By Mohammad Saffar, Arimo Time-series (longitudinal) data occurs in nearly every aspect of our lives; including customer activity on a website, financial transactions, sensor/IoT data. Just like in written text, specific events in a sequence of events are affected by the past and affect events in the future, and this can reveal a lot of hidden structure in the source of the events. Yet, today's predictive techniques largely rely on demographic (cross-sectional) data and do not take into account the sequences of events as they occur. In this session, Mohammad will discuss techniques for taking time-series data from a variety of domains and sources and grouping entities based on temporal behavior, using RNNs. These clusters of time-series sequences can either be visualized or used for campaign targeting in the case of user clickstream behavior or understanding stock symbols that behave similarly based on their trading behavior.