Dynamic Decision Research Articles

Self-Adapting Network Relaxations for Weakly Coupled Markov Decision Processes

High-dimensional weakly coupled Markov decision processes (WDPs) arise in dynamic decision making and reinforcement learning, decomposing into smaller Markov decision processes (MDPs) when linking constraints are relaxed. The Lagrangian relaxation of WDPs (LAG) exploits this property to compute policies and (optimistic) bounds efficiently; however, dualizing linking constraints averages away combinatorial information. We introduce feasibility network relaxations (FNRs), a new class of linear programming relaxations that exactly represents the linking constraints. We develop a procedure to obtain the unique minimally sized relaxation, which we refer to as self-adapting FNR, as its size automatically adjusts to the structure of the linking constraints. Our analysis informs model selection: (i) the self-adapting FNR provides (weakly) stronger bounds than LAG, is polynomially sized when linking constraints admit a tractable network representation, and can even be smaller than LAG, and (ii) self-adapting FNR provides bounds and policies that match the approximate linear programming (ALP) approach but is substantially smaller in size than the ALP formulation and a recent alternative Lagrangian that is equivalent to ALP. We perform numerical experiments on constrained dynamic assortment and preemptive maintenance applications. Our results show that self-adapting FNR significantly improves upon LAG in terms of policy performance and/or bounds, while being an order of magnitude faster than an alternative Lagrangian and ALP, which are unsolvable in several instances. This paper was accepted by Baris Ata, stochastic models and simulation. Supplemental Material: The electronic companion and data files are available at https://doi.org/10.1287/mnsc.2022.01108 .

Dynamic Relationship Analysis and Decision Optimization of Key System Factors Based on LSTM Model

Dynamic Relationship Analysis and Decision Optimization of Key System Factors Based on LSTM Model

Turing-like Experiment in a Cyber Defense Game

During the past decade, researchers of behavioral cyber security have created cognitive agents that are able to learn and make decisions in dynamic environments in ways that assimilate human decision processes. However, many of these efforts have been limited to simple detection tasks and represent basic cognitive functions rather than a whole set of cognitive capabilities required in dynamic cyber defense scenarios. Our current work aims at advancing the development of cognitive agents that learn and make defense-dynamic decisions during cyber attacks by intelligent attack agents. We also aim to evaluate the capability of these cognitive models in ``Turing-like'' experiments, comparing the decisions and performance of these agents against human cyber defenders. In this paper, we present an initial demonstration of a cognitive model of the defender that relies on a cognitive theory of dynamic decision-making, Instance-Based Learning Theory (IBLT); we also demonstrate the execution of the same defense task by human defenders. We rely on OpenAI Gym and CybORG and adapt an existing CAGE scenario to generate a simulation experiment using an IBL defender. We also offer a new Interactive Defense Game (IDG), where \textit{human} defenders can perform the same CAGE scenario simulated with the IBL model. Our results suggest that the IBL model makes decisions against two intelligent attack agents that are similar to those observed in a subsequent human experiment. We conclude with a description of the cognitive foundations required to build autonomous intelligent cyber defense agents that can collaborate with humans in autonomous cyber defense teams.

Continual three-way decisions via knowledge transfer

Traditional credit risk prediction, updates the model from scratch for time-changing data streams, resulting in significant computational, time, and storage consumption. For resource efficiency with acceptable prediction precision, we advocate incrementally training models by transferring knowledge and delayed decisions of low-confidence samples. To this end, we propose a novel multi-stage prediction approach, called Continual Three-Way Decisions, which focuses on knowledge accumulation and thresholds optimization between tasks from the perspective of uncertainty reduction. We utilize elastic weight consolidation to take previous important parameter information as transferred knowledge. Subsequently, we unify continual learning and dynamic three-way decisions through thresholds-based joint mechanism. Finally, the extensive experiments verify the efficacy of our proposed method, demonstrating up to a 38% reduction in running time and a 28% decrease in memory usage compared to isolated and static methods.

Decision-making dynamics in urban energy transition: A statistical analysis of policy frameworks, stakeholder collaboration and technological innovations

This research explores the intricate dynamics of decision-making in the context of urban energy transition, focusing on the interplay between policy frameworks, stakeholder collaboration, and technological innovations. The study makes three key contributions to the field. Firstly, it proposes an innovative approach to enhance market price prediction accuracy by integrating a Generative Adversarial Network (GAN) model. Leveraging the Adaptive Bat Algorithm (ABA) for GAN parameter optimization, the model exhibits improved precision in forecasting electricity prices, thereby providing stakeholders with more reliable insights. Secondly, the research introduces optimized model parameters for efficient energy decision-making, employing the ABA to dynamically adapt GAN parameters. This adaptive process enhances the overall performance of the model, facilitating better-informed decisions for stakeholders in the energy sector. Lastly, the integration of the ABA for GAN parameter optimization contributes to informed decision-making by generating more accurate market price values. This precision empowers policymakers, utilities, and investors with reliable insights, facilitating the development and implementation of strategies aligned with the goals of sustainable and efficient urban energy transition. The research underscores the significance of accurate market price predictions in shaping a resilient and sustainable energy landscape.

Breaking the plastic habit: Drivers of single-use plastic reduction among Thai university students.

This study investigated the decision-making dynamics for pro-environmental behavior among Thai university students, focusing on reducing the consumption of single-use plastics (SUP). By adopting a dynamic approach to the Theory of Planned Behavior (TPB), the research examined the influence of psychosocial factors, including attitudes, perceived behavioral control, and subjective norms, on SUP reduction intention at different phases of behavior change. Using structural equation modelling, we analyzed quantitative data (n = 317) from the selected universities. The results revealed that attitudes predicted behavioral intentions only among individuals in the contemplation phase of reducing SUP. Attitudes had a small but limited influence on the behavioral intentions of students who had not yet acted. Perceived behavioral control, on the other hand, significantly impacted behavioral intentions across all phases of behavior change, highlighting its importance in SUP reduction. The study also confirmed subjective norms' positive influence on students' behavioral intentions in the pre-contemplation phase. Practical implications suggested segmenting residents based on their behavior change phase so that public policymakers can allocate resources more efficiently and effectively by tailoring campaigns to specific behavior change phases, ultimately promoting sustainable behavior among university students.

Critical care nurses' role in rapid response teams: A qualitative systematic review.

To analyse the qualitative evidence on the role of critical care nurses in rapid response teams. Qualitative systematic review. This qualitative systematic review employed Bettany-Saltikov and McSherry's guidelines and is reported according to the Enhancing Transparency in Reporting the Synthesis of Qualitative Research checklist. Two pairs of blinded researchers screened the articles. The data were synthesised using a thematic analysis approach. A systematic literature search was conducted using the CINAHL, Embase and MEDLINE databases. Seven studies were included, and three main roles were identified: (1) balancing between confidence and fear in clinical encounters, (2) facilitating collaboration and (3) managing challenging power dynamics in decision-making. Critical care nurses possess extensive knowledge and skills in providing critical care to patients experiencing deterioration on general wards. They play a vital role in facilitating collaboration between team members and ward staff. Furthermore, within the rapid response team, critical care nurses assume leadership responsibilities by overseeing the comprehensive coordination of patient care and actively engaging in the decision-making process concerning patient care. Highlighting the central role of critical care nurses in rapid response teams as well such a team's benefits in healthcare organisations can promote applications for funding to support further quality assurance of rapid response teams and thus enhance patient safety. Health care organisations can assure the quality of rapid response team by providing economical resources and training. The education providers should facilitate and standardise curriculum for critical care nursing students to achieve necessary knowledge and skills as members in rapid response teams. No patient or public contribution.

Two-sided dynamic pricing and value-added service investment strategies of competitive platforms considering indirect network effects

In recent years, many platforms have realized that relying on subsidies and low-price strategies may result in limited access to users. To expand the market scale and realize the second growth in user scale, some platforms have started adding value-added service (VAS) investment. In this study, we focus on two competing platforms whose bilateral users can be multi-homed. Considering that the users' scale and indirect network effects (INEs) at the initial stage affect their willingness to access and the platforms’ VAS investment in the next stage, we build a two-stage game model to study the two-sided dynamic pricing decisions of competitive platforms when VAS is offered. The results indicate that the platforms should formulate different pricing strategies at two stages. In the first stage, the platforms can adopt a strategy of subsidizing or charging. Particularly, under certain conditions, it will be more beneficial for the platforms to subsidize the side users with the weaker strength of INE. Differently, in the second stage, the platforms should always charge bilateral users. Moreover, at this stage, the platforms will implement differentiated VAS and pricing combination strategies for both sides; they can offer a lower VAS level to one side of users but charge them a higher access fee, while offering a higher VAS level to the other side of users but charge them a lower access fee.

Genetic Algorithm Optimization with Selection Operator Decider

AbstractGenetic Algorithm (GA) is a powerful and flexible meta-heuristic tool to deal with the complexity of optimization problems, as they are directly related to real-life situations. The primary goal of an optimization problem could be to obtain a solution with less effort and near-optimal rather than slow, improbable optimal. GAs serve this purpose by broadly exploring the possible solution space and using genetic operators. The performance of GAs can vary significantly depending on the genetic operators. Although each operator type has upsides and downsides, the selection operator greatly influences the GA’s performance. Conventional GAs initialize with predetermined genetic operators and continue with the same throughout all iterations. In this paper, dynamically adjusting the selection operators to the current progress of the iteration will be shown to be a crucial strategy to improve the performance of the GA. This study aims to propose a novel GA capable of harnessing multiple selection operators by a self-deciding operator structure, which is more advantageous at the current iteration. For this, Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), which is known as a simple and effective multi-criteria decision-making method, will be integrated into the GA by a proposed dynamic decision matrix. The proposed Selection Operator Decider Genetic Algorithm (SODGA) has unique properties with varying selection processes and is capable of using TOPSIS as a decider of the operator inside the iterations. The effectiveness of the presented SODGA framework will be analyzed by a Capacitated Vehicle Routing Problems (CVRPs) benchmark set.

Contingent Reasoning and Dynamic Public Goods Provision

Contributions toward public goods often reveal information that is useful to others considering their own contributions. This experiment compares static and dynamic contribution decisions to determine how contingent reasoning differs in dynamic decisions where equilibrium requires understanding how future information can inform about prior events. This identifies partially cursed individuals who can only extract partial information from contingent events, others who are better at extracting information from past rather than future or concurrent events, and Nash players who effectively perform contingent thinking. Contrary to equilibrium, the dynamic provision mechanism does not lead to lower contributions than the static mechanism. (JEL C92, D71, D82, D91, H41)

Dynamic decision making for situational awareness using drones: Requirements, identification and comparison of decision support methods

Decision makers increasingly operate in real-time information-rich environments, where limited time is available for interpreting data to inform decisions. These environments are driven by static or mobile sensing devices that can provide numerous dynamic data points. A prominent approach in this space is to utilise drones, which can be deployed to gather targeted information. However, deciding how best to deploy available drones is nontrivial, and stands to benefit from decision support aids that plan routes. Such a system must operate under time constraints created by the changing attributes of routes as the situation unfolds. This study describes a dynamic decision support system (DSS) for situational awareness with drones. The system applies Multi-Criteria Decision Making (MCDM) methods within a dynamic genetic algorithm to provide a continuously revised ranking of routes. Five desiderata for dynamic decision support are presented. It is shown how a dynamic DSS can be equipped with declarative specification of preferences (Desiderata 1), dynamic revision of recommendations (Desiderata 2), and high diversity of options (Desiderata 3). The study then compares four MCDM methods, namely the Weighted Product Model (WPM), the Analytic Hierarchy Process (AHP), the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS), and the Preference Ranking Organization METHod for Enrichment Evaluation (PROMETHEE), with regards to how consistently they trade-off between criteria (Desiderata 4) and the stability of results under small changes to criteria values (Desiderata 5). To evaluate the trade-offs between criteria we analyse the smoothness of change in criteria outcomes as criteria weightings increase for each algorithm. The outcomes are calculated by automating the selection of routes in a case study that applies drones to the task of harbour management. The stability of results for the different MCDM methods are compared. Perturbations were applied to sets of routes ranked by each algorithm then each algorithm was reapplied and the magnitude of the changes in ranking was assessed. Overall, TOPSIS was found to be the algorithm which made the most consistent trade-offs between criteria, only under-performing another algorithm with respect to a single criterion. AHP and WPM were the next most consistent algorithms and PROMETHEE was the least consistent algorithm. TOPSIS was also found to be the most stable method under small changes to criteria values. AHP was the second most stable, followed by PROMETHEE and WPM respectively. The results show that TOPSIS achieves the best result for both Desiderata 4 and 5 and consequently the study finds TOPSIS to be an appropriate MCDM method for dynamic decision support.

Power Dynamics in Accounting-Related Strategic Decision-Making within Hospital Management: A Narrative Literature Review

This paper aims to explore how power dynamics shape strategic decisions and performance measurement systems in hospital management, elucidating their impact on managerial choices in healthcare settings. Key themes and factors related to power dynamics in hospitals are identified, including the distribution of power among management teams, the influence of individual and group power dynamics, and the effects of power on decision-making across organizational levels. By synthesizing insights from previous research, this paper informs the development of theoretical frameworks and methodological approaches for studying the interplay between power dynamics and strategic decision-making in hospital management. Furthermore, it offers practical implications for hospital administrators and managers, providing guidance on navigating power dynamics to enhance decision-making effectiveness and organizational performance. This paper contributes to advancing our understanding of the complex dynamics of power and decision-making in hospital management, offering valuable insights for both research and practice in healthcare administration.

Designing and Developing Dynamic Decision Support Information for Disaster Response

Designing and Developing Dynamic Decision Support Information for Disaster Response

Multi-robot Source Navigation Method Based on Coordination Graph Monte Carlo Tree Search

To address the dynamic cooperative multi-robot sequential decision problem, we propose a multi-robot source navigation method based on coordination graph Monte Carlo tree search. The Monte Carlo tree search online planning is designed with the algorithm system's structure in mind. We combine the upper confidence bound strategy with the coordination graph, which represents multi-robot cooperative communication, and solve the coordination graph using the max-sum algorithm to select joint actions. This paper proposes a time series prediction model for optimizing multi-robot movement trends using historical data, which is then used to solve the exploration and exploitation problem in Monte Carlo tree search. The experimental analysis and comparison show that our proposed method outperforms the comparison algorithms in terms of source search steps, task execution time, and source search success rate, as well as robustness and efficiency for multi-robot source search.

Dynamic Decision Making for Connected Vehicles in IoT System

Intelligent Transportation System (ITS) which focuses on dynamic decision making for IoT data processes using distributed and decentralized systems has attracted much attention in recent years. In this paper, we propose a novel approach for enabling computational intelligence into dynamic decision-making for connected vehicles to provide various applications of smart cities. The proposed approach is based on the ant colony optimization (ACO) approach, which is able to improve the performance of intelligent transportation systems. In addition, the simulated results are compared with previous works in the literature.

Dynamic pricing strategy for content products considering consumer fairness concerns and strategic behavior

PurposeThe development of the digital age has made data and information more transparent, enhancing the strategic perspectives of both buyers (strategic waiting) and sellers (price fluctuations) in their decision-making. This research investigates the optimal dynamic pricing strategy of the content product developer in relation to their consideration of consumer fairness concerns to elucidate the impact of consumer fairness concerns on the dynamic pricing strategy of the developer.Design/methodology/approachThis paper assumes that monopolistic content developers implement a dynamic pricing strategy for the content product. Through constructing a two-period dynamic pricing game model, this research investigates the optimal decisions of the content developer, contingent upon their consideration or disregard of consumer fairness concerns. In the extension section, the authors additionally account for the influence of myopic consumers on these optimal decisions.FindingsOur findings reveal that the degree of consumer fairness concerns significantly influences the developer’s optimal dynamic pricing decision. When a developer offers content products with lower depth, there is a propensity for the developer to refrain from incorporating consumer fairness concerns into a dynamic pricing strategy. Conversely, in cases where the developer offers a high-depth content product, consumer fairness concerns benefit the developer. Furthermore, our analysis reveals a consistent benefit for the developer from the inclusion of myopic consumers.Originality/valueFew studies have delved into the conjoined influence of consumer fairness concerns and strategic behavior on dynamic pricing strategy. Our findings indicate that consumer fairness concerns can enhance the efficiency of the value chain for content products under specific conditions. This paper not only enriches the existing literature on dynamic pricing by incorporating consumer fairness concerns theoretically but also offers practical insights. The outcomes of this research can guide content product developers in devising optimal dynamic pricing strategies.

An EEG Dataset of Neural Signatures in a Competitive Two-Player Game Encouraging Deceptive Behavior

Studying deception is vital for understanding decision-making and social dynamics. Recent EEG research has deepened insights into the brain mechanisms behind deception. Standard methods in this field often rely on memory, are vulnerable to countermeasures, yield false positives, and lack real-world relevance. Here, we present a comprehensive dataset from an EEG-monitored competitive, two-player card game designed to elicit authentic deception behavior. Our extensive dataset contains EEG data from 12 pairs (N = 24 participants with role switching), controlled for age, gender, and risk-taking, with detailed labels and annotations. The dataset combines standard event-related potential and microstate analyses with state-of-the-art decoding approaches of four scenarios: spontaneous/instructed truth-telling and lying. This demonstrates game-based methods’ efficacy in studying deception and sets a benchmark for future research. Overall, our dataset represents a unique resource with applications in cognitive neuroscience and related fields for studying deception, competitive behavior, decision-making, inter-brain synchrony, and benchmarking of decoding frameworks in a difficult, high-level cognitive task.

Gender dynamics in health decision-making: A study on social health protection utilization in Pakistan

Gender dynamics in health decision-making: A study on social health protection utilization in Pakistan

Building Flexible, Data-driven Framework for Real-time Analysis

In the contemporary business landscape, the escalating demand for real-time predictive analytics is driven by the imperative for dynamic decision-making. Traditional analytics models often prove inadequate in addressing the need for agility required to respond swiftly to rapidly changing circumstances. Real-time predictive analytics, however, offers a transformative solution, empowering organizations to make informed and timely decisions in fast-paced environments. This capability proves invaluable in industries were staying ahead of emerging trends is critical, fostering a proactive approach to decision-making that can significantly impact competitiveness. The sheer volume and diversity of data require sophisticated solutions for processing and analysis. Real-time predictive analytics becomes an indispensable tool, offering the capability to promptly extract valuable insights from massive datasets. This not only enhances decision-making but also allows organizations to stay ahead by uncovering trends and patterns in real time. Scalability is a fundamental consideration for organizations on a growth trajectory. Real-time predictive analytics frameworks provide a scalable foundation, allowing businesses to seamlessly expand their analytical capabilities. This adaptability ensures that the framework can handle the increasing demands for processing power and storage, aligning with the evolving needs of a growing organization.

A Novel Approach to Mitigating Packet Loss in Wireless Communication Networks through Machine Learning-Based Adaptive Error Correction

Wireless communication networks are integral to modern computing, facilitating seamless data transmission across diverse devices. Despite their importance, packet loss remains a persistent challenge, adversely affecting network reliability and performance. This research paper introduces a pioneering approach to tackle this longstanding issue, employing machine learning for adaptive error correction. The proposed method aims to significantly enhance the robustness and efficiency of wireless communication systems, presenting an innovative solution that has not been extensively explored in existing literature. Keywords—Wireless communication networks,Packet loss mitigation,Machine learning,Adaptive error correction ,Reinforcement learning,Dynamic decision-making,Real-time network conditions,Signal strength,Interference levels,Robustness,Throughput improvement,Latency reduction,Experimental setup,Performance metrics,Comparative analysis,Statistical significance,Sensitivity analysis,Ethical considerations,Practical implications,Future directions