Applied Stochastic Models in Business and Industry最新文献

{"title":"Dynamic Bayesian Networks with Conditional Dynamics in Edge Additions and Deletions","authors":"Lupe S. H. Chan, Amanda M. Y. Chu, Mike K. P. So","doi":"10.1002/asmb.70135","DOIUrl":"https://doi.org/10.1002/asmb.70135","url":null,"abstract":"<div>\u0000 \u0000 <p>This study presents a dynamic Bayesian network framework that facilitates intuitive, gradual edge changes. We use two conditional dynamics to model the edge additions and deletions, as well as edge selections, separately. In contrast to previous research that employed a mixture network approach—which limits the number of edge changes—or relied on structural priors to induce gradual changes—often leading to ambiguous network evolution—our model fosters more frequent and intuitive edge change dynamics. Moreover, when the maximum number of parents for the nodes in the network is <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>d</mi>\u0000 <mo>≪</mo>\u0000 <mi>n</mi>\u0000 </mrow>\u0000 <annotation>$$ dll n $$</annotation>\u0000 </semantics></math>, the correlation matrix can be represented by at most <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>n</mi>\u0000 <mi>d</mi>\u0000 <mo>=</mo>\u0000 <mi>O</mi>\u0000 <mo>(</mo>\u0000 <mi>n</mi>\u0000 <mo>)</mo>\u0000 </mrow>\u0000 <annotation>$$ nd=O(n) $$</annotation>\u0000 </semantics></math> correlations. In contrast, conventional dynamic correlation models necessitate <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>n</mi>\u0000 <mo>(</mo>\u0000 <mi>n</mi>\u0000 <mo>−</mo>\u0000 <mn>1</mn>\u0000 <mo>)</mo>\u0000 <mo>/</mo>\u0000 <mn>2</mn>\u0000 <mo>=</mo>\u0000 <mi>O</mi>\u0000 <mo>(</mo>\u0000 <msup>\u0000 <mrow>\u0000 <mi>n</mi>\u0000 </mrow>\u0000 <mrow>\u0000 <mn>2</mn>\u0000 </mrow>\u0000 </msup>\u0000 <mo>)</mo>\u0000 </mrow>\u0000 <annotation>$$ nleft(n-1right)/2=Oleft({n}^2right) $$</annotation>\u0000 </semantics></math> correlations. Consequently, the structure specified by the Bayesian network facilitates dimensionality reduction of the correlation matrix from <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>O</mi>\u0000 <mo>(</mo>\u0000 <msup>\u0000 <mrow>\u0000 <mi>n</mi>\u0000 </mrow>\u0000 <mrow>\u0000 <mn>2</mn>\u0000 </mrow>\u0000 </msup>\u0000 <mo>)</mo>\u0000 </mrow>\u0000 <annotation>$$ Oleft({n}^2right) $$</annotation>\u0000 </semantics></math> to <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>O</mi>\u0000 <mo>(</mo>\u0000 <mi>n</mi>\u0000 <mo>)</","PeriodicalId":55495,"journal":{"name":"Applied Stochastic Models in Business and Industry","volume":"42 6","pages":""},"PeriodicalIF":1.5,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149177561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Strategy for Data-Based Problem Solving","authors":"Ronald D. Snee","doi":"10.1002/asmb.70134","DOIUrl":"https://doi.org/10.1002/asmb.70134","url":null,"abstract":"<div>\u0000 \u0000 <p>A strategy for data-based problem solving is presented. Strategy, a plan for being successful, is essential for any endeavor to be successful. Unfortunately, the statistical community has not placed a great deal of focus on strategy in the past. In this article, strategy is defined and its importance is delineated. The strategy presented has been developed over six decades, integrating the author's experiences and methods and those of other professionals working in the field. The overall strategy involves two interacting sub-strategies—Problem Solving and Data Analysis. The critical elements of each strategy are identified, illustrated, and referenced.</p>\u0000 </div>","PeriodicalId":55495,"journal":{"name":"Applied Stochastic Models in Business and Industry","volume":"42 5","pages":""},"PeriodicalIF":1.5,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149146451","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SEC Form N-PORT: Insights on Fund Holdings Changes","authors":"Meredith Kruse,&nbsp;Katherine B. Ensor","doi":"10.1002/asmb.70130","DOIUrl":"https://doi.org/10.1002/asmb.70130","url":null,"abstract":"<p>Investigating the dynamic relationship between institutional investment and market returns, this paper addresses how equity price is correlated with changes in institutional investment fund holdings using data from the Securities and Exchange Commission Form N-PORT. The focus is on changes in quarterly fund holding of small-cap equities in the Russell 2000 from 2020-03-31 to 2024-12-31. For our analysis, we use both fixed and random effects panel regression to show the relationship between changes in fund holdings and asset returns. The results suggest that fund holding flow information, as reported in N-PORT filings, provides important insight into institutional trading behavior and individual asset returns. Our work builds on existing literature that uses 13F data and demonstrates the added value of N-PORT for fund flow analysis.</p>","PeriodicalId":55495,"journal":{"name":"Applied Stochastic Models in Business and Industry","volume":"42 5","pages":""},"PeriodicalIF":1.5,"publicationDate":"2026-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/asmb.70130","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149146229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Foreword to the Special Issue on The Foundations of Applied Statistics","authors":"Ron S. Kenett,&nbsp;David M. Steinberg","doi":"10.1002/asmb.70136","DOIUrl":"https://doi.org/10.1002/asmb.70136","url":null,"abstract":"&lt;p&gt;Statisticians have responded to challenges posed in such areas by pioneering methods for the collection and analysis of data, by developing predictive analytics, and by supporting decision support systems. Box [&lt;span&gt;1&lt;/span&gt;] places special emphasis on the role of applications in stimulating statistical research, pointing to many illustrative examples in science and engineering. Cox [&lt;span&gt;2&lt;/span&gt;] maps out a general theory of statistical inference; Kass [&lt;span&gt;3&lt;/span&gt;] writes that the need to thoughtfully analyze data leads to substantial common ground across different theories of statistical inference, a view he describes as “statistical pragmatism.” Neyman [&lt;span&gt;4&lt;/span&gt;] and Rubin [&lt;span&gt;5&lt;/span&gt;] exploit potential outcomes to assess the effect of interventions; Pearl [&lt;span&gt;6&lt;/span&gt;] and Bareinboim et al. [&lt;span&gt;7&lt;/span&gt;] consider a causal hierarchy structure with observed data in the lower layer followed by the study interventions and counterfactuals. With a computer science perspective, Feder et al. [&lt;span&gt;8&lt;/span&gt;] consider causality in large language models, and Raghavan and Bareinboim [&lt;span&gt;9&lt;/span&gt;] introduce models to account for realizable counterfactuals. These are just examples of developments in statistics and its applications.&lt;/p&gt;&lt;p&gt;In the last decade, an exponential growth in data, sensing, and computing technologies has made statistics an essential component of data science and other analytic disciplines. We present below some proposals for general frameworks of analytics and applied statistics. These contributions are more strategic in scope.&lt;/p&gt;&lt;p&gt;Donoho [&lt;span&gt;10&lt;/span&gt;] describes three socio-technical initiatives that affect the evolution of analytics and data science. He labels this evolution “frictionless reproducibility.” These initiatives are: [FR-1: Data] Availability of online publicly accessible datasets on a wide range of application domains. [FR-2: Re-execution] Sharing of code to exactly re-execute the same data analysis workflow and [FR-3: Challenges] Adopting challenge problems as a leading paradigm powering methodological research.&lt;/p&gt;&lt;p&gt;Yu and Kumbier [&lt;span&gt;11&lt;/span&gt;] propose a framework consisting of (i) predictability, (ii) computability, and (iii) stability, labeled “PCS.” With PCS one can then show that results are predictable by computationally demonstrating that they re-emerge in relevant future data and are in line with domain knowledge. Results from analytics are demonstrated as stable if they do not change when changes are made throughout an analytic life cycle. Such cycles account for the real work of data science [&lt;span&gt;12&lt;/span&gt;]. By demonstrating that results are predictable and stable, one provides evidence that data-driven conclusions are trustworthy and relevant to reality.&lt;/p&gt;&lt;p&gt;Many of our colleagues who are engaged in analytics and applied statistics have forged principles and guidelines that shape the way they contribute to projects. These principles run from problem identification","PeriodicalId":55495,"journal":{"name":"Applied Stochastic Models in Business and Industry","volume":"42 5","pages":""},"PeriodicalIF":1.5,"publicationDate":"2026-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/asmb.70136","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149145578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Modeling Power Outages Under a Random Environment: A Bayesian Approach","authors":"Atilla Ay,&nbsp;Fabrizio Ruggeri,&nbsp;Refik Soyer","doi":"10.1002/asmb.70132","DOIUrl":"https://doi.org/10.1002/asmb.70132","url":null,"abstract":"<div>\u0000 \u0000 <p>We consider modeling the number of households affected by power outages occurring in multiple locations. In so doing, we assume that the power distribution systems in those locations operate under a common environment. For each location, we consider a compound Poisson process to model the number of affected households, whose jump rate (outage rate) and jump size (the number affected by each outage) change with the changing environment which is modeled as a latent Markov process. Therefore, we refer to this model as a Markov modulated multiple compound Poisson process. Given the state of the environment, the occurrence of power outages in different regions and the number of households affected by each power outage are assumed to be conditionally independent. We extend the model to account for regional variation in a deterministic manner by using covariates on outage rates and the number of affected households. We use simulated and real power outage data from five counties in Northern Virginia (USA) to illustrate the proposed model.</p>\u0000 </div>","PeriodicalId":55495,"journal":{"name":"Applied Stochastic Models in Business and Industry","volume":"42 5","pages":""},"PeriodicalIF":1.5,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149145882","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Forecasting Technology Adoption in Uncertain and Dynamic Markets: A Market Coverage Diffusion Approach","authors":"Umashankar Samal","doi":"10.1002/asmb.70131","DOIUrl":"https://doi.org/10.1002/asmb.70131","url":null,"abstract":"<div>\u0000 \u0000 <p>How innovations spread in a fast-changing and uncertain market is vital for accurate forecasting and planning. This study introduces a generalized diffusion framework that incorporates evolving market coverage along with dynamic market and market uncertainty. A random variable is used to represent market uncertainty, while three coverage functions, exponential, delayed, and logistic are used to capture different patterns of market growth. The models are evaluated on two different data sets: quarterly sales of battery electric vehicles (BEVs) and quarterly sales of Apple iPhones. The performance of the proposed models is compared to that of some benchmark diffusion models using various error and information-based measures. The results indicate that the proposed models outperform the existing ones. Among the proposed models, the model with the logistic coverage provides the best fit for both data sets as it can capture the early growth and later stabilization more effectively. The study also highlights the differences in adoption patterns for infrastructure-driven technologies, such as BEVs, and fast-moving consumer products, like smartphones.</p>\u0000 </div>","PeriodicalId":55495,"journal":{"name":"Applied Stochastic Models in Business and Industry","volume":"42 5","pages":""},"PeriodicalIF":1.5,"publicationDate":"2026-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149146620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improved Genetic Algorithm-Optimized SVR for Robust Long-Term Forecasting of Global Stock Indices for Investment Decisions","authors":"Mohit Beniwal","doi":"10.1002/asmb.70133","DOIUrl":"https://doi.org/10.1002/asmb.70133","url":null,"abstract":"<div>\u0000 \u0000 <p>Accurate long-term forecasts are essential for high-net-worth individuals, institutional investors, and traders, yet long-term multi-step price forecasting remains a formidable challenge due to the inherent uncertainty over the long term. The proposed improved genetic algorithm-optimized support vector regression (IGA-SVR) model is specifically designed for long-term price prediction of global indices. The genetic algorithm optimizes the SVR hyperparameters by minimizing a weighted average Mean Absolute Percentage Error (MAPE), assigning 20% weight to the full training dataset and 80% to the latest month validation window. The performance of the IGA-SVR model is evaluated against four baseline models: Long Short-Term Memory (LSTM), N-BEATS, Transformer, and the forward-validating genetic algorithm optimized support vector regression (OGA-SVR). Extensive testing was conducted on the five global indices: Nifty, Dow Jones Industrial Average (DJI), DAX Performance Index (DAX), Nikkei 225 (N225), and Shanghai Stock Exchange Composite Index (SSE) from 2021 to 2024 on daily price prediction up to a year. Overall, the IGA-SVR model achieved lower MAPE than other models, outperforming Transformer by 19.4%, LSTM by 24.5%, N-BEATS by 41.3%, and OGA-SVR by 55.1% on 1-year daily price forecasting of global indices. Further, IGA-SVR achieved an execution time reduction of 80% compared to N-BEATS and 86% compared to LSTM and Transformer, highlighting its computational efficiency. Unlike rolling-forward validation approaches that suffer from recency bias or deep learning models requiring heavy computation, IGA-SVR provides a better accuracy and computationally efficient alternative for long-term financial time series forecasting.</p>\u0000 </div>","PeriodicalId":55495,"journal":{"name":"Applied Stochastic Models in Business and Industry","volume":"42 5","pages":""},"PeriodicalIF":1.5,"publicationDate":"2026-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149146621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"On the Mixed Delta-Shock Model With Dependencies","authors":"Maxim Finkelstein,&nbsp;Ji Hwan Cha","doi":"10.1002/asmb.70129","DOIUrl":"https://doi.org/10.1002/asmb.70129","url":null,"abstract":"<div>\u0000 \u0000 <p>We consider the survival of a system subject to the renewal process of shocks. A system can fail when shocks are ‘too close’ to each other. The corresponding window for the failure is defined, which increases monotonically with the magnitude of a shock. Thus, more time is needed for a system to recover after a shock with a larger magnitude. A system can also fail when the magnitude of a shock is larger than a critical level, which is a property of the classical extreme shock model. To model negative dependence between shock magnitudes and subsequent interarrival times, we adopt a conditional intensity approach, when the arrival rate of the next shock depends monotonically on the magnitude of the previous shock. It captures directly the causal effect of large shocks accelerating future arrivals. Survival probabilities for a general and specific models are obtained and analysed. Some numerical examples illustrating our findings are presented.</p>\u0000 </div>","PeriodicalId":55495,"journal":{"name":"Applied Stochastic Models in Business and Industry","volume":"42 5","pages":""},"PeriodicalIF":1.5,"publicationDate":"2026-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148994511","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From Cure Rate Models to Explainable Survival Analysis: SurvSHAP Based Insights for Credit Risk","authors":"Jacob Majakwara","doi":"10.1002/asmb.70128","DOIUrl":"https://doi.org/10.1002/asmb.70128","url":null,"abstract":"<p>This study proposes a unified credit risk framework that combines mixture cure rate models with time-varying SurvSHAP(t) explanations. The model separates the risk of default into incidence submodel (whether default occurs) and latency submodel (when default occurs among susceptibles). A simulation study shows accurate parameter recovery and reliable coverage in low- and high-cure-rate settings, with SurvSHAP(t) correctly identifying incidence, latency, and noise variables. Empirical results for Prosper P2P lending and mortgage data show that the lognormal mixture cure rate model outperforms standard survival models, reflecting non-monotonic default hazard and substantial cured subpopulations. Credit score drives the incidence submodel, while behavioural and macroeconomic variables govern the latency submodel. SurvSHAP(t) reveals consistent temporal structure across simulation and real data: incidence submodel effects dominate long-term survival, while latency submodel effects are strongest early in time. The framework provides an interpretable and statistically sound tool for credit risk modelling, supporting risk stratification and regulatory transparency.</p>","PeriodicalId":55495,"journal":{"name":"Applied Stochastic Models in Business and Industry","volume":"42 5","pages":""},"PeriodicalIF":1.5,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/asmb.70128","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Single Server Markovian Queue With Time-Homogeneous Partial and Complete Breakdowns and Cost Optimization by Genetic Algorithm","authors":"K. Santhi,&nbsp;S. Pazhani Bala Murugan,&nbsp;B. Manikandan","doi":"10.1002/asmb.70127","DOIUrl":"https://doi.org/10.1002/asmb.70127","url":null,"abstract":"<div>\u0000 \u0000 <p>This paper investigates the steady-state performance of an <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>M</mi>\u0000 <mo>/</mo>\u0000 <mi>M</mi>\u0000 <mo>/</mo>\u0000 <mn>1</mn>\u0000 </mrow>\u0000 <annotation>$$ M/M/1 $$</annotation>\u0000 </semantics></math> queueing system subject to random and time-homogeneous partial and complete server breakdowns. Under partial breakdown conditions, the server continues to provide service at a reduced rate, while service is entirely suspended during complete breakdown periods. By applying the Probability Generating Function (PGF) methodology, the joint probability distribution of the server state and the number of customers in the system is obtained. Several key performance measures are derived and numerically illustrated to highlight the influence of system parameters on overall performance. In addition, a structured cost model is developed to account for service, breakdown, and holding costs. A Genetic Algorithm (GA) is then employed to optimize the cost function and identify effective operational strategies for handling partial and complete breakdowns.</p>\u0000 </div>","PeriodicalId":55495,"journal":{"name":"Applied Stochastic Models in Business and Industry","volume":"42 5","pages":""},"PeriodicalIF":1.5,"publicationDate":"2026-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942163","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}