Decision Support Systems最新文献

We propose a novel curvature-based indicator constructed on log-price time series that captures an interplay between trend, acceleration, and volatility found relevant to quantify risks and improve trading strategies. We apply it to diagnose explosive bubble-like behaviors in cryptocurrency price time series and provide early warning signals of impending market shifts or increased volatility. This improves significantly on standard statistical tests such as the Generalized Supremum Augmented Dickey–Fuller (GSADF) and the Backward SADF tests. Furthermore, the incorporation of our curvature-based indicator as a feature into the Light Gradient Boosting Machine enhances its predictive capabilities, as measured by classification accuracy and trading performance.

The Common Vulnerability Scoring System (CVSS) is widely used in the cybersecurity industry to assess the severity of vulnerabilities. However, manual assessments and human error can lead to delays and inconsistencies. This study employs situational awareness theory to develop an automated decision support system, integrating perception, comprehension, and projection components to enhance effectiveness. Specifically, an interpretable principal component analysis (iPCA) combined with machine learning is utilized to forecast CVSS scores using text descriptions from the Common Vulnerabilities and Exposures (CVE) database. Different forecasting approaches, including traditional machine learning models, Long-Short Term Memory Neural Networks, and Transformer architectures (ChatGPT) are compared to determine the best performance. The results show that iPCA combined with support vector regression achieves a high performance (R² = 98%) in predicting CVSS scores using CVE text descriptions. The results indicate that the variability, length, and details in the vulnerability description contribute to the performance of the transformer model. These findings are consistent across vulnerability descriptions from six companies between 2017 and 2019. The study's outcomes have the potential to enhance organizations' security posture, improving situational awareness and enabling better managerial decision-making in cybersecurity.

In today's digital economy, virtually everything from products and services to political debates and cultural phenomena can spark WOM on social media. Analyzing online WOM poses at least three challenges. First, online WOM typically consists of unstructured data that can transform into myriad variables, necessitating effective dimension reduction. Second, online WOM is often continuous and dynamic, with the potential for rapid, time-varying changes. Third, significant events may trigger symmetric or asymmetric responses across various entities, resulting in “bursty” and intense WOM from multiple sources. To address these challenges, we introduce a new computationally efficient method—multi-view sequential canonical covariance analysis. This method is designed to solve the myriad online WOM conversational dimensions, detect online WOM dynamic trends, and examine the shared online WOM across different entities. This approach not only enhances the capability to swiftly interpret and respond to online WOM data but also shows potential to significantly improve decision-making processes across various contexts. We illustrate the method's benefits through two empirical examples, demonstrating its potential to provide profound insights into online WOM dynamics and its extensive applicability in both academic research and practical scenarios.

Successful attended home delivery (AHD) is the most important aspect of e-commerce order fulfillment. Prior literature focuses on incentive scheme development for customers' choices of delivery windows and predictive analytics for delivery results, but it is not clear whether the effect of AHD on the appointment date set by customers increases the success rate of AHD. Therefore, we developed an uplift modeling method, PSM-NDML, as a relevant prescriptive analytic tool for AHD on an appointment date, which aims to estimate the causal effect of the by-appointment delivery on the delivery result. PSM-NDML integrates propensity score matching and double machine learning, effectively addressing sample selection bias, low predictive performance, and poor interpretability. Applied to a real-world product delivery dataset of a Chinese logistics company, PSM-NDML achieves superior performance relative to ten other state-of-the-art uplift models in terms of cumulative gain and the Qini coefficient. The predicted responses gained from PSM-NDML are also visually interpreted at the global and local levels, which reveals various managerial insights. In practice, the findings expand managers' understanding of the heterogeneous effects of AHD on appointment dates and provide decision support for logistics companies in the development of home delivery plans.

While many online platforms use incentive hierarchies to stimulate consumers to generate more online reviews, the extent to which these hierarchies influence reviewer behavior is not fully understood. This study, drawing on image motivation theory and consumer attention theory, takes a novel approach to investigate whether reviewers strategically adjust their review behavior after reaching higher ranks in a hierarchy. We use data from rank change timestamps on platforms to accurately identify reviewers' ranks when posting reviews and then employ a quasi-natural experimental design for causal inference. Additionally, we use Fisher's permutation test to explore the different effects at various ranks. The empirical results reveal that reviewers tend to increase their review length and insert more pictures into their reviews after they reach higher ranks. Reviewers at lower ranks tend to submit more extreme ratings upon rank advancement, whereas their higher-ranking counterparts do not demonstrate significant change. Unlike ratings, reviewers tend to consistently increase the sentiment intensity of their expressions in text after reaching higher ranks. Furthermore, our findings indicate that the magnitude of changes in reviewing behavior only shows an increasing trend in the early stages of rank progression. These insights contribute to a better understanding of the efficacy of incentive hierarchies and offer practical implications for decision-making by platform managers.

A critical part of flow-based conceptual modeling, such as process modeling, is visualizing the logical and temporal sequence in which activities in a process should be completed. While there are established standards and recommendations, there is limited empirical research examining the influence of process model layout on model comprehension. To address this research gap, we conducted a controlled eye-tracking experiment with 70 participants comparing different layouts. The experimental results confirm that the visibility of control flow patterns is critical for assisting users with visual processing, particularly attentional allocation, when comprehending process models for both local comprehension tasks and tasks requiring cognitive integration of model components. In models with more directional changes, users’ visual attention is more drawn to irrelevant regions, but comprehension is less affected as long as patterns remain visible. Our findings not only elucidate how cognitive fit between a visual representation and a task can manifest itself and the perceptual benefits it brings, but they can also guide the automated layout of models in tools and complement practical process modeling guidelines.

This study investigates how organizations may increase innovation and productivity through the Metaverse environment efficacy (MVEE), Artificial intelligence usage (AIU), Internet of Things usage (IoTU), and Big Data Analytics usage (BDAU). The study gathers responses from the gaming, information technology, and entertainment industries, using a multi-method involving Partial Least Squares Structural Equation Modeling, Fuzzy-set Qualitative Comparative Analysis, and Artificial Neural Networks to investigate how these technologies might be used to improve the linking of disparate realities in a business context. The use of AI in personalized and decision-support applications, IoT for real-time data collecting, and BDAU for an insights-driven strategy all combine to create a dynamic MVEE ecosystem. The research also delves into theoretical implications concerning the viability of using the MVEE to boost innovation and productivity. This research identifies the applications of using AI, IoT, and BDA to drive organizational performance in terms of innovation and productivity. Also, the research lays out the role of AI, IoT, and BDA in creating a dynamic metaverse ecosystem.

The restaurant industry has been slow to adopt analytics for the supply chain, operations, and demand forecasting, with limited research on this sector. The COVID-19 pandemic's significant impact on the restaurant industry, one of the hardest-hit sectors, has underscored the need for digital technologies and advanced analytics for managing supply chains and making operational decisions. This paper presents a collaborative study with one of the largest restaurant chains in the United States, highlighting the value of advanced data analytics in forecasting restaurant demand. The study offers insights into the benefit of integrating external data, including macroeconomic and pandemic-related factors, into demand forecasting. It explores traditional machine learning algorithms and state-of-the-art deep learning architectures, evaluating their effectiveness in the context of the restaurant industry. The paper further discusses the implications of utilizing advanced forecasting models, providing valuable insights for the restaurant industry in the face of supply chain disruptions and pandemics.

In an era where user-generated content drives social media growth, effectively incentivizing contributions remains a challenge. This study explores the empirical impact of a crypto-integrated platform, Steemit, focusing on a system transition designed to enhance fairness in reward distribution. We assess how this shift affects user engagement, specifically through the volume of posts. Our findings indicate that a fairer crypto-reward distribution boosts user-generated posts, though the increase is less pronounced for users with higher capital or reputation. Further analysis reveals the complex dynamics of cryptocurrency rewards and their role in fostering individual contributions and platform growth, while offering financial incentives. The effects of fair distribution are consistent across diverse user groups, highlighting novel incentivization strategies in social media and the transformative potential of integrating cryptocurrencies into reward systems.