首页> 外文会议>Annual AGIFORS symposium >A Reinforced-Learning Approach for Calibrating Airlines Itinerary Choice Models with Constrained Demand
【24h】

A Reinforced-Learning Approach for Calibrating Airlines Itinerary Choice Models with Constrained Demand

机译:具有受约束需求的校准航空公司行程选择模型的加强学习方法

获取原文

摘要

1. Can we develop a model to replicate airlines competition and estimate demand for each itinerary, flight, and market? 1.1 What are itinerary choice models? 1.2 How itinerary choice models are calibrated? 2. What is wrong with the current models? 3. How to model the problem correctly? 4.Model accuracy and Sources of Error. 5. Prediction? 6. Conclusions. 1. Can We develop a Model to Replicate Airlines Competition? Knowing the following: 1. Origin-Destination (OD) demand and fares. 2. Flight schedule of all competing airlines. A logic to generate all competing itineraries from the flight schedule (itinerary builder). A logic to replicate how travelers select itineraries (itinerary choice models). Simulate travelers on the different itineraries using Monte Carlo simulation and keep track of full flights until all demand is loaded.
机译:1.我们可以制定模型,以复制航空公司竞争和对每个行程,航班和市场的需求吗? 1.1什么是行程选择模型? 1.2如何校准行程选择模型? 2.当前模型有什么问题? 3.如何正确模拟问题? 4.模型准确性和错误来源。 5.预测? 6。结论。 1.我们可以开发模型来复制航空公司竞争吗?知道以下内容:1。原始目的地(OD)需求和票价。 2.所有竞争航空公司的航班时间表。从航班时刻表(行程建设者)生成所有竞争行程的逻辑。复制旅行者选择行程(行程选择模型)的逻辑。使用Monte Carlo仿真模拟不同行程上的旅行者,并跟踪全部航班,直至加载所有需求。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号