Search

As the COVID-19 pandemic motivated a shift to virtual teaching, exams have increasingly moved online too. Detecting cheating through collusion is not easy when tech-savvy students take online exams at home and on their own devices. Such online at-home exams may tempt students to collude and share materials and answers. However, online exams' digital output also enables computer-aided detection of collusion patterns. This paper presents two simple data-driven techniques to analyze exam event logs and essay-form answers. Based on examples from exams in social sciences, we show that such analyses can reveal patterns of student collusion. We suggest using these patterns to quantify the degree of collusion. Finally, we summarize a set of lessons learned about designing and analyzing online exams.

Eco-labels are a way to benchmark transportation shipments with respect to their environmental impact. In contrast to an eco-labeling of consumer products, emissions in transportation depend on several operational factors like the mode of transportation (e.g., train or truck) or a vehicle's current and potential future capacity utilization when new orders are added for consolidation. Thus, satisfying eco-labels and doing this cost efficiently is a challenging task when dynamically routing orders in an intermodal network. In this paper, we model the problem as a multiobjective sequential decision process and propose a reinforcement learning method: value function approximation (VFA). VFAs frequently simulate trajectories of the problem and store observed values (violated eco-labels and costs) for states aggregated to a set of features. The observations are used for improved decision making in the next trajectory. For our problem, we face two additional challenges when applying a VFA, the multiple objectives and the "delayed" realization of eco-label satisfaction due to future consolidation. For the first, we propose different feature sets dependent on the objective function's focus: costs or eco-labels. For the latter, we propose enhancing the suboptimal decision making and observed pessimistic primal values within the VFA trajectories with optimistic dual decision making when all information of a trajectory is known ex post. This enhancement is a general methodological contribution to the literature of approximate dynamic programming and will likely improve learning for other problems as well. We show the advantages of both components in a comprehensive study for intermodal transport via trains and trucks in Europe. History: This paper has been accepted for the Transportation Science Special Section on 2021 TSL Workshop: Supply and Demand Interplay in Transport and Logistics. Funding: A. Heinold's work is funded by the Deutsche Forschungsgemeinschaft (DFG) [Project 268276815]. M. Ulmer's work is funded by the Emmy Noether Programme of the DFG [Project 444657906]. This support is gratefully acknowledged. Supplemental Material: The online appendix is available at https://doi.org/10.1287/trsc.2022.1164. [ABSTRACT FROM AUTHOR]