Francesca Maggioni, Fabrizio Dabbene, Georg Ch. Pflug
{"title":"Sampling methods for multi-stage robust optimization problems","authors":"Francesca Maggioni, Fabrizio Dabbene, Georg Ch. Pflug","doi":"10.1007/s10479-025-06545-4","DOIUrl":"10.1007/s10479-025-06545-4","url":null,"abstract":"<div><p>In this paper, we consider multi-stage robust optimization problems of the minimax type. We assume that the total uncertainty set is the cartesian product of stagewise compact uncertainty sets and approximate the given problem by a sampled subproblem. Instead of looking for the worst case among the infinite and typically uncountable set of uncertain parameters, we consider only the worst case among a randomly selected subset of parameters. By adopting such a strategy, two main questions arise: (1) Can we quantify the error committed by the random approximation, especially as a function of the sample size? (2) If the sample size tends to infinity, does the optimal value converge to the “true” optimal value? Both questions will be answered in this paper. An explicit bound on the probability of violation is given and chain of lower bounds on the original multi-stage robust optimization problem provided. Numerical results dealing with a multi-stage inventory management problem show that the proposed approach works well for problems with two or three time periods while for larger ones the number of required samples is prohibitively large for computational tractability. Despite this, we believe that our results can be useful for problems with such small number of time periods, and it sheds some light on the challenge for problems with more time periods.</p></div>","PeriodicalId":8215,"journal":{"name":"Annals of Operations Research","volume":"347 3","pages":"1385 - 1423"},"PeriodicalIF":4.4,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10479-025-06545-4.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Optimized churn prediction using ensemble-based feature selection via second-order cone programming","authors":"Baha Ulug, Süreyya Akyüz","doi":"10.1007/s10479-025-06543-6","DOIUrl":"10.1007/s10479-025-06543-6","url":null,"abstract":"<div><p>This paper investigates the diverse applications of ensemble-based artificial intelligence algorithms in analyzing customer churn within the banking industry. Additionally, it conducts a comprehensive comparison, rigorously contrasting well-established conventional methods with the relatively less-familiar second-order cone programming (SOCP) ensemble-based feature selection method. Conducting a comprehensive analysis, the study explores large-scale feature engineering using demographic, financial and transactional data. This approach not only enhances the complexity and real-world adaptability of churn analysis methodologies but also makes a significant contribution to business analytics in the banking sector. The research stands as a rare example in the literature, utilizing bank customer data within the interest-free financial system, thereby advancing our understanding of customer relationship management in both the operations research and financial sectors. Banks can use these methods to enhance their customer retention strategies, which may result in lower churn rates and higher customer lifetime value. By minimizing customer churn, banks can improve their financial stability and profitability, potentially leading to more consistent lending practices and lower interest rates for customers.</p></div>","PeriodicalId":8215,"journal":{"name":"Annals of Operations Research","volume":"353 2","pages":"635 - 665"},"PeriodicalIF":4.5,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145296494","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Małgorzata M. O’Reilly, Sebastian Krasnicki, James Montgomery, Mojtaba Heydar, Richard Turner, Pieter Van Dam, Peter Maree
{"title":"Markov decision process and approximate dynamic programming for a patient assignment scheduling problem","authors":"Małgorzata M. O’Reilly, Sebastian Krasnicki, James Montgomery, Mojtaba Heydar, Richard Turner, Pieter Van Dam, Peter Maree","doi":"10.1007/s10479-025-06553-4","DOIUrl":"10.1007/s10479-025-06553-4","url":null,"abstract":"<div><p>We study the patient assignment scheduling (PAS) problem in a random environment that arises in the management of patient flow in hospital systems, due to the stochastic nature of the arrivals as well as the length of stay (LoS) distribution. At the start of each time period, emergency patients in the waiting area of a hospital system need to be admitted to relevant wards. Decisions may involve allocation to less suitable wards, or transfers of the existing inpatients to accommodate higher priority cases when wards are at full capacity. However, the LoS for patients in non-primary wards may increase, potentially leading to long-term congestion. To assist with decision-making in this PAS problem, we construct a discrete-time Markov decision process over an infinite horizon, with multiple patient types and multiple wards. Since the instances of realistic size of this problem are not easy to solve, we develop numerical methods based on approximate dynamic programming. We demonstrate the application potential of our methodology under practical considerations with numerical examples, using parameters obtained from data at a tertiary referral hospital in Australia. We gain valuable insights, such as the number of patients in non-primary wards, the number of transferred patients, and the number of patients redirected to other facilities, under different policies that enhance the system’s performance. This approach allows for more realistic assumptions and can also help determine the appropriate size of wards for different patient types within the hospital system.</p></div>","PeriodicalId":8215,"journal":{"name":"Annals of Operations Research","volume":"347 3","pages":"1493 - 1531"},"PeriodicalIF":4.4,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10479-025-06553-4.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925552","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Mixed frequency data and portfolio selection: A novel approach integrating DEA with\u0000mixed frequency data sources","authors":"Weiqing Wang, Shuhao Liang, Liukai Wang, Yu Xiong","doi":"10.1007/s10479-025-06529-4","DOIUrl":"10.1007/s10479-025-06529-4","url":null,"abstract":"<div><p>This paper presents an innovative approach to portfolio optimization by integrating key elements of asset selection, risk management, and portfolio rebalancing. We first employ the Mixed Data Sampling (MIDAS) model to accurately measure Expected Shortfall (ES). Then, the Range Directional Measure-based Data Envelopment Analysis is considered to assess the portfolio efficiency, which integrates ES, asset returns, and inter-asset correlations for asset selection. Finally, utilizing the mixed frequency data from the metal futures market, we compared the portfolio performance of the Global Minimum ES strategy and the Market Neutral strategy, which reveals that our framework always outperforms traditional benchmarks in multiple aspects. Our findings indicate that, under the comprehensive risk management, a weekly rebalancing strategy is more effective compared to a daily rebalancing scheme. Furthermore, our study demonstrates that stringent asset selection, as opposed to loose selection or non-selection, significantly enhances the overall portfolio performance under the comprehensive risk management. Collectively, this research underscores the necessity of judicious asset selection and rebalance strategies in the modern portfolio management, and validates the practical utility of the portfolio efficiency with DEA and the mixed frequency data sources with MIDAS scheme.</p></div>","PeriodicalId":8215,"journal":{"name":"Annals of Operations Research","volume":"347 3","pages":"1533 - 1565"},"PeriodicalIF":4.4,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}