[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120203-en":3,"doc-seo-120203-105":30,"detail-sidebar-cat-0-en-105":83},{"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},120203,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Can machine learning algorithms deliver superior models for rental guides - paper","The paper investigates whether machine learning–driven models improve rent prediction in Germany’s rental guides (Mietspiegel), which traditionally rely on regression or simple contingency tables. Using Munich rental guide data, the study evaluates predictive power, emphasizing performance under the “black-box” issue of interpretability. It further examines robustness through adversarial effects by analyzing how corrupted inputs alter prediction quality. Results indicate that models with stronger predictive accuracy may be more vulnerable to data corruption than classical linear approaches such as Ridge or Lasso.","AStA Wirtschafts-und Sozialstatistisches Archiv (2023) 17:305–330  \n[https://doi.org/10.1007/s11943-023-00333-x](https://doi.org/10.1007/s11943-023-00333-x)  \nORIGINALVERÖFFENTLICHUNG  \nCan machine learning algorithms deliver superior models for rental guides?  \nOliver Trinkaus · Göran Kauermann  \nReceived: 11 April 2023 / Accepted: 13 November 2023 / Published online: 12 December 2023 © The Author(s) 2023  \nAbstract In this paper we discuss the use and potential advantages and disadvantages of machine learning driven models in rental guides. Rental guides are a formal legal instrument in Germany for surveying rents of flats in cities and municipalities, which are today based on regression models or simple contingency tables. We discuss if and how modern and timely methods of machine learning outperform existing and established routines. We make use of data from the Munich rental guide and mainly focus on the predictive power of these models. We discuss the “black-box”character making some of these models difficult to interpret and hence challenging for applications in the rental guide context. Still, it is of interest to see how “blackbox” models perform with respect to prediction error. Moreover, we study adversarial effects, i.e. we investigate robustness in the sense how corrupted data influence the performance of the prediction models. With the data at hand we show that models with promising predictive performance suffer from being more vulnerable to corruptions than classic linear models including Ridge or Lasso regularization.  \nKeywords Machine learning · Statistical learning · Regression · Adversarial regression · Mietspiegel · Rental guide  \n􀀂 Oliver Trinkaus  \nEMA-Institut für empirische Marktanalysen, Regensburg, Germany E-Mail: [trinkaus@ema-institut.de](trinkaus@ema-institut.de)  \n􀀂 Göran Kauermann  \nLudwig-Maximilians-Universität München, München, Germany [E-Mail: Goeran.Kauermann@stat.uni-muenchen.de](E-Mail: Goeran.Kauermann@stat.uni-muenchen.de)  \nK  \n1 Introduction  \nRental guides for flats are an official instrument in the German rental market, see e.g. Kauermann and Windmann (2016) . Based on regular surveys, city councils issue the average rent for flats given the flat’s facilities, like floor space, year of construction and facilities such as well equipped kitchen or high standard bathroom. Given available survey data one is interested in constructing a prediction model for the rent per squared meter, given the input variables, which we call features subsequently. Denoting the features as x and the rent per squared meter as y we are interested in finding a good prediction model  \ny D f.x/ C \" (1)  \nwhere \" is considered as noise, mirroring market price variation. We denote y subsequently also as response variable.  \nBefore discussing the statistical approaches to tackle function f.x/ in (1) we want to add some more explanation about rental guides in Germany. These are used as an instrument to infringe on a landlord’s constitutional rights to his property (Art. 14 German Constitution) . Therefore, a judge, in order to deny a landlord a rent increase, will need a solid base for his judgment. Rental guides aim to fulfill this purpose. This, in turn, seem to exclude “black box models” from the set of instruments that one should use. Moreover, there is a significant amount of vested interest involved in the process of rental guide creation which of course increases the likeliness of data corruption to occur. Hence, careful and detailed guidelines for rental guides are inevitable. With this being said, we can now approach rental guides formally as a prediction model. We also refer to Kauermann and Windmann (2016) and Fitzenberger and Fuchs (2017) for more details.  \nIn times of increased usage of machine learning methods we can consider Eq. (1) as a supervised learning setting. Hence, we may take advantage of the toolbox of available machine learning algorithms to train or estimate a suitable prediction model f. A classi","cbCaiumg09rSuvHa","https://ap.wps.com/l/cbCaiumg09rSuvHa","pdf",1108140,1,26,"English","en",105,"# Introduction\n## Rental guides in Germany\n## Supervised learning and regression baselines\n## Machine learning models for rent prediction\n## Interpretability and the black-box concern\n## Robustness and adversarial effects","[{\"question\":\"What data is used for model evaluation?\",\"answer\":\"The analysis uses data from the Munich rental guide and focuses primarily on prediction error and related performance measures.\"}]","Can machine learning algorithms deliver superior models for rental guides - paper | PDF",1785728710,66,{"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":78,"head_meta":80,"extra_data":82,"updated_unix":28},"can-machine-learning-algorithms-deliver-superior-models-for-rental-guides-paper","",{"@graph":36,"@context":77},[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/can-machine-learning-algorithms-deliver-superior-models-for-rental-guides-paper/120203/",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","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"What data is used for model evaluation?","Question",{"text":75,"@type":76},"The analysis uses data from the Munich rental guide and focuses primarily on prediction error and related performance measures.","Answer","https://schema.org",{"og:url":52,"og:type":79,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":81,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,112,115,120,123,127],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":46,"category_name":109,"show_sort_weight":110,"slug":111},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":113,"slug":114},30,"research-report",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":98,"slug":130},19,"General","general"]