competitive landscaping

Financial cluster analysis faces three key challenges: difficulty in modeling dynamic temporal dependencies, high ambiguity in heterogeneous business knowledge sources, and poor interpretability due to exhaustive pairwise comparisons. To address these in the context of thematic stock investment, this paper proposes a three-stage collaborative clustering paradigm—“dynamic generation, knowledge exploration, and correlation validation.” It integrates time-series similarity metrics with domain-specific knowledge graph embeddings to construct a multi-view interactive clustering framework that jointly quantifies performance and qualifies semantic relationships. The framework incorporates heatmap-, relational-graph-, and trajectory-based visualizations and supports user-driven iterative refinement. Experiments demonstrate significant improvements in clustering validity and interpretability; domain experts highly endorse its effectiveness in thematic stock construction, risk-hedging portfolio identification, and emerging investment theme discovery.

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.

This work addresses the challenge of evaluating commercial analytics agents in multi-step insight generation. We introduce InsightBench, the first end-to-end benchmark comprising 100 real-world business datasets and human-annotated ground-truth insights, requiring agents to autonomously execute the full pipeline: question formulation, data analysis, and derivation of actionable insights. We propose a novel multi-step insight generation evaluation paradigm and an open-source dual-path assessment framework built on LLaMA-3, incorporating a quality assurance process that jointly enforces goal clarity and analytical depth. Experiments demonstrate that our AgentPoirot—integrating Pandas, SQL, and natural language reasoning—significantly outperforms single-step baselines (e.g., Pandas Agent). Results validate the feasibility of open-weight large language models for complex commercial analytics tasks. All datasets, code, and evaluation tools are publicly released.

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 evaluation of generative AI is hindered by the scarcity of high-quality benchmarks, whose manual construction is costly and time-consuming. Method: We propose the first automated benchmark construction framework powered by collaborative large language model (LLM) agents, decomposing benchmark creation into four sequential stages—planning, generation, verification, and evaluation—integrating task decomposition, agent coordination, human-in-the-loop feedback, and explicit constraint-satisfaction assessment. Contribution/Results: The framework significantly enhances data diversity and metric reliability. Leveraging it, we construct the first high-quality benchmark specifically targeting planning and constraint-satisfaction capabilities in text generation. We systematically evaluate seven state-of-the-art models, uncovering shared failure modes and fine-grained capability disparities. Our work establishes a scalable, reproducible paradigm for evaluating generative AI capabilities, advancing both benchmark methodology and empirical analysis.

This work addresses the challenges of low quality and poor transparency in build-or-buy decisions within enterprise software development, which often stem from reliance on unstructured experiential knowledge. To overcome these limitations—particularly in cold-start scenarios lacking historical data—the authors propose a structured approach that integrates a decision-factor ontology, rule-based reasoning, and reference-class matching. This method enables transparent, auditable evaluation of alternatives and represents the first application of combined ontology modeling and rule reasoning to build-or-buy decision-making. By revealing critical decision thresholds and supporting traceability, the approach enhances the rationality, transparency, and auditability of choices. Its practical efficacy is demonstrated through a lightweight tool validated in a financial industry case study, showing significant improvements in decision quality.

Existing benchmarking methodologies rely on static datasets and struggle to support architectural trade-off analysis and evolutionary assessment of heterogeneous information systems in multi-model environments. This work proposes the TransforMMer framework, which reconceptualizes benchmark engineering as a systematic design tool by introducing a unified representation model that explicitly captures schema semantics and cross-model mappings. From a single source dataset, TransforMMer automatically generates semantically consistent yet structurally diverse variants across relational, document, and graph database models. The framework supports structural redesign operations—including embedding, augmentation, and hybrid partitioning—to enable reproducible cross-representation transformations. Experimental results demonstrate that query performance disparities primarily stem from interactions between workload characteristics and data representations, thereby validating the framework’s efficacy in guiding the evolution of heterogeneous systems.

Current paradigms for evaluating reasoning capabilities are constrained by benchmark saturation, data contamination, and subjective judgments, limiting their ability to comprehensively assess model intelligence. This work proposes a novel interactive benchmarking framework that shifts the evaluation focus toward a model’s capacity to actively acquire and leverage information. By introducing a multi-turn interaction mechanism under budget constraints, the framework integrates logical reasoning, UI2HTML conversion, and mathematical tasks within contexts such as interactive proofs and games, offering a unified, objective, and contamination-resistant assessment. Experimental results demonstrate that this approach more robustly exposes significant deficiencies in contemporary models’ interactive reasoning abilities, thereby establishing a new pathway for evaluating artificial intelligence.

Existing benchmarks for knowledge work evaluation largely adhere to traditional NLP task paradigms, failing to capture systems’ capabilities in real-world knowledge-intensive settings. This work proposes a three-step framework—explicitly defining work activities, establishing realistic test environments, and focusing evaluation on deliverable outputs—and derives 18 core knowledge work activities from the O*NET database. Innovatively integrating role responsibilities, local tool usage, and downstream usability into benchmark design, the approach establishes a coherent “work activity–test setup–scoring artifact” alignment. Validation through three case studies (GDPval, OfficeQA Pro, and APEX-SWE) exposes critical misalignments in current benchmarks between tasks, environments, and actual work objectives, offering a new paradigm for evaluating knowledge work systems in practical, application-oriented contexts.