Decision Making and Analysis

Stakeholder bias and group decision dynamics: mitigating cognitive biases with an integrated consensus-building process‎

Omid Hossein Zadeh, Marzieh Hajjarian, Mohammad Reza Abdi — Wed, 17 Jun 2026 00:00:00 +0800

This study examines how stakeholder-driven preferential amplification affects outcomes in participatory group decision-making (DM) when allocation consequences have material significance. We structured development priorities for local value chains using the Analytic Network Process (ANP) and directly compared the pairwise judgments of value-chain representatives with those of other panel members to assess incentive alignment effects. Pre-consensus analysis revealed substantial divergence between stakeholder and non-stakeholder evaluations, indicating strong preferential positioning within the ANP structure under high-stakes conditions. We then implemented a structured Delphi-based iterative consensus refinement process and returned aggregated judgments (geometric means) to participants across two rounds to enable controlled reconsideration and revision. Post-iteration analysis shows a marked reduction in between-group divergence. Effect size assessment confirms moderation of extreme preferential positions rather than their complete elimination, consistent with the limited statistical power of small stakeholder subgroups. These findings demonstrate that participatory group DM frameworks remain essential for inclusive governance. However, when incentives are directly linked to allocation outcomes, decision architects should design balanced panel structures and incorporate structured consensus-feedback mechanisms to enhance robustness, transparency, and stability in ANP-based policy applications.

Safety control system evaluation in the textile industry using interval type-2 fuzzy topsis approach

Kamala Aliyeva, Nihad Mehdiyev, Shamil Mehdi — Thu, 15 Oct 2026 00:00:00 +0800

Safety control systems have a significant role in the textile industry, where complex production processes, equipment-related risks, and human error create a highly hazardous work environment. Evaluating such systems involves interrelated and often conflicting criteria and is complicated by the uncertainty and subjectivity of expert assessments. To overcome these challenges, this study proposes a fuzzy decision-making model based on the concept of an ideal solution for evaluating safety control systems in the textile industry. The proposed approach employs Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method under a Type-2 Fuzzy Number (T2FN) environment to address the uncertainty and imprecision inherent in expert evaluations. Type-2 fuzzy numbers are used to represent linguistic assessments and capture the uncertainty associated with experts’ judgments in the evaluation of safety control systems. This concept allows the systematic assessment and ranking of safety control alternatives according to their relative closeness to the ideal solution. The results provide a structured approach for identifying appropriate safety control systems and supporting decision-making for occupational safety in the textile industry. The offered framework enables safety-related criteria and alternatives to be evaluated systematically under uncertain conditions and provides a robust basis for identifying the most appropriate safety control solutions in textile manufacturing. This methodology combines fuzzy logic with multi-criteria decision making, based on the principles of positive and negative ideal solutions. Key evaluation criteria, such as system reliability, hazard prevention capability, response time, maintenance effectiveness, and compliance with safety standards, are structured within an integrated decision-making model. Expert assessments are expressed using linguistic variables and converted into fuzzy numbers, effectively accounting for uncertainty and imprecision. Alternatives are then ranked based on their relative proximity to the ideal solution, enabling reliable prioritization of safety control systems.

Fuzzy approach to analyzing a three-factor experiment with binary levels

Rahul Thakur, Prof. S.C. Malik, Masum Raj — Thu, 04 Jun 2026 00:00:00 +0800

A factorial experiment is a widely used statistical analysis technique in experimental studies in agricultural and engineering sciences. The classical factorial experiment design considers several factors at different crisp levels, which are quantitatively measurable. However, factor levels are often imprecise, vague, incomplete, or described linguistically. In such cases, fuzzy statistics are used instead of classical statistics when analyzing data with uncertain observations. In this paper, we propose an extension of the classical factorial design for analyzing experiments with fuzzy observations. The experimental data are represented using triangular fuzzy numbers and transformed using the α-cut interval approach, resulting in lower-level and upper-level factorial models. These models are analyzed separately to evaluate the effects of factors and their interactions under uncertainty. The results are also compared with classical ANOVA applied to defuzzified data to highlight the advantages of incorporating uncertainty through fuzzy representations. Furthermore, the robustness of the proposed approach is examined through sensitivity analysis across different α levels. The findings demonstrate that the proposed fuzzy factorial approach provides a more flexible framework for analyzing experimental data in the presence of imprecision and uncertainty.

Novel Russell's approximation method for transportation problem under hesitant bifuzzy environment

Ismat Beg, Soniya Gupta, Arpa Ghosh, Dheeraj Kumar Joshi — Tue, 30 Dec 2025 00:00:00 +0800

Transportation problem is one of the significant linear programming problems that emerges in several conditions and gains attention of many researchers. Reducing a commodity's transportation expense to meet demand at destination is the goal of the transportation problem. However, uncertainty plays a vital role in real life, making it challenging for decision-makers to provide precise values for the coefficients related to the transportation problem. Hesitant bifuzzy sets are a notable advancement of fuzzy set theory, as they allow decision-makers to deal with every hesitancy without any restriction. This study aims to introduce a formulation of transportation problem under a hesitant bifuzzy environment. In this study, we have introduced a novel Russel approximation method (RAM) for the hesitant bifuzzy transportation problem, where every parameter is represented by hesitant bifuzzy elements. To show the applicability of the proposed method, a real-life illustration has been taken in this article. Additionally, to demonstrate the superiority of the proposed method, a comparative study has also been conducted with other existing methods, which results in the minimum transportation cost.

Bias regulation in algorithmic decision systems: a metaheuristic intervention for business development decisions

Yu-Min Wei — Thu, 24 Sep 2026 00:00:00 +0800

Metaheuristic decision systems can develop exploration-exploitation imbalance under cognitive bias. Existing decision research examines outcomes, adaptive search control, and bias reduction but gives limited attention to internal search structure. This study develops the Metaheuristic-Based Bias Intervention Module as a decision analysis artifact that combines genetic algorithm and particle swarm optimization search with cognitive bias mechanisms, bounded parameter control, and structural indicators. Controlled experiments compare a genetic algorithm, a fixed hybrid configuration, and the proposed module across simulated business development allocation scenarios. Results show that the proposed module preserves decision accuracy and bias reduction while improving symmetry and convergence stability relative to the fixed hybrid configuration. Recorded parameter changes confirm controller activity, while calibration tests and comparisons with entropy, proportional balance, and population diversity support symmetry as a measure of search structure. Exchange symmetry contributes a measurable property of search allocation under cognitive bias and distinguishes structural balance from outcome quality. Integrating adaptivity, symmetry, stability, bias reduction, and accuracy creates a process-level diagnostic structure for decision analysis. Practical relevance lies in a proposed diagnostic logic for search concentration and potential intervention points in partner selection, investment prioritization, and opportunity evaluation. The computational framework provides a foundation for subsequent organizational research on contextual calibration, managerial utility, and decision quality.

Bilevel optimization for the regulation of shared resources under uncertainty

Luigi Greco, Lina Mallozzi — Mon, 21 Sep 2026 00:00:00 +0800

We study normal-form noncooperative games corresponding to Common-Pool Resource (CPR) situations. A social planner aims to regulate the use of the resource and acts as a leader in a two-stage game. The followers are non-cooperative players who choose a Nash equilibrium representing optimal extraction levels. Due to uncertainty about the state of the resource, in this article we consider the possibility that production, which depends on the aggregation of strategies, is a set-valued mapping. We examine appropriate selections of this mapping and analyze the corresponding two-stage games where a social planner regulates the use of the resource and act as a leader. We prove the existence of a Stackelberg-Nash equilibrium and discuss its properties.

Binary extended theta operation of binary soft sets

Aslıhan Sezgin, Orhan Karamustafaoğlu — Mon, 27 Apr 2026 00:00:00 +0800

Binary soft set theory, first introduced by Açıkgöz and Taş in 2016, has become widely accepted as a technique for addressing and modeling uncertainty. Numerous theoretical and practical problems have been solved using this approach. Scholars have shown sustained interest in the theory's core concepts and operations since its inception. In this study, we propose the binary extended theta operation, a special binary soft set operation, and provide a thorough analysis of its basic algebraic features. We also study the distribution of this operation over certain types of binary soft set operations. By considering its algebraic properties and distribution rules, we show that, when combined with specific binary soft set operations, the binary extended theta operation forms many important algebraic structures within the collection of binary soft sets over the universe under certain conditions. The fundamental conceptual difference between the proposed binary extended theta operation and existing binary extended operations in the literature is that unlike approaches based on positive information aggregation, the theta operation systematically extracts negative information through common parameters and offers a unique and complementary tool, particularly for decision problems requiring reliable elimination, risk exclusion, and error detection. Further applications, including cryptology and decision-making, rely on operations of binary soft sets, making this theoretical subject essential from both theoretical and practical perspectives.

Risk-informed decision making for beach nourishment: integrating technical, environmental and operational criteria

Thu, 12 Nov 2026 00:00:00 +0800

Beach nourishment requires repeated decisions during planning, construction, monitoring, and maintenance. These decisions rely on technical, environmental, and operational information collected throughout the project. However, monitoring results do not always lead to clear management responses, and different indicators may provide conflicting assessments. This study proposes a practical risk-informed framework for operational decision making in beach nourishment projects. The framework integrates technical, environmental, and operational criteria without combining them into a single weighted score. Observed conditions are classified into four classes: acceptable, uncertain, correctable deviation, and critical. The four conditions are linked to four responses: continue, verify, modify, or stop and reassess. The framework considers uncertainty in monitoring information and subsequent corrective actions. A non-compensatory logic prevents good performance in one dimension from offsetting a critical condition in another. Economic and management implications are considered as consequences of operational decisions. Illustrative scenarios show how the framework supports decisions during sediment selection, dredging, placement, monitoring, and maintenance. The approach does not replace engineering judgement or provide a formal probabilistic risk assessment. Instead, it organizes available evidence within a transparent and traceable decision process using information already collected by standard nourishment monitoring and quality-control programmes.

Proper edge coloring of direct product of path and star fuzzy graphs

Bacha Khan, Tabasam Rashid, Ismat Beg — Fri, 15 May 2026 00:00:00 +0800

This research explored adjacent vertex distinguishing proper edge coloring (AVDPEC) in the context of the direct product of fuzzy graphs, with particular emphasis on combinations of fuzzy path and fuzzy star graph. In this study, the classical coloring theory of crisp graphs were applied to fuzzy graphs, as membership values introduce an additional layer of intricacy to them. The main contribution of this research is an algorithm for the direct product of fuzzy path and fuzzy star networks, which acquires appropriate edge coloring that distinguishes adjacent vertices utilizing fuzzy membership values. In applications where recognizing between entities or tasks is crucial, this algorithm ensures that each adjacent vertex pair in the fuzzy graph product is identified by the specific colors of their incident edges. By using fuzzy membership values, we provided a versatile structure for managing complicated systems with incomplete or probabilistic interactions between nodes. We also introduced two significant applications of this edge coloring technique: load balancing in data networks and task parallelism in parallel computing. All things considered, our work strengthens the concept of AVDPEC in uncertain graphs, which benefits graph theory both hypothetically and essentially.

Prioritizing 6G supply-chain resilience policies with an evidencecalibrated DEMATEL–TOPSIS model

Jia-Ying Lyu — Wed, 11 Nov 2026 00:00:00 +0800

The transition from 5G-Advanced to IMT-2030 is occurring before the material and component architecture of 6G has stabilized. Governments nevertheless face immediate choices about diversification, domestic capacity, stockpiles, research alliances, recycling, supplier qualification, and technology controls. This study develops an evidence-calibrated decision model for prioritizing those policies without assuming that a fixed 6G bill of materials already exists. A structured evidence synthesis of 35 substantive records—four official data or policy sources and 31 peer-reviewed studies—was used to code twelve interdependent resilience criteria and seven policy alternatives. The Decision-Making Trial and Evaluation Laboratory (DEMATEL) identified causal structure and systemic prominence; Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) ranked policy packages using the normalized prominence profile as a structural-salience baseline rather than as a claim about stakeholder preferences. Visibility and traceability, innovation compatibility, environmental compatibility, geopolitical-risk reduction, and administrative feasibility formed the net-causal group. Durability of dependence reduction received the highest prominence weight (0.103), followed by domestic and allied capacity (0.100) and scalability (0.092). Shared supplier qualification and certification platforms ranked first (closeness coefficient 0.816), ahead of joint research and standards alliances (0.637), recycling and substitution (0.576), and multi-sourcing (0.574). A6 remained first under equal weights, four policy scenarios, twelve leave-one-criterion-out tests, and 10,000 weight perturbations. These tests establish within-model stability under the reported weight changes; they do not constitute external stakeholder validation. The findings support a sequenced portfolio: build visibility and common qualification infrastructure first, use diversification and research alliances to expand feasible options, and reserve capital-intensive capacity, stockpiles, and controls for clearly diagnosed layer-specific bottlenecks.

Decision-oriented explainable artificial intelligence: a PDR-based review of methods, applications, and emerging frontiers

Jiangshan Zhu — Fri, 14 Aug 2026 00:00:00 +0800

Explainable artificial intelligence (XAI) is increasingly used in consequential decisions, but method selection still requires evidence about predictive reliability, explanatory fidelity, and stakeholder usefulness. This latent Dirichlet allocation (LDA)-assisted structured review used the OpenAlex Works metadata application programming interface (API) to retrieve 4,200 English-language records published from 2018 to 13 July 2026. Sequential DOI, exact-title, and fuzzy-title deduplication retained 3,166 records; title, abstract, and keyword screening retained 694; eligibility assessment retained 666; and 666 records entered the final document-term matrix. Candidate LDA models with k = 5 − 16 were compared using c_v and u_mass coherence, conventional perplexity, matched-topic stability, and Jensen–Shannon separation. The selected k = 8 solution achieved c_v = 0.5226, stability = 0.6809, and mean topic separation = 0.5824. Manual inspection of the top terms and documents identified themes concerning robust counterfactual generation, responsible and regulated decision support, interpretable clinical risk prediction, industrial, cybersecurity, and infrastructure XAI, causal and actionable algorithmic recourse, visual and multimodal medical explanation, clinical XAI adoption, trust, and workflow, and human-centered XAI evaluation and taxonomy. These evidence-derived themes are integrated with the adopted Predictive-Descriptive-Relevance (PDR) framework as a decision-oriented synthesis lens. The review contributes a reproducible literature map, a critical method comparison, a stakeholder-centered cross-domain matrix, and a research roadmap for causal, robust, uncertainty-aware, multimodal, generative, foundation-model XAI.

Common-sense thinking and decision making

Mats Danielson — Wed, 21 Oct 2026 00:00:00 +0800

Common-sense thinking (CST) is proposed as the dynamic, situation-responsive application of commonsense knowledge rather than the mere possession of static facts. This conceptual article distinguishes two modes of CST. System A applies an already adequate representation of a familiar situation, whereas System B becomes important when that representation must be constructed, adapted, or reconsidered. The distinction concerns the amount of situation-specific construction required rather than simply the speed or effort of reasoning. CST is related to, but distinguished from, neighbouring constructs and research traditions, including practical intelligence, executive functions, rational thinking, metacognition, wisdom, adaptive expertise, and Naturalistic Decision Making. Its central decision-theoretic contribution is the proposal that CST also functions at a meta-decision level: recognising when unaided judgement is adequate and when a problem requires more explicit structuring and decision analysis. Examples from scientific reasoning and professional practice illustrate how context-sensitive practical judgement may operate, while structured decision methods are viewed as complements to rather than replacements for such judgement. The framework is explicitly conceptual and remains to be empirically validated. Testable propositions are proposed concerning System B reasoning, individual differences in recognising the limits of unaided judgement, and the appropriate transition from informal judgement to structured decision analysis.