The Spatial neural network model with disruptive technology for property appraisal in real estate industry
•A Spatial Neural Network (SNN) model is proposed for automatic property appraisal as required by Basel II and Ш, called Property Appraisal 4.0.•We uses disruptive technology and discover hidden neighbourhood features of real estate information in the satellite embedding vectors.•The latest deep lea...
Gespeichert in:
| Veröffentlicht in: | Technological forecasting & social change 2021-12, Vol.173, p.121067, Article 121067 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | 121067 |
| container_title | Technological forecasting & social change |
| container_volume | 173 |
| creator | Lin, Regina Fang-Ying Ou, Chiye Tseng, Kuo-Kun Bowen, Deng Yung, K.L. Ip, W.H. |
| description | •A Spatial Neural Network (SNN) model is proposed for automatic property appraisal as required by Basel II and Ш, called Property Appraisal 4.0.•We uses disruptive technology and discover hidden neighbourhood features of real estate information in the satellite embedding vectors.•The latest deep learning technologies are also employed, such as knowledge distillation, incremental learning, and Deep-Automated Optical Inspection.•Class Activation Mapping is also adapted to reinforce the proposed spatial neural network in the model.•Experimental results show that our approach's performance is better than that of previous mainstream models,
Property valuation is a complex issue that has always been the focal point for the real estate industry. The traditional valuation models used for appraisals cannot meet real-world demand anymore due to the improper processing of correlated information of nearby facilities. In this study, we propose a Spatial Neural Network (SNN) model, called Property Appraisal 4.0, that uses disruptive technology to forecast property values and discover hidden neighbourhood features of real estate information in the satellite embedding vectors. The latest deep learning technologies are also employed, such as knowledge distillation, incremental learning, and Deep-Automated Optical Inspection. Class Activation Mapping is also adapted to reinforce the proposed spatial neural network in the model. Experimental results show that our approach's performance is better than that of previous mainstream models, such as the Hedonic Pricing Model and Support Vector Machines. |
| doi_str_mv | 10.1016/j.techfore.2021.121067 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2604532097</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0040162521004996</els_id><sourcerecordid>2604532097</sourcerecordid><originalsourceid>FETCH-LOGICAL-c372t-d99cc6e88df543c3e22bd25765300fb4551f214c6e1e218bf33ce0df10f1c893</originalsourceid><addsrcrecordid>eNqFUMtKAzEUDaJgrf6CBFxPvUkm89gp4gsEF3YfpsmNzVgnY5JR-vemVteuDhfO6x5CzhksGLDqsl8k1GvrAy44cLZgnEFVH5AZa2pRSAntIZkBlFCwistjchJjDwC1aKoZ6ZdrpC9jl1y3oQNO4QfSlw9v9N0b3NAvl9bUuBimMblPpLuwwW_865bmTDoGP2JIW9qNY-hczHo30IAZMaYuYT7NFFPYnpIj220inv3inCzvbpc3D8XT8_3jzfVToUXNU2HaVusKm8ZYWQotkPOV4bKupACwq1JKZjkrM4UhZ83KCqERjGVgmW5aMScXe9vc7GPKHVTvpzDkRMUrKKXg0NaZVe1ZOvgYA1o1Bvfeha1ioHazql79zap2s6r9rFl4tRdifuHTYVBROxw0GhdQJ2W8-8_iG03khkw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2604532097</pqid></control><display><type>article</type><title>The Spatial neural network model with disruptive technology for property appraisal in real estate industry</title><source>Elsevier ScienceDirect Journals Complete</source><source>Sociological Abstracts</source><creator>Lin, Regina Fang-Ying ; Ou, Chiye ; Tseng, Kuo-Kun ; Bowen, Deng ; Yung, K.L. ; Ip, W.H.</creator><creatorcontrib>Lin, Regina Fang-Ying ; Ou, Chiye ; Tseng, Kuo-Kun ; Bowen, Deng ; Yung, K.L. ; Ip, W.H.</creatorcontrib><description>•A Spatial Neural Network (SNN) model is proposed for automatic property appraisal as required by Basel II and Ш, called Property Appraisal 4.0.•We uses disruptive technology and discover hidden neighbourhood features of real estate information in the satellite embedding vectors.•The latest deep learning technologies are also employed, such as knowledge distillation, incremental learning, and Deep-Automated Optical Inspection.•Class Activation Mapping is also adapted to reinforce the proposed spatial neural network in the model.•Experimental results show that our approach's performance is better than that of previous mainstream models,
Property valuation is a complex issue that has always been the focal point for the real estate industry. The traditional valuation models used for appraisals cannot meet real-world demand anymore due to the improper processing of correlated information of nearby facilities. In this study, we propose a Spatial Neural Network (SNN) model, called Property Appraisal 4.0, that uses disruptive technology to forecast property values and discover hidden neighbourhood features of real estate information in the satellite embedding vectors. The latest deep learning technologies are also employed, such as knowledge distillation, incremental learning, and Deep-Automated Optical Inspection. Class Activation Mapping is also adapted to reinforce the proposed spatial neural network in the model. Experimental results show that our approach's performance is better than that of previous mainstream models, such as the Hedonic Pricing Model and Support Vector Machines.</description><identifier>ISSN: 0040-1625</identifier><identifier>EISSN: 1873-5509</identifier><identifier>DOI: 10.1016/j.techfore.2021.121067</identifier><language>eng</language><publisher>New York: Elsevier Inc</publisher><subject>Appraisals ; Class activation mapping ; Deep learning ; Deep-Automated Optical Inspection (AOI) ; Disruptive innovation ; Disruptive technology ; Distillation ; Evaluation ; Inspection ; Machinery ; Neural networks ; Property values ; Real estate ; Real estate appraisal ; Real estate valuation ; Spatial information ; Spatial neural network ; Support vector machines ; Technology ; Valuation</subject><ispartof>Technological forecasting & social change, 2021-12, Vol.173, p.121067, Article 121067</ispartof><rights>2021</rights><rights>Copyright Elsevier Science Ltd. Dec 2021</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c372t-d99cc6e88df543c3e22bd25765300fb4551f214c6e1e218bf33ce0df10f1c893</citedby><cites>FETCH-LOGICAL-c372t-d99cc6e88df543c3e22bd25765300fb4551f214c6e1e218bf33ce0df10f1c893</cites><orcidid>0000-0001-9625-829X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.techfore.2021.121067$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,780,784,3550,27924,27925,33774,45995</link.rule.ids></links><search><creatorcontrib>Lin, Regina Fang-Ying</creatorcontrib><creatorcontrib>Ou, Chiye</creatorcontrib><creatorcontrib>Tseng, Kuo-Kun</creatorcontrib><creatorcontrib>Bowen, Deng</creatorcontrib><creatorcontrib>Yung, K.L.</creatorcontrib><creatorcontrib>Ip, W.H.</creatorcontrib><title>The Spatial neural network model with disruptive technology for property appraisal in real estate industry</title><title>Technological forecasting & social change</title><description>•A Spatial Neural Network (SNN) model is proposed for automatic property appraisal as required by Basel II and Ш, called Property Appraisal 4.0.•We uses disruptive technology and discover hidden neighbourhood features of real estate information in the satellite embedding vectors.•The latest deep learning technologies are also employed, such as knowledge distillation, incremental learning, and Deep-Automated Optical Inspection.•Class Activation Mapping is also adapted to reinforce the proposed spatial neural network in the model.•Experimental results show that our approach's performance is better than that of previous mainstream models,
Property valuation is a complex issue that has always been the focal point for the real estate industry. The traditional valuation models used for appraisals cannot meet real-world demand anymore due to the improper processing of correlated information of nearby facilities. In this study, we propose a Spatial Neural Network (SNN) model, called Property Appraisal 4.0, that uses disruptive technology to forecast property values and discover hidden neighbourhood features of real estate information in the satellite embedding vectors. The latest deep learning technologies are also employed, such as knowledge distillation, incremental learning, and Deep-Automated Optical Inspection. Class Activation Mapping is also adapted to reinforce the proposed spatial neural network in the model. Experimental results show that our approach's performance is better than that of previous mainstream models, such as the Hedonic Pricing Model and Support Vector Machines.</description><subject>Appraisals</subject><subject>Class activation mapping</subject><subject>Deep learning</subject><subject>Deep-Automated Optical Inspection (AOI)</subject><subject>Disruptive innovation</subject><subject>Disruptive technology</subject><subject>Distillation</subject><subject>Evaluation</subject><subject>Inspection</subject><subject>Machinery</subject><subject>Neural networks</subject><subject>Property values</subject><subject>Real estate</subject><subject>Real estate appraisal</subject><subject>Real estate valuation</subject><subject>Spatial information</subject><subject>Spatial neural network</subject><subject>Support vector machines</subject><subject>Technology</subject><subject>Valuation</subject><issn>0040-1625</issn><issn>1873-5509</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>BHHNA</sourceid><recordid>eNqFUMtKAzEUDaJgrf6CBFxPvUkm89gp4gsEF3YfpsmNzVgnY5JR-vemVteuDhfO6x5CzhksGLDqsl8k1GvrAy44cLZgnEFVH5AZa2pRSAntIZkBlFCwistjchJjDwC1aKoZ6ZdrpC9jl1y3oQNO4QfSlw9v9N0b3NAvl9bUuBimMblPpLuwwW_865bmTDoGP2JIW9qNY-hczHo30IAZMaYuYT7NFFPYnpIj220inv3inCzvbpc3D8XT8_3jzfVToUXNU2HaVusKm8ZYWQotkPOV4bKupACwq1JKZjkrM4UhZ83KCqERjGVgmW5aMScXe9vc7GPKHVTvpzDkRMUrKKXg0NaZVe1ZOvgYA1o1Bvfeha1ioHazql79zap2s6r9rFl4tRdifuHTYVBROxw0GhdQJ2W8-8_iG03khkw</recordid><startdate>20211201</startdate><enddate>20211201</enddate><creator>Lin, Regina Fang-Ying</creator><creator>Ou, Chiye</creator><creator>Tseng, Kuo-Kun</creator><creator>Bowen, Deng</creator><creator>Yung, K.L.</creator><creator>Ip, W.H.</creator><general>Elsevier Inc</general><general>Elsevier Science Ltd</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7TB</scope><scope>7U4</scope><scope>8FD</scope><scope>BHHNA</scope><scope>DWI</scope><scope>F28</scope><scope>FR3</scope><scope>JQ2</scope><scope>KR7</scope><scope>WZK</scope><orcidid>https://orcid.org/0000-0001-9625-829X</orcidid></search><sort><creationdate>20211201</creationdate><title>The Spatial neural network model with disruptive technology for property appraisal in real estate industry</title><author>Lin, Regina Fang-Ying ; Ou, Chiye ; Tseng, Kuo-Kun ; Bowen, Deng ; Yung, K.L. ; Ip, W.H.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c372t-d99cc6e88df543c3e22bd25765300fb4551f214c6e1e218bf33ce0df10f1c893</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Appraisals</topic><topic>Class activation mapping</topic><topic>Deep learning</topic><topic>Deep-Automated Optical Inspection (AOI)</topic><topic>Disruptive innovation</topic><topic>Disruptive technology</topic><topic>Distillation</topic><topic>Evaluation</topic><topic>Inspection</topic><topic>Machinery</topic><topic>Neural networks</topic><topic>Property values</topic><topic>Real estate</topic><topic>Real estate appraisal</topic><topic>Real estate valuation</topic><topic>Spatial information</topic><topic>Spatial neural network</topic><topic>Support vector machines</topic><topic>Technology</topic><topic>Valuation</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Lin, Regina Fang-Ying</creatorcontrib><creatorcontrib>Ou, Chiye</creatorcontrib><creatorcontrib>Tseng, Kuo-Kun</creatorcontrib><creatorcontrib>Bowen, Deng</creatorcontrib><creatorcontrib>Yung, K.L.</creatorcontrib><creatorcontrib>Ip, W.H.</creatorcontrib><collection>CrossRef</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Sociological Abstracts (pre-2017)</collection><collection>Technology Research Database</collection><collection>Sociological Abstracts</collection><collection>Sociological Abstracts</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Civil Engineering Abstracts</collection><collection>Sociological Abstracts (Ovid)</collection><jtitle>Technological forecasting & social change</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Lin, Regina Fang-Ying</au><au>Ou, Chiye</au><au>Tseng, Kuo-Kun</au><au>Bowen, Deng</au><au>Yung, K.L.</au><au>Ip, W.H.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>The Spatial neural network model with disruptive technology for property appraisal in real estate industry</atitle><jtitle>Technological forecasting & social change</jtitle><date>2021-12-01</date><risdate>2021</risdate><volume>173</volume><spage>121067</spage><pages>121067-</pages><artnum>121067</artnum><issn>0040-1625</issn><eissn>1873-5509</eissn><abstract>•A Spatial Neural Network (SNN) model is proposed for automatic property appraisal as required by Basel II and Ш, called Property Appraisal 4.0.•We uses disruptive technology and discover hidden neighbourhood features of real estate information in the satellite embedding vectors.•The latest deep learning technologies are also employed, such as knowledge distillation, incremental learning, and Deep-Automated Optical Inspection.•Class Activation Mapping is also adapted to reinforce the proposed spatial neural network in the model.•Experimental results show that our approach's performance is better than that of previous mainstream models,
Property valuation is a complex issue that has always been the focal point for the real estate industry. The traditional valuation models used for appraisals cannot meet real-world demand anymore due to the improper processing of correlated information of nearby facilities. In this study, we propose a Spatial Neural Network (SNN) model, called Property Appraisal 4.0, that uses disruptive technology to forecast property values and discover hidden neighbourhood features of real estate information in the satellite embedding vectors. The latest deep learning technologies are also employed, such as knowledge distillation, incremental learning, and Deep-Automated Optical Inspection. Class Activation Mapping is also adapted to reinforce the proposed spatial neural network in the model. Experimental results show that our approach's performance is better than that of previous mainstream models, such as the Hedonic Pricing Model and Support Vector Machines.</abstract><cop>New York</cop><pub>Elsevier Inc</pub><doi>10.1016/j.techfore.2021.121067</doi><orcidid>https://orcid.org/0000-0001-9625-829X</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0040-1625 |
| ispartof | Technological forecasting & social change, 2021-12, Vol.173, p.121067, Article 121067 |
| issn | 0040-1625 1873-5509 |
| language | eng |
| recordid | cdi_proquest_journals_2604532097 |
| source | Elsevier ScienceDirect Journals Complete; Sociological Abstracts |
| subjects | Appraisals Class activation mapping Deep learning Deep-Automated Optical Inspection (AOI) Disruptive innovation Disruptive technology Distillation Evaluation Inspection Machinery Neural networks Property values Real estate Real estate appraisal Real estate valuation Spatial information Spatial neural network Support vector machines Technology Valuation |
| title | The Spatial neural network model with disruptive technology for property appraisal in real estate industry |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-03T15%3A01%3A40IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=The%20Spatial%20neural%20network%20model%20with%20disruptive%20technology%20for%20property%20appraisal%20in%20real%20estate%20industry&rft.jtitle=Technological%20forecasting%20&%20social%20change&rft.au=Lin,%20Regina%20Fang-Ying&rft.date=2021-12-01&rft.volume=173&rft.spage=121067&rft.pages=121067-&rft.artnum=121067&rft.issn=0040-1625&rft.eissn=1873-5509&rft_id=info:doi/10.1016/j.techfore.2021.121067&rft_dat=%3Cproquest_cross%3E2604532097%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2604532097&rft_id=info:pmid/&rft_els_id=S0040162521004996&rfr_iscdi=true |