Abstract

Networks have provided novel insights across a wide variety of research areas, however, many real world systems are in fact a “network of networks”, or a multilayer network, which interact as parts of a greater, multimodal whole. In this talk, we discuss two research problems in multilayer networks. First, to detect possible cryptocurrency fraud, in particular market manipulation, previous research focused on the detection of changes in the network of trades; however, market manipulators are now trading across multiple cryptocurrency platforms, making their detection more difficult. Hence, it is important to consider the identification of changes across a ‘network of networks’ over time. To this end, we propose a new change-point detection method, labeled TenSeg, in the network structure of tensor-variate data. We apply our method to several simulated datasets and to a cryptocurrency dataset, which consists of network tensor-variate data from the Ethereum blockchain. Second, transportation networks provide information to people on how to efficiently travel between locations. To date, most research in transportation networks focused on only one mode of transportation, consequently they were unable to understand the entire transportation network as an integrated system. To this end, we propose a multilayer network framework for transportation and apply it to the ten selected cities' public transportation systems. We visualize these networks using our newly designed curated R package, and analyze these networks from the perspective of inter-layer connections and other network characteristics. Furthermore, we apply a community detection algorithm for future station planning. Finally, the multilayer networks allow us to predict housing prices across the cities using machine learning in order to find undervalued properties in the market.