In this seminar, Buğra Çınar will give a talk about Pricing, bundling, and compensation d ecisions in dynamic crowdsourced delivery problems.
Crowdsourc ed delivery leverages the unused transport capacity of vehicles alrea dy on the road to perform parcel deliveries. While it can potentially tackle challenges in urban delivery, it also introduces unique plann ing challenges, notably the operator’s lack of direct control over driver availability and acceptance behavior. Compensation, now, also is a decision of the operator, which affects drivers’ behavior. In addition, the operator can offer bundles of tasks, which further shap e drivers’ responses and increase the problem’s complexity. There fore, we study a setting in which tasks and drivers arrive dynamicall y and stochastically, explicitly model driver- and offer-dependent ac ceptance probabilities, and jointly determine bundles and compensatio n. We formulate the problem as a Markov Decision Process and solve it using Value Function Approximation within an Approximate Dynamic Pro gramming framework. Preliminary results show clear advantages over be nchmark policies.
DESCRIPTION: Crowdsourced delivery leverages the unused transport capa city of vehicles already on the road to perform parcel deliveries. Wh ile it can potentially tackle challenges in urban delivery, it also i ntroduces unique planning challenges, notably the operator’s lack o f direct control over driver availability and acceptance behavior. Co mpensation, now, also is a decision of the operator, which affects dr ivers’ behavior. In addition, the operator can offer bundles of tas ks, which further shape drivers’ responses and increase the problem ’s complexity. Therefore, we study a setting in which tasks and dri vers arrive dynamically and stochastically, explicitly model driver- and offer-dependent acceptance probabilities, and jointly determine b undles and compensation. We formulate the problem as a Markov Decisio n Process and solve it using Value Function Approximation within an A pproximate Dynamic Programming framework. Preliminary results show cl ear advantages over benchmark policies. In this seminar, Buğra Çın ar will give a talk about Pricing, bundling, and compensation decisio ns in dynamic crowdsourced delivery problems. END:VEVENT END:VCALENDAR