Good quality network connectivity is ever more important. For hybrid fiber coaxial (HFC) networks, searching for upstream high noise in the past was cumbersome and time-consuming. Even with machine learning due to the heterogeneity of the network and its topological structure, the task remains challenging. We present the automation of a simple business rule (largest change of a specific value) and compare its performance with state-of-the-art machine-learning methods and conclude that the precision@1 can be improved by 2.3 times. As it is best when a fault does not occur in the first place, we secondly evaluate multiple approaches to forecast network faults, which would allow performing predictive maintenance on the network.

National economies rest on networks of millions of customer-supplier relations. Some companies – in the case of their default – can trigger significant cascades of shock in the supply-chain network and are thus systemically risky. Up to now, systemic risk of individual companies was practically not quantifiable, due to the unavailability of firm-level transaction data. So far, economic shocks are typically studied in the framework of input-output analysis on the industry-level that can’t relate risk to individual firms. Exact firm-level supply networks based on tax or payment data exist only for very few countries. Here we explore to what extent telecommunication data can be used as an inexpensive, easily available, and real-time alternative to reconstruct national supply networks on the firm-level. We find that the conditional probability of correctly identifying a true customer-supplier link – given a communication link exists – is about 90%. This quality level allows us to reliably estimate a systemic risk profile of an entire country that serves as a proxy for the resilience of its economy. In particular, we are able to identify the high systemic risk companies. We find that 65 firms have the potential to trigger large cascades of disruption in production chains that could cause severe damages in the economy. We verify that the topological features of the inter-firm communication network are highly similar to national production networks with exact firm-level interactions.

In March 2020, the Austrian government introduced a widespread lock-down in response to the COVID-19 pandemic. Based on subjective impressions and anecdotal evidence, Austrian public and private life came to a sudden halt. Here we assess the effect of the lock-down quantitatively for all regions in Austria and present an analysis of daily changes of human mobility throughout Austria using near-real-time anonymized mobile phone data. We describe an efficient data aggregation pipeline and analyze the mobility by quantifying mobile-phone traffic at specific point of interest (POI), analyzing individual trajectories and investigating the cluster structure of the origin-destination graph. We found a reduction of commuters at Viennese metro stations of over 80% and the number of devices with a radius of gyration of less than 500 m almost doubled. The results of studying crowd-movement behavior highlight considerable changes in the structure of mobility networks, revealed by a higher modularity and an increase from 12 to 20 detected communities. We demonstrate the relevance of mobility data for epidemiological studies by showing a significant correlation of the outflow from the town of Ischgl (an early COVID-19 hotspot) and the reported COVID-19 cases with an 8-day time lag. This research indicates that mobile phone usage data permits the moment-by-moment quantification of mobility behavior for a whole country. We emphasize the need to improve the availability of such data in anonymized form to empower rapid response to combat COVID-19 and future pandemics.