Domain-independent generation and classification of behavior traces

TL;DR

This paper introduces CABBOT, a novel online learning method for classifying human-like agents based on their behavior traces, even with partial and noisy observations, across diverse domains.

Contribution

The paper presents CABBOT, a new domain-independent technique for real-time classification of agents' behavior types from partial, noisy data in various environments.

Findings

CABBOT achieves effective classification in multiple domains.

The method handles partial and noisy observations robustly.

Promising experimental results demonstrate its practical applicability.

Abstract

Financial institutions mostly deal with people. Therefore, characterizing different kinds of human behavior can greatly help institutions for improving their relation with customers and with regulatory offices. In many of such interactions, humans have some internal goals, and execute some actions within the financial system that lead them to achieve their goals. In this paper, we tackle these tasks as a behavior-traces classification task. An observer agent tries to learn characterizing other agents by observing their behavior when taking actions in a given environment. The other agents can be of several types and the goal of the observer is to identify the type of the other agent given a trace of observations. We present CABBOT, a learning technique that allows the agent to perform on-line classification of the type of planning agent whose behavior is observing. In this work, the observer agent has partial and noisy observability of the environment (state and actions of the other agents). In order to evaluate the performance of the learning technique, we have generated a domain-independent goal-based simulator of agents. We present experiments in several (both financial and non-financial) domains with promising results.