strategy

Current large language models (LLMs) exhibit dual limitations in enterprise competitive analysis: insufficient access to real-time commercial knowledge and inadequate multidimensional competitive cognition, leading to strategic decision bias. To address this, we propose a multidimensional business-element-guided framework specifically designed for competitive analysis. Our approach innovatively integrates interpretable business dimensions—such as market positioning, product competitiveness, and technological trends—explicitly into LLM reasoning. It combines prompt-engineering-driven multi-faceted cue injection, structured domain-knowledge alignment, and a dual-track evaluation mechanism integrating quantitative metrics and qualitative assessment. Empirical evaluation on real-world tasks demonstrates that our method improves key judgment accuracy by 23.6% and analytical consistency by 31.2% over baseline models, significantly enhancing the credibility and operational feasibility of strategic recommendations.

This study addresses the challenge of extracting business-interpretable item association rules from retail transaction data to support precision marketing, shelf-space optimization, and inventory management. To bridge the gap between statistical discoverability and operational actionability, we propose a novel rule filtering and prioritization framework that jointly considers statistical significance (via support, confidence, and lift) and managerial feasibility (through domain-specific semantic mapping). Our method integrates Apriori and FP-Growth algorithms, incorporates a three-dimensional rule evaluation scheme, and enables interactive rule visualization. Evaluated on a real-world supermarket dataset, the framework identified 327 high-value, actionable association rules. Deployment yielded an 18.6% increase in cross-buying rate and a 22.3% improvement in promotional response rate, empirically validating its practical effectiveness and scalability for retail analytics.

Antitrust market definition lacks consensus, undermining the robustness of merger assessments. This paper proposes a systematic sensitivity analysis framework grounded in partially ordered sets (posets) and Hasse diagrams—the first application of Hasse diagrams to market definition research. Integrating Shapley values and the Shapley–Shubik power index, the method quantifies firms’ marginal contributions and power distributions across alternative market definitions. It enables interpretable, structured cross-definition evaluation, substantially enhancing analytical transparency and reproducibility. Applied to the 2015 Albertsons/Safeway merger case, the framework successfully identifies pivotal firms and assesses the robustness of market definitions under varying assumptions. The approach establishes a novel paradigm for antitrust economic analysis and delivers a practical, implementable tool for competition authorities and practitioners.

Business professionals—non-technical domain experts—lack appropriate tools and methodologies for effective what-if analysis (WIA), hindering data-informed decision-making. Method: We conducted a two-phase mixed-methods user study—comprising contextual interviews and in-situ task-based evaluations—to systematically characterize their analytical behaviors for the first time. Contribution/Results: Based on empirical findings, we propose three domain-grounded design principles: business-contextual data preparation, risk-aware assessment, and domain-knowledge integration. We implemented and validated these principles in an interactive visual analytics prototype. The study identifies three critical support gaps, empirically confirms that six classes of what-if techniques significantly improve decision efficiency and confidence, and yields eight actionable design guidelines for commercial business intelligence systems. This work bridges a key theoretical and practical gap in WIA research concerning non-technical users.

Existing approaches to business optimization face bottlenecks including heavy reliance on human modeling experts, limited long-range logical reasoning capabilities of large language models (LLMs), scarcity of high-quality training data, and absence of domain-adapted evaluation metrics. Method: This paper proposes an AI-Copilot framework for production scheduling that integrates modular problem synthesis, structured prompt engineering, semantic correctness evaluation tailored for optimization modeling, and lightweight fine-tuning—enabling end-to-end automatic translation of natural-language requirements into solvable mathematical programming models. Contribution/Results: We introduce the first custom evaluation metric system that jointly addresses token-length constraints and modeling fidelity. Empirical results on complex, large-scale scheduling tasks demonstrate significant improvements over state-of-the-art baselines in both formalization accuracy and practical usability, substantially reducing dependence on domain experts.

This work addresses the challenge of transitioning AI systems from executing predefined tasks to autonomously planning business actions aligned with high-level strategic objectives. It introduces, for the first time, a systematic application of world models to commercial settings by constructing an executable business simulator that integrates semantic representations, deterministic business rules, and probabilistic machine learning. This framework explicitly models business states, dynamics, constraints, objectives, and action spaces, enabling agents to perform counterfactual reasoning, predict outcomes, and evaluate trade-offs under uncertainty. By supporting goal-driven autonomous decision-making, the proposed approach establishes both conceptual and technical foundations for autonomous business agents, marking a significant step toward advancing AI from mere instruction execution to strategic planning.

This study addresses the challenges of extreme demand volatility, delayed pricing responses, and misalignment between short-term revenue and long-term profitability during major fashion e-commerce promotions. To tackle these issues, the authors propose a high-frequency “predict–optimize” automated pricing system that breaks away from traditional weekly decision cycles by operating at a minute-level granularity. The system achieves the first industrial-scale deployment of daily multi-objective dynamic pricing in large-scale e-commerce settings, combining gradient-boosted tree models for daily demand forecasting with a multi-objective optimization framework to generate real-time pricing strategies that jointly maximize long-term profit and net merchandise value. Evaluated across 23 A/B tests in 12 Zalando markets from 2023 to 2024, the system delivered approximately 6% higher profit while maintaining sales volume and has since been fully deployed for promotional pricing.

Automated business rule generation for retail category and pricing optimization faces three key challenges: inaccurate customer profiling due to unstructured text inputs, difficulty in modeling dynamic price elasticity, and infeasible strategies arising from multi-layered operational constraints. Method: This paper proposes an automated rule generation framework integrating deep semantic parsing with hybrid search-based optimization. It features a three-tier architecture: (i) LLM-powered semantic parsing for domain knowledge injection; (ii) game-theoretic constrained optimization to ensure operational feasibility; and (iii) LLM-guided symbolic regression—incorporating economic priors (e.g., non-negative elasticity)—to produce interpretable, closed-form pricing rules. Contribution/Results: Evaluated on real-world retail data, the framework achieves statistically significant profit gains over B2C baselines while satisfying 100% of operational constraints. It is the first approach to enable end-to-end, knowledge-driven, dynamically adaptive, and fully interpretable business rule generation for retail pricing and assortment optimization.

This work proposes a systematic approach to derive task effectiveness requirements in the absence of explicit user needs. The method deconstructs task intent into context, functionality, constraints, critical dimensions, performance attributes, and architectural solutions, and introduces a task complexity factor to quantify the impact of external challenges and technology maturity. By integrating Best-Worst Scaling, it prioritizes critical dimensions based on stakeholder judgments. Through task decomposition modeling and quantitative complexity analysis, the framework supports integration with UAF/SysML artifacts and establishes a traceable mechanism for generating Tier 1 and Tier 2 requirements. The approach is validated using a close air support mission case study, effectively addressing a critical gap in requirements engineering when clear initial inputs are unavailable.

This study addresses the limitations of traditional B2B customer segmentation approaches, such as the RFM model, which rely on singular metrics and struggle to capture the complexity and dynamics of business interactions. To overcome this, the authors propose a dynamic, multi-criteria segmentation framework that extends RFM by incorporating stability and growth dimensions. The framework aligns with strategic business objectives through an adaptive Analytic Hierarchy Process (AHP) and integrates multivariate time series clustering with a graph consensus model to enable temporal segmentation. Evaluated on data from over 3,000 manufacturing enterprises, the approach demonstrates strong temporal robustness and significantly enhances the precision of customer strategy formulation through preference-driven dynamic clustering.