[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121728-en":3,"doc-seo-121728-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121728,962075006959,"Anda","https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297",8,"Research & Report","Machine Learning Approaches for Computing Information Value and Information Density - VoI Estimation","Information value (VoI) analysis is central to decision-making when supported by quantitative simulations, yet its practical use is limited by computational efficiency. This thesis investigates machine learning methods for estimating VoI in realistic simulators. It compares smoothing approaches, proves a central limit theorem for a nearest-neighbors method, and introduces automatic neighbor selection via LassoLars weighting. It also modifies an algorithm using MARS regression and evaluates estimators through extensive numerical experiments. The methods are adapted to information density and support consistent variable importance assessments individually and in groups.","Universit `a Commerciale “Luigi Bocconi”  \nPhD School  \nPhD program in: STATISTICS  \nCycle: 34th  \nDisciplinary Field (code): SECS-S/01 STATISTICS  \nMachine Learning Approaches for Computing Information Value and Information Density  \nAdvisor: EMANUELE BORGONOVO  \nPhD Thesis by Mariusz Budzinski ID number: 3084829  \nAcademic Year: 2023  \n1  \n1. Abstract  \nInformation value (VoI) analysis is a key component for decision-making supported by quantitative simulations [37] . A key obstacle to the full utilization of VoI is computational efficiency. This thesis examines the use of machine learning approaches to estimating VoI for realistic simulators. We compare the smoothing approaches already introduced, and propose two novelties. First, an approach based on the nearest neighbors. We prove a central limit theorem and then we discuss the automatic selection of the number of neighbors through a LassoLars weighting approach. We also propose a modification of a previously introduced algorithm by using MARS regression. We compare the resulting estimators through a wide range of numerical experiments. We then adapt the algorithms for the estimation of a new quantity, the information density. Experiments show that the algorithms can be successfully modified and one obtains consistent indications about the regional importance of variables, both individually and in groups.  \nContents 1  \nContents  \n1. Abstract 2  \n2. Acknowledgement 3  \n3 Introduction 5  \n4. Literature Review 7  \n4.1. Information Value 7  \n4.2. The Nearest Neighbors approach 11  \n4.3. Lasso Lars 11  \n5. A Nearest Neibghour Approach to VoI Estimation 12  \n5.1. A Central Limit Theorem Result 12  \n5.2. Cross-validation + LassoLars weighting 15  \n5.3. Local learning approach 18  \n6. Numerical Experiments 19  \n6.1. Case Study 1.[37] 19  \n6.2. Case Study 2 of Strong and Oakley 2014 [37] 24  \n6.3. VoI as feature selection tool for decision problems 29  \n7 Introduction 31  \n8. Information Density 32  \n9. Estimation 37  \n10. Numerical Experiments 40  \n10.1. Results for the Analytical Example 40  \n10.2. Case Study 1.[37] 43  \n10.3. Case Study 2.[37] 46  \n11. Summary 50  \nReferences 51  \n12. Appendix A 55  \n13. Appendix B 65  \n2 Contents  \n2. Acknowledgement  \nAt the outset, I would like to express my deepest thanks to the entire academic staff of Bocconi University’s department of Decicion Sciences for the knowledge they imparted tome, without which this work would not have been written. In particular, I would like to sincerely thank my supervisor and mentor, Prof. Emmanuele Borgonovo, for his support of my person, joint work and forbearance, without which also this work would not have been written. I would also like to thank my parents, my mother Elz˙bieta and especially my father Miroslaw, for their great and continuous support at every stage of my life and education. Without your involvement in my upbringing and education, I would certainly not be where I am now. I sincerely thank you for that. Finally, I would like to dedicate this work, to my dearest daughter Sophia.  \n4 Contents  \nCHAPTER 1  \nESTIMATING INFORMATION VALUE: A COMPARISON OF MACHINE LEARNING APPROACHES  \n3. Introduction  \nDecision-makers rely on the information provided by quantitative models in an increasing number of applications. As [11] highlights, proper uncertainty quantification plays a central role in making the analysis transparent and better informed. Within uncertainty quantification, factor prioritization, i.e. , the identification of the factors that drive uncertainty in model predictions becomes a key task for analysts and decision-makers. For factor prioritization, analysts rely on global sensitivity measures. Indicators in this family range from variance-based ([33],[27]) to distribution-based [5]), to value of information-based indices [25] . Among these sensitivity measures, the value of information is specifically suited to all those applications in which simulation outputs are used to evaluate ","cbCaimBY8gEolDBp","https://ap.wps.com/l/cbCaimBY8gEolDBp","pdf",3537106,1,91,"English","en",105,"# Abstract\n# Acknowledgement\n# Introduction\n# Literature Review\n## Information Value\n## The Nearest Neighbors approach\n## Lasso Lars\n# A Nearest Neibghour Approach to VoI Estimation\n## A Central Limit Theorem Result\n## Cross-validation + LassoLars weighting\n## Local learning approach\n# Numerical Experiments\n## Case Study 1\n## Case Study 2\n## VoI as feature selection tool for decision problems\n# Information Density\n# Estimation\n# Summary\n# References\n# Appendix A\n# Appendix B","[{\"question\":\"Why is information value (VoI) estimation computationally challenging?\",\"answer\":\"VoI definition requires a double-loop Monte Carlo evaluation: first determining the nominal optimal alternative, then re-evaluating the model under conditional sampling for multiple fixed input values.\"},{\"question\":\"What machine learning approaches are proposed for VoI estimation?\",\"answer\":\"The thesis studies smoothing approaches and introduces a nearest-neighbors method, including a central limit theorem, automatic neighbor selection via LassoLars weighting, and an algorithm modification using MARS regression.\"},{\"question\":\"How are the methods extended beyond VoI to information density?\",\"answer\":\"Algorithms are adapted to estimate information density, and experiments show consistent indications of regional variable importance both individually and in groups.\"}]","Machine Learning Approaches for Computing Information Value and Information Density - VoI Estimation | PDF",1785806513,229,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-approaches-for-computing-information-value-and-information-density-voi-estimation","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-approaches-for-computing-information-value-and-information-density-voi-estimation/121728/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is information value (VoI) estimation computationally challenging?","Question",{"text":75,"@type":76},"VoI definition requires a double-loop Monte Carlo evaluation: first determining the nominal optimal alternative, then re-evaluating the model under conditional sampling for multiple fixed input values.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What machine learning approaches are proposed for VoI estimation?",{"text":80,"@type":76},"The thesis studies smoothing approaches and introduces a nearest-neighbors method, including a central limit theorem, automatic neighbor selection via LassoLars weighting, and an algorithm modification using MARS regression.",{"name":82,"@type":73,"acceptedAnswer":83},"How are the methods extended beyond VoI to information density?",{"text":84,"@type":76},"Algorithms are adapted to estimate information density, and experiments show consistent indications of regional variable importance both individually and in groups.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]