{"id":{"repo_id":"vilnius","oai_identifier":"oai:vu.lt:elaba:308334516"},"canonical_url":"https://search.ndltd.org/etd/vilnius/oai:vu.lt:elaba:308334516","repository":{"repo_id":"vilnius","name":"Vilnius University","base_url":"https://epublications.vu.lt/oai"},"display":{"title":"Alternatyvus Anykščių rajono savivaldybės žemės verčių zonų sudarymas ir jų tinkamumo sklypų kainų prognozavimui vertinimas /","abstract":"This bachelor’s thesis examines an alternative approach to the formation of real estate value zones using unsupervised and supervised machine learning methods. The study applies the widely used k-means and agglomerative hierarchical clustering methods, as well as the less commonly used spatially constrained SKATER and agglomerative hierarchical clustering methods. The resulting clusters were used to train a support vector classifier, whose predicted classes were included as a feature in a random forest model for predicting land parcel price per are. The proposed approach to value zone formation is based on real estate object data, thereby reducing the need for expert evaluation and contributing to the automation of the value zone formation process. The results of the study showed that different clustering methods produce clusters with varying levels of homogeneity and spatial structure. The k-means and agglomerative hierarchical clustering methods form distinct clusters and identify outlying objects. In contrast, the spatially constrained methods distinguish urban territories, while the remaining objects are grouped into large but homogeneous clusters. When evaluating the methods based on the accuracy of land parcel price prediction, the best results were obtained using the k-means method (RMSE=696.58; MAE=313.49; MAPE=67.27). The accuracy of this model was higher than that of the model using official value zones (RMSE=710.18; MAE=316.63; MAPE=67.54).","abstract_html":"This bachelor’s thesis examines an alternative approach to the formation of real estate value zones using unsupervised and supervised machine learning methods. The study applies the widely used k-means and agglomerative hierarchical clustering methods, as well as the less commonly used spatially constrained SKATER and agglomerative hierarchical clustering methods. The resulting clusters were used to train a support vector classifier, whose predicted classes were included as a feature in a random forest model for predicting land parcel price per are. The proposed approach to value zone formation is based on real estate object data, thereby reducing the need for expert evaluation and contributing to the automation of the value zone formation process. The results of the study showed that different clustering methods produce clusters with varying levels of homogeneity and spatial structure. The k-means and agglomerative hierarchical clustering methods form distinct clusters and identify outlying objects. In contrast, the spatially constrained methods distinguish urban territories, while the remaining objects are grouped into large but homogeneous clusters. When evaluating the methods based on the accuracy of land parcel price prediction, the best results were obtained using the k-means method (RMSE=696.58; MAE=313.49; MAPE=67.27). The accuracy of this model was higher than that of the model using official value zones (RMSE=710.18; MAE=316.63; MAPE=67.54).","abstract_has_math":false,"creators":["Gudonytė, Ieva,"],"institution":"Institutional Repository of Vilnius University","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-11-19T10:12:52Z","subjects":[],"languages":["lit"],"rights":["info:eu-repo/semantics/openAccess"],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://repository.vu.lt/VU:ELABAETD308334516&prefLang=en_US","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://repository.vu.lt/VU:ELABAETD308334516&prefLang=en_US","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":"open","embargo_until":null,"access_note":null},"source_record":{"url":"https://epublications.vu.lt/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Avu.lt%3Aelaba%3A308334516","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Gudonytė, Ieva,"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026"]},{"key":"dc:publisher","label":"Institution","values":["Institutional Repository of Vilnius University"]},{"key":"dc:relation","label":"Dc Relation","values":["https://epublications.vu.lt/object/elaba:308334516/308334516.pdf"]},{"key":"dc:type","label":"Dc Type","values":["info:eu-repo/semantics/bachelorThesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["lit"]},{"key":"dc:rights","label":"Dc Rights","values":["info:eu-repo/semantics/openAccess"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://repository.vu.lt/VU:ELABAETD308334516&prefLang=en_US"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["This bachelor’s thesis examines an alternative approach to the formation of real estate value zones using unsupervised and supervised machine learning methods. The study applies the widely used k-means and agglomerative hierarchical clustering methods, as well as the less commonly used spatially constrained SKATER and agglomerative hierarchical clustering methods. The resulting clusters were used to train a support vector classifier, whose predicted classes were included as a feature in a random forest model for predicting land parcel price per are. The proposed approach to value zone formation is based on real estate object data, thereby reducing the need for expert evaluation and contributing to the automation of the value zone formation process. The results of the study showed that different clustering methods produce clusters with varying levels of homogeneity and spatial structure. The k-means and agglomerative hierarchical clustering methods form distinct clusters and identify outlying objects. In contrast, the spatially constrained methods distinguish urban territories, while the remaining objects are grouped into large but homogeneous clusters. When evaluating the methods based on the accuracy of land parcel price prediction, the best results were obtained using the k-means method (RMSE=696.58; MAE=313.49; MAPE=67.27). The accuracy of this model was higher than that of the model using official value zones (RMSE=710.18; MAE=316.63; MAPE=67.54)."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Alternatyvus Anykščių rajono savivaldybės žemės verčių zonų sudarymas ir jų tinkamumo sklypų kainų prognozavimui vertinimas /","Alternative land value zoning in anykščiai district municipality and evaluation of its suitability for land plot price prediction."]}]}],"canonical_facts":{"dc:creator":["Gudonytė, Ieva,"],"dc:date":["2026"],"dc:description":["This bachelor’s thesis examines an alternative approach to the formation of real estate value zones using unsupervised and supervised machine learning methods. The study applies the widely used k-means and agglomerative hierarchical clustering methods, as well as the less commonly used spatially constrained SKATER and agglomerative hierarchical clustering methods. The resulting clusters were used to train a support vector classifier, whose predicted classes were included as a feature in a random forest model for predicting land parcel price per are. The proposed approach to value zone formation is based on real estate object data, thereby reducing the need for expert evaluation and contributing to the automation of the value zone formation process. The results of the study showed that different clustering methods produce clusters with varying levels of homogeneity and spatial structure. The k-means and agglomerative hierarchical clustering methods form distinct clusters and identify outlying objects. In contrast, the spatially constrained methods distinguish urban territories, while the remaining objects are grouped into large but homogeneous clusters. When evaluating the methods based on the accuracy of land parcel price prediction, the best results were obtained using the k-means method (RMSE=696.58; MAE=313.49; MAPE=67.27). The accuracy of this model was higher than that of the model using official value zones (RMSE=710.18; MAE=316.63; MAPE=67.54)."],"dc:format":["application/pdf"],"dc:identifier":["https://repository.vu.lt/VU:ELABAETD308334516&prefLang=en_US"],"dc:language":["lit"],"dc:publisher":["Institutional Repository of Vilnius University"],"dc:relation":["https://epublications.vu.lt/object/elaba:308334516/308334516.pdf"],"dc:rights":["info:eu-repo/semantics/openAccess"],"dc:title":["Alternatyvus Anykščių rajono savivaldybės žemės verčių zonų sudarymas ir jų tinkamumo sklypų kainų prognozavimui vertinimas /","Alternative land value zoning in anykščiai district municipality and evaluation of its suitability for land plot price prediction."],"dc:type":["info:eu-repo/semantics/bachelorThesis"]},"updated_at":"2026-11-19T10:12:52Z"}