科学研究

李想，北京理工大学教授/博导，国家优青、国家青拔，研究领域包括数据驱动决策、数智交通管理等，主持国家自然科学基金重点类项目3项；荣获省部级奖励9项、国家级行业协会奖励6项，出版英文专著2部，主编教材2部，发表论文 160 余篇，授权专利40项；现任SCI期刊International Journal of General Systems主编。

内容摘要：

This paper studies the capacity management of ride-hailing services with unstable passenger demand. In the existing parametric approaches, normally a two-stage prediction-then-optimization (PTO) paradigm is used to implement demand prediction and capacity management sequentially, which generally achieves suboptimal performance due to the information loss in demand prediction. To attain optimality, in this study, we integrate these two stages into a prediction & optimization (P&O) paradigm, and formulate a deep learning approach consisting of a weighted sample average approximation (WSAA) module and VMD-CNN-BiLSTM-AM1 (V-CBA) module, where the WSAA module embeds with knearest neighbors, kernel regression or a decision tree to select significant historical samples, and the V-CBA module couples decomposition, convolution, recursion, attention, and optimization together for complex nonlinear mapping. Based on real-world datasets, the deep learning-based P&O paradigm is demonstrated to have superior performance in capacity management of ride-hailing services.

联系人：智慧民航科创中心，吴一璇

编辑：袁晓慧