• Version
• Download 83
• File Size 1.53 MB
• File Count 1
• Create Date 9 October 2024
• Last Updated 9 October 2024

RMGPT: Transformers as Revenue Managers - Prof Kalyan Talluri & Hanzhao Wang - Imperial College, London

Professor Kalyan and Hanzao outline their research into the use of Generative Pre-training Operational Research Transformer (GPT) models to solve sequential decision-making.     They first propose a general sequence modelling framework to capture a number of sequential decision-making tasks as special cases, such as dynamic pricing, inventory management, resource allocation, and queueing control. Under the framework, all these tasks can be viewed as a sequential prediction task where the goal is to predict the optimal future action given all the history information.      When trained, this model marks a paradigm shift compared to the existing methods for these OR/OM tasks, which offers distinct advantages over any existing models.

Attached Files