Modern Research in Decision Making

Abstract With increasing market uncertainty and the growing complexity of competitive environments, supply chains have become more vulnerable to disruptions. Even minor fluctuations in demand or reductions in capacity can generate widespread negative impacts on overall supply chain performance. As a result, developing mathematical models that capture this complexity has become more challenging and requires appropriate solution methodologies. This study proposes an effective solution approach for the robust, scenario-based multi-objective mathematical model developed by Nazari et al. (2024), which seeks to reduce total system costs and environmental emissions. A key innovation of the model is the simultaneous consideration of demand uncertainty—driven by inflation rates—and capacity reductions caused by disruptions. Because exact solution methods become impractical for large-scale, multi-objective problems, two powerful metaheuristic algorithms were employed: a multi-objective extension of the emerging Honey Badger Algorithm (HBA) and the well-known Non-dominated Sorting Genetic Algorithm II (NSGA-II). To evaluate the performance of the proposed model and algorithms, a numerical case study was designed and executed. The results indicate that the proposed model is highly effective in handling uncertainty and supports more optimal decision-making aligned with economic, social, and environmental sustainability. Furthermore, the computational results demonstrate that the HBA algorithm achieves higher efficiency and accuracy in solving hard (NP-hard) problems with large, complex search spaces.

Abstract Energy is one of the basic needs of human life. Production, distribution and optimal consumption of energy have always been one of the basic questions in economics and planning. Energy is one of the main factors of economic growth and development of countries. Human's ever-increasing demand for all kinds of available energy and non-renewable resources to achieve economic development has always faced an increase in environmental pollution and various diseases for human life. The aim of this study is to model the supply chain of biofuels using urban sewage waste in Iran. For this purpose, the combination of system dynamics modeling method and integer mathematical programming model has been used. The period studied in this research is 1388-1397 and its simulation is considered until 1410. The assumptions considered in this research are: with the increase in the payment of subsidies to biofuels, the price of biofuel will decrease; with the increase in the conversion rate of sewage waste into fuel, the price of biofuel will decrease; and with the increase in the price of biomass, Biomass production capacity increases. Also, by doubling the price of green fuel, the production capacity of green fuel increases by 2.9 percent. The results of the simulation are the design of an optimal supply chain of urban biomass resources and also the maximization of the profit of the country's biological refineries.

Abstract The objective of this study is to design a data-driven model for extracting effective rules influencing the product acceptance rate in food industry production lines. To this end, first, 25 variables related to lean manufacturing principles were identified, and using the fuzzy Delphi method, six key variables were selected, including the percentage of conformity of raw materials with quality standards, production scrap rate, exceptional approval rate of the final product, average raw material storage time, work shift, and product return rate. Subsequently, a database consisting of 4,200 real records from two years of production line performance was collected, and after data preprocessing, modeling was conducted using machine learning algorithms. Among these, the decision tree algorithm (CART) was employed as the primary model for extracting interpretable decision rules, and its performance was compared with other classification algorithms. The results indicated that the “percentage of raw material conformity” and the “scrap rate” had the greatest impact on product acceptance. The decision tree model achieved an accuracy of 91% in classifying samples into acceptance and non-acceptance categories. Moreover, the extracted rules revealed transparent and interpretable relationships among the variables and provided a basis for developing decision-support patterns for production and quality control managers. Overall, the findings indicate the effectiveness of lean production–based data-driven approaches in improving quality prediction and reducing waste in the case study of this research.

Abstract With the expansion of operational data and the growing complexity of business environments—particularly in the retail industry—accurate demand forecasting has become a key requirement for effective decision-making and efficient supply chain management. The nonlinear nature, high volatility, and noise inherent in sales data often lead to poor and unreliable performance of traditional forecasting methods. This challenge is further amplified in Iran due to the high level of uncertainty arising from economic fluctuations, shifts in trade policies, logistical constraints, and the impacts of sanctions. In response to these needs, the present study introduces the GODFIS algorithm, a Global Optimization-based Dynamic Fuzzy Inference System, designed to provide accurate, robust, and adaptive forecasts in highly volatile environments. The architecture of GODFIS—through the integration of online learning, dynamic clustering, recursive updating of consequent parameters, and a noise-filtering mechanism—enables precise modeling of complex relationships without the need for full retraining. To evaluate its performance, the proposed algorithm is tested on two categories of data: (1) benchmark datasets with non-stationary behaviors, and (2) real-world data from an Iranian retailer. The results indicate that GODFIS delivers substantial improvements in accuracy, stability, and adaptation speed compared to classical methods, machine learning models, and evolving systems. Overall, the findings suggest that GODFIS, by offering interpretability, scalability, and computational efficiency, can serve as a dynamic forecasting framework for retail operational environments—especially under Iran’s unstable conditions—and play a significant role in optimizing inventory decisions and managing uncertainty.

Abstract Contemporary agriculture is increasingly confronted with challenges related to sustainability, adaptation to complex environments, and innovation development; challenges that can no longer be addressed solely through technological interventions or formal policy measures. In many agricultural systems, the core problem is not the lack of knowledge or innovation, but weaknesses in the absorption, internalization, interpretation, and application of new knowledge within organizational structures and operational processes. Drawing on the Viable System Model (VSM) as a cybernetic framework, this article reconceptualizes absorptive capacity as a mechanism for the emergence and institutionalization of innovation in agricultural systems. This study adopts a qualitative approach and is conducted through a case study of the Farijan Agro-Industrial Complex. Thematic analysis was employed for data analysis, while the Perez Rios diagnostic approach was used to operationalize the VSM framework. In addition, selected analytical considerations derived from the VIPLAN approach and Jackson’s checklist were used to address stakeholder interactions and structural pathologies. The findings indicate that absorptive capacity functions as a distributed mechanism across organizational subsystems and plays an important role in transforming external knowledge into operational and structural innovation. The results further show that the Viable System Model, through strengthening communication flows, recursive learning, and alignment across organizational levels, provides a suitable foundation for enhancing absorptive capacity and sustaining innovation in agricultural systems. This study argues that innovation in agriculture is fundamentally a systemic phenomenon that depends less on technological interventions and more on organizational architecture and knowledge capabilities for institutionalizing innovation.

Abstract This research investigates the predictability of Bitcoin price directions following investor overreaction, a prominent anomaly widely documented in behavioral finance. Leveraging a multimodal dataset—integrating transactional variables, technical indicators, on-chain metrics, and social signals derived from Google Trends—this study analyzes market dynamics from August 2017 to December 2023 and identifies 303 distinct overreaction episodes. To construct a reliable predictive framework, a rigorous three stage feature selection pipeline was implemented, combining Random Forest screening, correlation matrix analysis, and Variance Inflation Factor (VIF) assessment. This process yielded 11 highly informative and non multicollinear variables that served as the input features for the proposed multivariate Long Short Term Memory (LSTM) model. The LSTM model achieved a directional prediction accuracy of 67%, substantially outperforming the classical Logistic Regression benchmark with 53.4% accuracy. Moreover, the consistently declining and stable training and validation loss curves demonstrate strong generalization performance and confirm the model’s robustness against overfitting. Empirical findings reveal statistically significant short term market inefficiencies and predictable abnormal returns following overreaction events at the 99% confidence level. Overall, the study provides compelling evidence of exploitable behavioral patterns within the Bitcoin market and offers a practical foundation for developing advanced algorithmic trading strategies and dynamic risk management systems in cryptocurrency markets.