Generation and Interpretation of Temporal Decision Rules

TL;DR

This paper introduces a method for generating and interpreting temporal decision rules to understand systems producing ordered observations, using TIMERS to identify causal, acausal, or instantaneous relationships.

Contribution

The paper presents a novel approach combining temporal decision rules with the TIMERS method for interpreting temporal data relationships.

Findings

Effective in identifying causal and acausal relationships

Works with both synthetic and real temporal data

Provides insights into system behavior over time

Abstract

We present a solution to the problem of understanding a system that produces a sequence of temporally ordered observations. Our solution is based on generating and interpreting a set of temporal decision rules. A temporal decision rule is a decision rule that can be used to predict or retrodict the value of a decision attribute, using condition attributes that are observed at times other than the decision attribute's time of observation. A rule set, consisting of a set of temporal decision rules with the same decision attribute, can be interpreted by our Temporal Investigation Method for Enregistered Record Sequences (TIMERS) to signify an instantaneous, an acausal or a possibly causal relationship between the condition attributes and the decision attribute. We show the effectiveness of our method, by describing a number of experiments with both synthetic and real temporal data.