DeepRule: An Integrated Framework for Automated Business Rule Generation via Deep Predictive Modeling and Hybrid Search Optimization
Yusen Wu, Xiaotie Deng
TL;DR
<3-5 sentence high-level summary> DeepRule addresses the gap between theoretical pricing/assortment models and real-world retail complexity by integrating unstructured knowledge extraction, dynamic multi-agent optimization, and interpretable rule synthesis. It introduces a tri-level framework: a hybrid knowledge fusion engine that converts unstructured sources into structured features, a game-theoretic constrained optimization layer to reconcile supplier and retailer objectives, and an interpretable rule distillation interface using LLM-guided symbolic regression to generate auditable pricing strategies. The approach is validated on real retail data, showing profits and operational feasibility improvements over baselines, and is supported by extensive ablations of LLMs and search strategies. This work provides a replicable, end-to-end pipeline for AI-driven economic intelligence in capital-intensive retail ecosystems.
Abstract
This paper proposes DeepRule, an integrated framework for automated business rule generation in retail assortment and pricing optimization. Addressing the systematic misalignment between existing theoretical models and real-world economic complexities, we identify three critical gaps: (1) data modality mismatch where unstructured textual sources (e.g. negotiation records, approval documents) impede accurate customer profiling; (2) dynamic feature entanglement challenges in modeling nonlinear price elasticity and time-varying attributes; (3) operational infeasibility caused by multi-tier business constraints. Our framework introduces a tri-level architecture for above challenges. We design a hybrid knowledge fusion engine employing large language models (LLMs) for deep semantic parsing of unstructured text, transforming distributor agreements and sales assessments into structured features while integrating managerial expertise. Then a game-theoretic constrained optimization mechanism is employed to dynamically reconcile supply chain interests through bilateral utility functions, encoding manufacturer-distributor profit redistribution as endogenous objectives under hierarchical constraints. Finally an interpretable decision distillation interface leveraging LLM-guided symbolic regression to find and optimize pricing strategies and auditable business rules embeds economic priors (e.g. non-negative elasticity) as hard constraints during mathematical expression search. We validate the framework in real retail environments achieving higher profits versus systematic B2C baselines while ensuring operational feasibility. This establishes a close-loop pipeline unifying unstructured knowledge injection, multi-agent optimization, and interpretable strategy synthesis for real economic intelligence.