This project proposed a unified modeling framework for the traveller's choice of activity type, timing and duration. In the decision-making process, the traveler exhibits forward-looking behavior, i.e. the traveler realize the impact of the current choice on the future utility and take into account the future utility that he can obtain. Therefore, the activity scheduling behavior is formulated as a Markov Decision Process. Dynamic programming technique is adopted to solve solve the problem and maximum likelihood method is employed to estimate the model parameters.
Yiliang Xiong and William H.K. Lam. Modeling Within-day Dynamics in Activity Scheduling: A Markov Decision Process Approach. Journal of the Eastern Asia Society for Transportation Studies, Vol. 9 (2011), pp. 452--467, Fulltext.