Optimizing Interactive Systems via Data-Driven Objectives

TL;DR

This paper introduces a novel data-driven approach to optimize interactive systems by inferring objectives directly from user interactions, enabling more accurate and adaptable system improvements.

Contribution

It presents the Interactive System Optimizer (ISO), a new algorithm that infers objectives from data and optimizes systems without prior manual objective design.

Findings

ISO outperforms baseline methods in simulations

Data-driven objectives improve user satisfaction

The approach adapts to diverse user behaviors

Abstract

Effective optimization is essential for real-world interactive systems to provide a satisfactory user experience in response to changing user behavior. However, it is often challenging to find an objective to optimize for interactive systems (e.g., policy learning in task-oriented dialog systems). Generally, such objectives are manually crafted and rarely capture complex user needs in an accurate manner. We propose an approach that infers the objective directly from observed user interactions. These inferences can be made regardless of prior knowledge and across different types of user behavior. We introduce Interactive System Optimizer (ISO), a novel algorithm that uses these inferred objectives for optimization. Our main contribution is a new general principled approach to optimizing interactive systems using data-driven objectives. We demonstrate the high effectiveness of ISO over several simulations.