{"title":"局部高斯过程回归法,用于住宅物业的大规模评估","authors":"Jacob Dearmon, Tony E. Smith","doi":"10.1007/s11146-024-09980-5","DOIUrl":null,"url":null,"abstract":"<p>Mass appraisal of single-family homes is now possible using scalable versions of Gaussian process regression. However, it is here shown that the valuation accuracy of such models tends to suffer for higher priced properties where samples are thin. To remedy this, we turn to the industry standard practice of identifying small sets of comparable properties (comps) using rules loosely based on assessor methods. By using a real-world empirical dataset built on a decade’s worth of Assessor database backups, it is shown that this combination of domain expertise with machine learning improves predicted appraisals in a significant way. As part of this analysis, we also introduce and discuss a novel metric, average comp quality, for evaluating the predictive effectiveness of alternative comp sets.</p>","PeriodicalId":22891,"journal":{"name":"The Journal of Real Estate Finance and Economics","volume":"2015 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Local Gaussian Process Regression Approach, to Mass Appraisal of Residential Properties\",\"authors\":\"Jacob Dearmon, Tony E. Smith\",\"doi\":\"10.1007/s11146-024-09980-5\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Mass appraisal of single-family homes is now possible using scalable versions of Gaussian process regression. However, it is here shown that the valuation accuracy of such models tends to suffer for higher priced properties where samples are thin. To remedy this, we turn to the industry standard practice of identifying small sets of comparable properties (comps) using rules loosely based on assessor methods. By using a real-world empirical dataset built on a decade’s worth of Assessor database backups, it is shown that this combination of domain expertise with machine learning improves predicted appraisals in a significant way. As part of this analysis, we also introduce and discuss a novel metric, average comp quality, for evaluating the predictive effectiveness of alternative comp sets.</p>\",\"PeriodicalId\":22891,\"journal\":{\"name\":\"The Journal of Real Estate Finance and Economics\",\"volume\":\"2015 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-02-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"The Journal of Real Estate Finance and Economics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1007/s11146-024-09980-5\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"The Journal of Real Estate Finance and Economics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s11146-024-09980-5","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A Local Gaussian Process Regression Approach, to Mass Appraisal of Residential Properties
Mass appraisal of single-family homes is now possible using scalable versions of Gaussian process regression. However, it is here shown that the valuation accuracy of such models tends to suffer for higher priced properties where samples are thin. To remedy this, we turn to the industry standard practice of identifying small sets of comparable properties (comps) using rules loosely based on assessor methods. By using a real-world empirical dataset built on a decade’s worth of Assessor database backups, it is shown that this combination of domain expertise with machine learning improves predicted appraisals in a significant way. As part of this analysis, we also introduce and discuss a novel metric, average comp quality, for evaluating the predictive effectiveness of alternative comp sets.