Knowledge-informed Bidding with Dual-process Control for Online Advertising
This work aims to improve bid optimization for online advertising platforms by making bidding decisions more adaptive and robust, especially in data-sparse or out-of-distribution scenarios.
The paper addresses the limitations of black-box machine learning models in online advertising bid optimization by proposing KBD, a method that incorporates human expertise as inductive biases. KBD uses a Decision Transformer for global optimization of multi-step bidding sequences and implements dual-process control by combining a fast rule-based PID with the Decision Transformer.
Bid optimization in online advertising relies on black-box machine-learning models that learn bidding decisions from historical data. However, these approaches fail to replicate human experts' adaptive, experience-driven, and globally coherent decisions. Specifically, they generalize poorly in data-sparse cases because of missing structured knowledge, make short-sighted sequential decisions that ignore long-term interdependencies, and struggle to adapt in out-of-distribution scenarios where human experts succeed. To address this, we propose KBD (Knowledge-informed Bidding with Dual-process control), a novel method for bid optimization. KBD embeds human expertise as inductive biases through the informed machine-learning paradigm, uses Decision Transformer (DT) to globally optimize multi-step bidding sequences, and implements dual-process control by combining a fast rule-based PID (System 1) with DT (System 2). Extensive experiments highlight KBD's advantage over existing methods and underscore the benefit of grounding bid optimization in human expertise and dual-process control.