Causal-Aware Foundation-Model for Bilevel Optimization in Discrete Choice Settings

2026-05-07

AI Summary

This study addresses a bilevel discrete choice optimization problem arising from the interplay between service providers’ product assortment decisions and users’ personalized selections. The authors propose C3PO (Contextual Causal Constrained Pricing Optimization network), a foundational model framework that uniquely integrates causal inference, in-context learning, and behavioral economics priors to improve price elasticity estimation for new products. By combining price imitation learning, revenue-oriented multitask learning, and elasticity-aware contextual learning, C3PO generates real-time pricing recommendations while respecting operational constraints. Trained on synthetic data derived from multiple classical discrete choice models, the method consistently enhances key pricing performance indicators across simulated, synthetic, and real-world scenarios, with particularly strong gains among highly price-sensitive customer segments. C3PO has been successfully deployed in practical applications including healthcare services, procurement auctions, and ancillary airline revenue management.

Abstract

We introduce a causal aware foundation-model framework for real time optimal decision making in discrete choice environments. We propose a constrained triple-head price optimization (C3PO) network to solve a bilevel decision problem in which a service provider selects an optimal assortment while heterogeneous users make personalized acceptance or rejection choices optimizing their own personalized preferences. C3PO integrates imitation learning of prices, multi-task learning of revenue responses, and in context learning of price elasticity to generate pricing recommendations while adhering to business constraints. During inference, frontier model prompting retrieves an enhanced elasticity prior for new products from behavioral economics literature, improving pricing effectiveness. We demonstrate strong in context learning performance using simulated, synthetic, and real-world datasets. C3PO is trained on simulated data generated from multiple classical discrete choice models in economics. The model is trained on data comprising simulated customer segments and counterfactual action and outcome pairs and evaluated on randomly generated choice environments with no access to the underlying preference structure. The trained model consistently improves the pricing KPIs, with gains increasing as customer price sensitivity increases. We also deploy the tuned foundation model for optimal pricing in real-world applications such as healthcare, tender pricing, airline ancillary pricing, and other domains, achieving substantial gains across multiple products, markets, and divisions.

Problem

• bilevel optimization
• discrete choice
• optimal pricing
• heterogeneous users
• real-time decision making

Innovation

• causal-aware foundation model
• bilevel optimization
• discrete choice
• in-context learning
• price elasticity