BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Data-Driven Demand Prediction and Optimization for On-Demand Meal 
 Delivery Operations
DTSTART:20250307T110000
DTEND:20250307T120000
DTSTAMP:20260526T092349Z
UID:b7fe792d296a9958b6307b8aae641bac33d71130d039e1b914f3ffb7
CATEGORIES:Conferences - Seminars
DESCRIPTION:Rina (Jingyi) Cheng is a PhD candidate (2023–) at the Sustai
 nable Urban Multimodal Mobility (SUM) Lab at TU Delft\, co-supervised by D
 r. Shadi Sharif Azadeh\, Dr. ir. Gonçalo Correia\, and Prof. dr. Oded Cat
 s. She holds a BSc in Econometrics and Operations Research (Erasmus Univer
 sity Rotterdam\, 2021) and an MSc in Computational Science (University of 
 Amsterdam\, 2023). Her PhD\, part of the Horizon EU project SUM\, focuses 
 on real-time demand and availability predictions\, operations with learnin
 g-based approaches\, and complex-system-inspired solutions for shared micr
 o-mobility services.\nThe rapid growth of on-demand logistics and shared m
 obility services has underscored the need for intelligent decision-making 
 to enhance operational efficiency and service reliability. This talk prese
 nts data-driven solutions to address key challenges in short-term demand p
 rediction and real-time operations for meal delivery services. First\, I i
 ntroduce a predict-then-cluster framework that integrates distributional d
 emand forecasting with adaptive clustering to support dynamic service mana
 gement. Second\, I present a reinforcement learning-based dual-control str
 ategy for real-time order dispatching and idle courier rebalancing\, lever
 aging demand forecasts to optimize delivery efficiency and ensure fair wor
 kload distribution among contracted couriers. Beyond on-demand logistics\,
  these approaches also offer insights into their broader applicability for
  urban on-demand transportation services.\n\n 
LOCATION:GR A1 402 https://plan.epfl.ch/?room==GR%20A1%20402
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR