Stelios Bekiros, University of Turin

Andrea D'Ariano, Roma Tre University

Peng Wu, Fuzhou University

Guowei Zhang, Dalian University of Technology

Operations research (OR) problems increasingly arise in data-rich and highly uncertain environments where operational decisions must adapt dynamically to evolving contextual information. Advances in sensing technologies, digital platforms, enterprise systems, and large-scale data collection have significantly expanded the availability of side information related to demand patterns, operational states, user behaviors, market conditions, and environmental factors. In many modern applications, such contextual information provides valuable predictive signals that can substantially improve decision quality when effectively integrated into optimization models.

In response, contextual optimization has emerged as a rapidly growing research direction at the intersection of optimization, machine learning, statistics, and prescriptive analytics. Unlike classical optimization paradigms that rely solely on historical averages or predefined uncertainty sets, contextual optimization explicitly incorporates side information into the decision-making process, enabling more adaptive, personalized, and data-driven operational policies. Recent developments in this area include contextual stochastic optimization, distributionally robust optimization with covariates, decision-focused learning, learning-enhanced optimization, online optimization, and adaptive decision-making frameworks.

Despite substantial progress, several important challenges remain open. Real-world contextual optimization problems often involve high-dimensional and heterogeneous data, noisy or incomplete observations, distribution shifts, privacy concerns, interpretability requirements, and stringent real-time computational constraints. Moreover, predictive accuracy alone is insufficient in operational settings; the ultimate objective is to improve downstream decision quality and system performance. Consequently, there is a growing need for new theories, methodologies, and computational frameworks that systematically integrate learning, analytics, and optimization under uncertainty.

This special issue aims to bring together recent advances in contextual and data-driven optimization methods, with particular emphasis on optimization and decision making under uncertainty using side information. We welcome high-quality contributions that develop novel theories, models, algorithms, and applications integrating optimization with machine learning, statistical learning, and data analytics.

Potential topics

• Contextual Stochastic Optimization
• Distributionally Robust Optimization with Side Information
• Prescriptive Analytics and Contextual Decision Making
• Learning-Enhanced Optimization
• Decision-Focused Learning
• Online, Dynamic, and Adaptive Optimization
• Learning-Augmented Algorithms
• Interpretable and Trustworthy Optimization Models
• Statistical Guarantees and Generalization in Optimization
• Data-Driven Optimization Under Uncertainty
• AI and Machine Learning for OR
• Human-in-the-Loop Optimization
• Optimization with Foundation Models or Generative AI
• Scalable Algorithms for Large-Scale Optimization Problems
• Digital Twin and Real-Time Decision Systems
• Contextual Transportation and Logistics Optimization
• Contextual Supply Chain and Revenue Management
• Data-Driven Healthcare and Service Operations

Timeline

• July 31, 2027: Submission deadline

Yi-Kuei Lin, National Yang Ming Chiao Tung University

Industrial engineering systems, including manufacturing systems, supply chains, logistics networks, energy and power systems, transportation systems, and service operations, play a critical role in modern society. The reliable operation of such systems is essential for ensuring efficiency, safety, and robustness in the presence of uncertainty, disruptions, and complex interactions among system components. Failures or performance degradation in these systems may lead to significant economic losses, operational inefficiencies, and societal impacts.

Traditionally, reliability modeling in industrial engineering has been grounded in probabilistic analysis, stochastic modeling, and analytical evaluation techniques. While these approaches remain fundamental, recent advances in sensing technologies, industrial Internet of Things, and information systems have enabled the collection of large-scale operational and condition-monitoring data. This has led to a growing interest in data-driven and intelligent reliability modeling, where statistical learning, machine learning, and other statistical analytical approaches complement classical reliability theory.

At the same time, reliability analysis is increasingly expected to support decision-making processes, such as maintenance planning, resource allocation, system design, and operational optimization. Integrating reliability modeling with decision support frameworks allows practitioners and decision-makers to move beyond reliability assessment toward actionable, reliability-informed decisions under uncertainty.

We invite submissions on topics related to reliability modeling and decision support for industrial engineering systems using Operations Research, industrial engineering, and data-driven methodologies. Contributions addressing both theoretical developments and practical applications are welcome.

We welcome the submission of original research papers that provide new insights and practical solutions to challenges in reliability modeling and decision support for industrial engineering systems. Submissions should demonstrate methodological rigor and clearly highlight their relevance to real-world industrial applications. Papers that illustrate how data-driven reliability analysis can enhance decision-making and system performance are particularly encouraged.

Potential topics

• Data-driven reliability modeling and parameter estimation using operational data
• Reliability analysis using statistical learning and machine learning methods
• Reliability models combining analytical formulations with data-driven learning approaches
• Decision support systems incorporating reliability analysis and risk information
• Optimization and decision-making problems informed by reliability performance
• Predictive maintenance and condition monitoring using data and learning models
• Multistate system and network reliability analysis
• Reliability evaluation of manufacturing, logistics, and supply chain systems
• Reliability modeling in energy, power, and infrastructure systems
• Stochastic modeling and uncertainty analysis in data-driven reliability studies
• Simulation, enumeration, and approximation methods for reliability evaluation
• System design and resource allocation considering reliability and operational data
• Reliability analysis supported by digital twins, data analytics, and intelligent systems
• Reliability, robustness, and resilience of industrial engineering systems

Timeline

• July 31, 2027: Submission deadline

Xu-Feng Zhao, Nanjing University of Aeronautics and Astronautics

Yan-Fu Li, Tsinghua University

Hoang Pham, Rutgers University

Modern industrial systems generate massive datasets from sensor monitoring, which presents computational and memory challenges in data processing. Advanced machine learning technologies such as transfer learning, federated learning, quantum machine learning, and reinforcement learning offer effective and scalable solutions for processing and analyzing large volumes of data, as well as supporting subsequent decision-making.

Recently, various new techniques of advanced machine learning have already been applied to system reliability management, such as fault diagnosis, health condition assessment, remaining useful life prediction, degradation modeling, and maintenance optimization. Yet, ongoing research works continue to explore this exciting research area.

This special issue invites high-quality original research papers, review papers, and case studies that delve into advancements in advanced machine learning for system reliability management.

Potential topics

• Deep learning for anomaly detection and/or fault detection
• Machine learning-enhanced maintenance optimization
• Federated learning for system monitoring and predictive maintenance
• Reinforcement learning for maintenance decision making
• Transfer learning for cross-domain maintenance
• Generative models for synthetic data generation for predictive maintenance
• Self-supervised learning for unlabeled data for fault detection
• Large models for fault detection and/or diagnosis
• Generative models for reliability testing
• Meta-heuristics for large-scale reliability design optimization

Timeline

• May 30, 2026: Manuscript submission deadline
• August 31, 2026: Submission deadline for special issue

Hoang Pham, Rutgers, The State University of New Jersey

The era of AI, through its focus on the reliability and statistical machine computing of intelligent systems in everyday applications and the service industry, has experienced a dramatic shift in recent years. Such systems require reliable and timely responses.

Articles concerning new theoretical research and methods in advanced reliability and statistical computing for intelligent systems are solicited. Preference will be given to papers with real-world applications over purely theoretical papers.

Potential topics

• Mathematical reliability and statistical methods
• Big data modeling and prediction
• Statistical learning algorithms, models, and theories
• Machine learning models for intelligent systems
• Text mining and deep machine learning
• Intelligent system dependability and performability
• Reliability modeling and optimization
• High-dimensional data analysis
• Statistical inference for intelligent systems
• Industrial case studies in intelligent systems, including field and service robotics, medical care, education, visual surveillance, intelligent transportation, etc.

Timeline

• September 30, 2026: Submission deadline

Timeline

• Invalid DateTime: Submission deadline

The interdepartmental virtual special issue on AI for finance and business decisions aims to explore the transformative impact of AI and attract top-quality research on the economics, methodology, and applications of AI and novel data analytics in practice and research in finance and business decisions.

Both theoretical and empirical work is welcome, and studies developing new methods for decision making, optimization, inference and prediction, and interdisciplinary research are encouraged. The special issue especially welcomes submissions that transcend the departmental boundaries and explore unconventional frameworks.

Potential topics

• Economics of AI and machine learning
• Methodology and algorithms for decision making, optimization, inference and prediction
• Applications of AI and novel data analytics in finance and business
• Theoretical and empirical work on AI in practice
• Interdisciplinary research combining AI with business and finance
• Novel frameworks transcending traditional departmental boundaries

Timeline

• December 31, 2025: Submission deadline

Mirco Peron, NEOMA Business School

Ibrahim Kucukkoc, Balikesir University

Daniel Alejandro Rossit, Universidad Nacional del Sur

Ilkyeong Moon, Seoul National University

Olga Battaïa, KEDGE Business School

Michael Pinedo, New York University

Production planning has historically been a central pillar of industrial engineering and operations management. Since the mid-20th century, the field has developed a rich body of classical problems and models, such as lot sizing, job shop and flow shop scheduling, capacity planning, assembly line balancing, material requirements planning (MRP), and aggregate production planning. These models provided structured ways to allocate resources, balance supply and demand, and coordinate activities across production systems, often under deterministic assumptions and with objectives focused primarily on cost and efficiency. Linear programming, dynamic programming, and combinatorial optimization offered rigorous formulations and exact methods, while heuristics and metaheuristics emerged to address large-scale and computationally complex instances.

Over time, production planning research progressively expanded to address uncertainty via stochastic and robust optimization, multi-objective trade-offs (e.g. cost, service level, inventory, lead times), and integration across planning levels (strategic, tactical, and operational). Still, the focus remained on well-defined, structured problems and a relatively stable industrial context.

Today, however, technological, environmental, and societal shifts are reshaping the landscape of production planning. The rise of cyber-physical systems, IoT-enabled factories, advanced robotics, digital twins, additive manufacturing, and AI-based automation has disrupted the stability of traditional assumptions. These innovations have created new types of planning problems, characterized by more frequent reconfiguration, increased heterogeneity of resources, and the necessity of integrating multiple technologies and objectives.

Digital twin–driven planning enables real-time updates of plans and schedules, requiring adaptive and rolling-horizon optimization. Hybrid production systems, combining conventional and additive manufacturing, pose new challenges in sequencing, capacity allocation, and cross-technology coordination. Reconfigurable and modular manufacturing requires planning models that adapt to changing system topologies, dynamic routing, and flexible resource reassignments. Circular and sustainable production systems demand that environmental and social objectives be embedded in planning alongside economic goals. Resilience-oriented planning has become critical in the face of global disruptions, pandemics, and supply shocks, demanding strategies that balance efficiency with adaptability and robustness.

At the same time, innovation has not only transformed the problems but also the solution approaches. Whereas traditional production planning was dominated by mathematical programming and rule-based heuristics, the current era witnesses the rapid adoption of data-driven, hybrid, and AI-enabled methods.

Reinforcement learning and deep learning models are increasingly applied to dynamic planning and scheduling, such as graph neural network and RL architectures for scheduling problems. Hybrid metaheuristics combine classical optimization with machine learning models, surrogate functions, or decomposition techniques to tackle high-dimensional problems. Simulation–optimization coupling allows planners to test, validate, and adapt decisions under complex system dynamics, particularly in systems where analytical modeling is intractable. Multi-agent and distributed approaches enable decentralized planning in highly connected production networks, where local agents coordinate planning decisions. Online and rolling-horizon algorithms become critical when plans must be revised frequently, and incremental updating is required.

Despite these advances, major challenges persist. Industrial adoption demands bridging the gap between academic models and real-world constraints: data sparsity, computational scalability, integration with legacy systems (ERP/MES), and user trust. Decision-makers must also reconcile conflicting objectives: efficiency vs. resilience, speed vs. sustainability, optimality vs. interpretability.

This special issue seeks to collect innovative contributions that redefine the boundaries of production planning. We welcome papers that introduce novel problem formulations reflecting new industrial realities and innovative solution approaches leveraging modern computational, AI, and optimization tools. Both theoretical/methodological and empirical/applied submissions are encouraged, including case studies and empirical validation.

Potential topics

• Evolution of classical planning problems (lot sizing, capacity planning, scheduling, assembly line balancing) in modern manufacturing contexts
• Planning in reconfigurable, modular, and hybrid manufacturing systems
• Integration of additive manufacturing and conventional processes in planning
• Additive manufacturing production scheduling
• Digital twin–enabled planning and real-time adaptive scheduling
• Production planning under sustainability, circular economy, emissions or carbon goals
• Resilience-oriented planning under uncertainty, disruptions, and volatility
• Advanced optimization methods: decomposition, robust/stochastic models, metaheuristics
• Machine learning, reinforcement learning, hybrid AI–optimization for planning
• Simulation–optimization frameworks and surrogate modeling
• Production Planning problems associated with customized environments (engineering-to-order, make-to-order, mass customization)
• Human–robot collaborative systems and operator-driven planning in the context of Industry 5.0
• Reinforcement learning / deep learning models applied to dynamic planning and scheduling, (e.g., graph neural network and RL architectures for scheduling problems)
• Optimization of production and inventory strategies in modern distribution systems (e.g., e-commerce, platform-based logistics)

Timeline

• September 30, 2026: Manuscript deadline