.
The CDS model and methodologies are integrated into an architecture using concepts from cognitive computing. The proposed architecture is implemented with an example use case to inventory management.
Reinforcement learning (RL) is discussed as an alternative, generalized adaptive learning engine for the CDS system to handle the complexity of many problems with unknown environments. An adaptive state dimension with context that can increase with newly available information is discussed. Several enhanced components for RL which are critical for complex use cases are integrated. Deep Q networks are embedded with the adaptive learning methodologies and applied to an example supply chain management problem on capacity planning.
A new approach using Ito stochastic processes is proposed as a more generalized method to generate non-stationary demands in various patterns that can be used in decision problems. The proposed method generates demands with varying non-stationary patterns, including trend, cyclical, seasonal, and irregular patterns. Conventional approaches are identified as special cases of the proposed method. Demands are illustrated in realistic settings for various decision models. Various statistical criteria are applied to filter the generated demands. The method is applied to a real-world example.
The first problem is a route assignment and scheduling problem in which a set of vehicles need to traverse a directed network while maintaining a minimum inter-vehicle distance at any time. This problem is inspired by applications in hazmat logistics and the coordination of autonomous agents. The proposed approach includes realistic features such as continuous-time vehicle scheduling, heterogeneous speeds, minimum and maximum waiting times at any node, among others.
The second problem is a fixed-charge network design, which aims to find a minimum-cost plan to transport a target amount of a commodity between known origins and destinations. In addition to the typical flow decisions, the model chooses the capacity of each arc and selects sources and sinks. The proposed algorithms admit any nondecreasing piecewise linear cost structure. This model is applied to the Carbon Capture and Storage (CCS) problem, which is to design a minimum-cost pipeline network to transport CO2 between industrial sources and geologic reservoirs for long-term storage.
The third problem extends the proposed decomposition framework to a special case of joint chance constraint programming with independent random variables. This model is applied to the probabilistic transportation problem, where demands are assumed stochastic and independent. Using an empirical probability distribution, this problem is formulated as an integer program with the goal of finding a minimum-cost distribution plan that satisfies all the demands with a minimum given probability. The proposed scalable algorithm is based on a concave envelop approximation of the empirical probability function, which is iteratively refined as needed.