Trajectories through temporal networks

Abstract What do football passes and financial transactions have in common? Both are networked walk processes that we can observe, where records take the form of timestamped events move something tangible from one node to another. Here propose an approach analyze this type data extracts actual trajectories taken by items involved. The main advantage analyzing resulting compared using, e.g., existing temporal network analysis techniques, is sequential, temporal, domain-specific aspects process respected retained. As a result, lets us produce contextually-relevant insights. Demonstrating usefulness technique, consider passing play within association matches (an unweighted process) e-money transacted mobile money system (a weighted process). Proponents providers care know how these systems used—using trajectory extraction find 73% was used for stand-alone tasks only 21.7% account holders built up substantial savings at some point during 6-month period. Coaches teams sports analysts interested strategies advantageous. Trajectory allows replicate classic results science on 2018 FIFA World Cup. Moreover, able distinguish consistently exhibited complex, multi-player dynamics 2017–2018 club season using ball trajectories, coincidentally identifying winners five most competitive first-tier domestic leagues Europe.