[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-146234-105":59,"doc-detail-146234-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","variable-selection-a-comparison-of-various-techniques-rpm-presentation","Variable Selection - A Comparison of Various Techniques - RPM Presentation","","Presentation outlining a practical framework for selecting an effective shortlist from potentially hundreds or thousands of candidate variables for predictive modeling. The work distinguishes variable selection from variable reduction (e.g., principal component analysis) and focuses on ordinal, pre-banded, anonymized geo-demographical variables. It describes problem framing for homeowners fire and water risks (frequency and severity), the dataset structure, the modeling workflow, ranking criteria, and how results are interpreted to guide next steps.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/variable-selection-a-comparison-of-various-techniques-rpm-presentation/146234/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/variable-selection-a-comparison-of-various-techniques-rpm-presentation/146234.png","ImageObject",300,407,{"name":92,"@type":93},"Emma Wilson","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-08","2026-08-26",true,{"@type":102,"interactionType":103,"userInteractionCount":52},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the presentation address in variable selection?","Question",{"text":112,"@type":113},"When predictive modeling has access to hundreds or thousands of candidate variables, it becomes impractical to evaluate them all. The presentation targets selecting a useful shortlist for current modeling techniques.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does variable selection differ from variable reduction?",{"text":117,"@type":113},"Variable reduction creates “super variables,” such as combinations of original variables, with principal component analysis given as a classical example. Variable selection instead identifies which original variables to shortlist.",{"name":119,"@type":110,"acceptedAnswer":120},"What data and modeling context are used for the comparisons?",{"text":121,"@type":113},"The study uses homeowners data across five years, covering water and fire perils with frequency and severity as response measures. It includes a set of core attributes and a large block- or zip-level geo-demographic variable set, with training/testing split for model evaluation.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},146234,1787739177,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":52,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":144},3848291630094,"https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45","Variable Selection  \nA Comparison of Various Techniques  \nA Presentation to RPM March 11, 2015  \nBen Williams Greg Hansen Ari Baraban  \n© 2015 Towers Watson. All rights reserved. Proprietary and Confidential. For Towers Watson and Towers Watson client use only.  \nAntitrust Notice  \n• The Casualty Actuarial Society is committed to adhering strictly to the letter and spirit of the antitrust laws. Seminars conducted under the auspices of the CAS are designed solely to provide a forum for the expression of various points of view on topics described in the programs or agendas for such meetings.  \n• Under no circumstances shall CAS seminars be used as a means for competing companies or firms to reach any understanding – expressed or implied – that restricts competition or in any way impairs the ability of members to exercise independent business judgment regarding matters affecting competition.  \n• It is the responsibility of all seminar participants to be aware of antitrust regulations, to prevent any written or verbal discussions that appear to violate these laws, and to adhere in every respect to the CAS antitrust compliance policy.  \nThis presentation summarizes the work detailed in the paper,“A Practical Approach to Variable Selection– a Comparison of Various Techniques”, by Benjamin Williams, Greg Hansen, Aryeh Barbaran , and Alessandro Santoni.  \nThe paper will be appearing in an upcoming edition of the CAS E-Forum ( [http://www.casact.org/pubs/forum/](http://www.casact.org/pubs/forum/))  \n3  \n[towerswatson.com](towerswatson.com) © 2014 Towers Watson. All rights reserved. Proprietary and Confidential. For Towers Watson and Towers Watson client use only.  \nAgenda  \n􀁺 Variable Selection  \n􀁺 The problem in general  \n􀁺 How we framed it  \n􀁺 Methods  \n􀁺 Lists of methods used  \n􀁺 Overview of selected methods  \n􀁺 Approach  \n􀁺 Data used  \n􀁺 Process  \n􀁺 Ranking criteria  \n􀁺 Conclusions  \n􀁺 Results  \n􀁺 Interpretation and next steps  \n[towerswatson.com](towerswatson.com)  \n4  \n© 2015 Towers Watson. All rights reserved. Proprietary and Confidential. For Towers Watson and Towers Watson client use only.  \nVariable Selection  \n© 2015 Towers Watson. All rights reserved. Proprietary and Confidential. For Towers Watson and Towers Watson client use only.  \nThe Problem  \n􀁺 Between the data stored by companies and that available from external providers, modelers now have access to hundreds or even thousands of variables  \n􀁺 So many variables are available that it is often impractical to consider all of them in a formal predictive modeling context.  \n􀁺 This situation will only be accentuated in the future, as the number of candidate variables continues to grow (Big Data!)  \n􀁺 Recognizing which variables to consider in predictive modeling becomesan important problem for which automated approaches are required.  \n[towerswatson.com](towerswatson.com)  \n6  \n© 2015 Towers Watson. All rights reserved. Proprietary and Confidential. For Towers Watson and Towers Watson client use only.  \nThe Problem  \n􀁺 Note that we are not talking about Variable Reduction, which we consider to be the creation of “Super Variables”, functions of combinationsof the original variables  \n􀁺 A classical example of Variable Reduction is Principal Component Analysis  \n[towerswatson.com](towerswatson.com)  \n7  \n© 2015 Towers Watson. All rights reserved. Proprietary and Confidential. For Towers Watson and Towers Watson client use only.  \nThe Problem  \n􀁺 Stated formally, the question we investigated was:  \nHow to select, from a (potentially very) long list of variables, a shortlist which will be useful for current predictive modeling techniques  \n􀁺 In particular, we limited our investigation to ordinal, pre-banded, anonymized geo-demographical variables  \n􀁺 Context was homeowners fire and water, frequency and severity  \n􀁺 We used a list of variable selection techniques to pick shortlists from the list of variables available, and compared the results, in terms of  \n􀁺 Quality of the res","cbCaiu5Y1SHtbpZH","https://ap.wps.com/l/cbCaiu5Y1SHtbpZH","pdf",1463759,56,"English","# Agenda\n## Variable Selection\n## The problem in general\n## How we framed it\n## Methods\n## Lists of methods used\n## Overview of selected methods\n## Approach\n## Data used\n## Process\n## Ranking criteria\n## Conclusions\n## Results\n## Interpretation and next steps","[{\"question\":\"What problem does the presentation address in variable selection?\",\"answer\":\"When predictive modeling has access to hundreds or thousands of candidate variables, it becomes impractical to evaluate them all. The presentation targets selecting a useful shortlist for current modeling techniques.\"},{\"question\":\"How does variable selection differ from variable reduction?\",\"answer\":\"Variable reduction creates “super variables,” such as combinations of original variables, with principal component analysis given as a classical example. Variable selection instead identifies which original variables to shortlist.\"},{\"question\":\"What data and modeling context are used for the comparisons?\",\"answer\":\"The study uses homeowners data across five years, covering water and fire perils with frequency and severity as response measures. It includes a set of core attributes and a large block- or zip-level geo-demographic variable set, with training/testing split for model evaluation.\"}]","Variable Selection - A Comparison of Various Techniques - RPM Presentation | PDF",141]