Event-triggered causality: a causality detection tool for big data

Abstract

Finding causal relationships in time series data is a well-known problem and methods such as Granger causality or transfer entropy look for it in continuous data sources. However, when data contains discrete events and comes from multiple sources with varying data types, assumptions underlying these methods are often violated. We present a new method called Event Triggered Causality (ETC) that can determine causal relationships between observed events within time series data from very different sensors. The new causality metric takes a data mining approach where events in the data are first identified with data dependent event detectors. The events are then clustered according to their spectral fingerprints and assessed for causality using both similarity and predictability measures. Event similarity is measured using distance metrics while temporal predictability is measured using a temporal entropy metric. ETC is then extended to find successive causal links between events, called Directed Event Triggered Causality, which takes the form of a directed graph. We use these methods to analyze potential causal links in two different situations. The first is searching for causal links between marmoset vocal interactions and related movements. The second is between commands from a farmer, his sheep dog, and the movement of sheep. The construction of these metrics helps to expand the definition of event-based causality and provides a method to further understand complex systems such as social and behavioral interactions.