Developing practical models for capturing competitive effects in revenue management and pricing systems has been a significant challenge for airlines and other industries. The prevalent mechanisms of accounting for competitive effects rely on changing the price structure and making manual adjustments to respond to dynamically evolving competitive scenarios. Furthermore, micro-economic models have also not become popular in practice primarily because of the simplistic mechanisms proposed for modeling consumer behavior in a competitive setting. In particular, many of these models assume that the customers always seek the lowest price in the market, that is they are fully flexible. In practice, customers may display some degree of affinity or loyalty to an airline and may pay a premium for their preferred choice. On the other hand, almost all early revenue management models did not explicitly consider competitive effects and assumed that an airline’s demand only depends on their prices i.e., demand is fully dedicated to an airline (loyal). This paper develops a model to capture more realistic competitive dynamics by including both these types of customer behavior. We also develop a Bayesian machine learning based demand forecasting methodology for such models with explicit competitive considerations and show the benefit of this approach over traditional models on a real airline data set.

对于航空公司和其他行业而言，开发实用的模型以在收入管理和定价系统中获取竞争优势一直是一项重大挑战。衡量竞争效应的普遍机制依赖于改变价格结构并进行手动调整，以应对动态变化的竞争情景。此外，微观经济模型在实践中也未流行，主要是因为提出了在竞争环境中为消费者行为建模的简单机制。特别是，这些模型中的许多模型都假定客户始终在市场上寻求最低价格，也就是说，它们具有足够的灵活性。在实践中，客户可能对航空公司表现出一定程度的亲和力或忠诚度，并可能为他们的偏好选择支付溢价。另一方面，几乎所有早期的收入管理模型都没有明确考虑竞争影响，并假设航空公司的需求仅取决于其价格，即需求完全专用于航空公司（忠诚）。本文开发了一个模型，通过同时包括这两种类型的客户行为来捕获更现实的竞争动态。我们还针对此类模型开发了基于贝叶斯机器学习的需求预测方法，该方法具有明确的竞争考虑因素，并在真实的航空公司数据集上展示了该方法优于传统模型的优势。本文开发了一个模型，通过同时包括这两种类型的客户行为来捕获更现实的竞争动态。我们还针对此类模型开发了基于贝叶斯机器学习的需求预测方法，该方法具有明确的竞争性考虑因素，并在实际航空公司数据集上展示了该方法优于传统模型的优势。本文开发了一个模型，通过同时包括这两种类型的客户行为来捕获更现实的竞争动态。我们还针对此类模型开发了基于贝叶斯机器学习的需求预测方法，该方法具有明确的竞争考虑因素，并在真实的航空公司数据集上展示了该方法优于传统模型的优势。