At first, we run the case studies with a small network setting.
Fig. 6 Jupyter notebook running the case study workflow.
LVB implemented the approach and ran the case studies.
The rejected model was therefore run using the case study data i.e. including agency and excluding state.
We used a longer run for the case study (50,000 iterations after a 150,000 burn-in).
As a runnable demonstration of the workflow, we also provide a virtual machine with a complete setup including a Jupyter [35, 36] notebook for running and replicating the case study.
Do its obligations to help ensure financial stability trump all others?The case study runs for several hours.
The case study is run over 640 stages, with 1 stage representing 1 day.
As the number of segments increases, the benefit of this selective approach increases exponentially, and it is in fact required for the algorithm to run in a reasonable time for the case study dataset.
This screenshot shows the case study workflow running in a Jupyter notebook inside the virtual machine provided with the case study.
