Goal recognition via model-based and model-free techniques
This work addresses goal recognition for financial institutions, but it is incremental as it adapts existing techniques without introducing major innovations.
The paper tackled the problem of predicting human intentions from observations by adapting state-of-the-art learning techniques to goal recognition and comparing model-based and model-free approaches across domains, finding that planning-based methods are suitable for some finance-related tasks.
Goal recognition aims at predicting human intentions from a trace of observations. This ability allows people or organizations to anticipate future actions and intervene in a positive (collaborative) or negative (adversarial) way. Goal recognition has been successfully used in many domains, but it has been seldom been used by financial institutions. We claim the techniques are ripe for its wide use in finance-related tasks. The main two approaches to perform goal recognition are model-based (planning-based) and model-free (learning-based). In this paper, we adapt state-of-the-art learning techniques to goal recognition, and compare model-based and model-free approaches in different domains. We analyze the experimental data to understand the trade-offs of using both types of methods. The experiments show that planning-based approaches are ready for some goal-recognition finance tasks.