System-2 Recommenders: Disentangling Utility and Engagement in Recommendation Systems via Temporal Point-Processes

TL;DR

This paper introduces a novel recommendation framework that distinguishes between utility-driven and impulsive user behaviors by modeling return probabilities with a Hawkes process, aiming to improve content relevance and user satisfaction.

Contribution

It proposes a generative model that separates long-term utility effects from short-term impulsive interactions using temporal point processes, enabling better content optimization.

Findings

Effective disentanglement of System-1 and System-2 behaviors demonstrated on synthetic data.

Long-term user return probability correlates with utility-driven interactions.

Model provides a foundation for optimizing recommendations based on true user utility.

Abstract

Recommender systems are an important part of the modern human experience whose influence ranges from the food we eat to the news we read. Yet, there is still debate as to what extent recommendation platforms are aligned with the user goals. A core issue fueling this debate is the challenge of inferring a user utility based on engagement signals such as likes, shares, watch time etc., which are the primary metric used by platforms to optimize content. This is because users utility-driven decision-processes (which we refer to as System-2), e.g., reading news that are relevant for them, are often confounded by their impulsive decision-processes (which we refer to as System-1), e.g., spend time on click-bait news. As a result, it is difficult to infer whether an observed engagement is utility-driven or impulse-driven. In this paper we explore a new approach to recommender systems where we infer user utility based on their return probability to the platform rather than engagement signals. Our intuition is that users tend to return to a platform in the long run if it creates utility for them, while pure engagement-driven interactions that do not add utility, may affect user return in the short term but will not have a lasting effect. We propose a generative model in which past content interactions impact the arrival rates of users based on a self-exciting Hawkes process. These arrival rates to the platform are a combination of both System-1 and System-2 decision processes. The System-2 arrival intensity depends on the utility and has a long lasting effect, while the System-1 intensity depends on the instantaneous gratification and tends to vanish rapidly. We show analytically that given samples it is possible to disentangle System-1 and System-2 and allow content optimization based on user utility. We conduct experiments on synthetic data to demonstrate the effectiveness of our approach.