From mobile-network data to mobility indicators
The mobility insights big-data platform processes anonymised network events — more than 2 Million per second — and produces more than 10 Million anonymous trips per day. These trips are trajectories that we describe in term of time, space and mode of transport. As we focus on collective mobility, we aggregate these trips into dynamic mobility indicators that describe minute by minute the mobility pulse of Switzerland. For example, we are able to quantify, for a given minute of the day, the number of highway and train trips that go through a given area. We are also able to build the associated distribution of origins and destinations. All results we share are k-anonymised to minimise the risk of re-identification.
Collecting ground-truth data
Benchmarking machine-learning algorithms requires data that associate samples with ground truth (actual label). This is challenging given that the machine learning task at hand is very specific with no public datasets available. We therefore decided to collect the data ourselves: we developed an application — only open to Swisscom employees with an explicit opt-in — that provides personalised mobility reports which describe the daily trips performed by the user as well as the associated CO2 footprint. At the same time, the user is able to provide feedback: She can rate the reconstructed trip, correct the origin and destination of each trip as well as the detected mode of transport.
Source : Medium & Swisscom
Resilience enhances the traditional risk management toolkit in several aspects, and insurance is an effective risk transfer mechanism that can contribute to increasing resilience. However providing insurance to a CI based on its resilience level is a complicated matter. Resilience is for systems, whereas insurance policyholders are companies, not systems. Beyond the fact that insurance can strengthen resilience and the assumption that resilience can improve insurability, many of the ‘needs’ from insurance relating to resilience come back to understanding and calculating risk. The SmartResilience Horizon2020 project (2017-2019) considered the problem of how to assess the resilience of a CI and developed a series of indicators and methods for that purpose. Then it considered the problems currently faced by the insurance sector and explored whether such methods could reduce vulnerability to consequences of disruptions, and provide better insurance coverage.
This paper briefly presents some of the outcomes of the SmartResilience project, focusing on (1) the extent to which insurance can enhance resilience, (2) how resilience can improve the conditions of insurability of CI, and (3) how SmartResilience methods can be used for that purpose. There exists a positive feedback mechanism.
Source : EPFL