Accuracy measurement of Random Forests and Linear Regression for mass appraisal models that estimate the prices of residential apartments in Nicosia, Cyprus
Thomas Dimopoulos
CORRESPONDING AUTHOR
Neapolis University Pafos, School of Architecture, Engineering, Land
and Environmental Sciences, 2 Danais Avenue, 8042 Paphos, Cyprus
Cyprus University of Technology, School of Surveying Engineering and
Geoinformatics, 30 Arch. Kyprianos Str., 3036 Limassol, Cyprus
Hristos Tyralis
Air Force Support Command, Hellenic Air Force, Elefsina, 192 00,
Greece
Nikolaos P. Bakas
Neapolis University Pafos, School of Architecture, Engineering, Land
and Environmental Sciences, 2 Danais Avenue, 8042 Paphos, Cyprus
Diofantos Hadjimitsis
Cyprus University of Technology, School of Surveying Engineering and
Geoinformatics, 30 Arch. Kyprianos Str., 3036 Limassol, Cyprus
Related authors
No articles found.
Alexandra Tsekeri, Anna Gialitaki, Marco Di Paolantonio, Davide Dionisi, Gian Luigi Liberti, Alnilam Fernandes, Artur Szkop, Aleksander Pietruczuk, Daniel Pérez-Ramírez, Maria J. Granados Muñoz, Juan Luis Guerrero-Rascado, Lucas Alados-Arboledas, Diego Bermejo Pantaleón, Juan Antonio Bravo-Aranda, Anna Kampouri, Eleni Marinou, Vassilis Amiridis, Michael Sicard, Adolfo Comerón, Constantino Muñoz-Porcar, Alejandro Rodríguez-Gómez, Salvatore Romano, Maria Rita Perrone, Xiaoxia Shang, Mika Komppula, Rodanthi-Elisavet Mamouri, Argyro Nisantzi, Diofantos Hadjimitsis, Francisco Navas-Guzmán, Alexander Haefele, Dominika Szczepanik, Artur Tomczak, Iwona S. Stachlewska, Livio Belegante, Doina Nicolae, Kalliopi Artemis Voudouri, Dimitris Balis, Athena A. Floutsi, Holger Baars, Linda Miladi, Nicolas Pascal, Oleg Dubovik, and Anton Lopatin
Atmos. Meas. Tech., 16, 6025–6050, https://doi.org/10.5194/amt-16-6025-2023, https://doi.org/10.5194/amt-16-6025-2023, 2023
Short summary
Short summary
EARLINET/ACTRIS organized an intensive observational campaign in May 2020, with the objective of monitoring the atmospheric state over Europe during the COVID-19 lockdown and relaxation period. The work presented herein focuses on deriving a common methodology for applying a synergistic retrieval that utilizes the network's ground-based passive and active remote sensing measurements and deriving the aerosols from anthropogenic activities over Europe.
G. Giannarakis, I. Tsoumas, S. Neophytides, C. Papoutsa, C. Kontoes, and D. Hadjimitsis
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLVIII-1-W2-2023, 1379–1384, https://doi.org/10.5194/isprs-archives-XLVIII-1-W2-2023-1379-2023, https://doi.org/10.5194/isprs-archives-XLVIII-1-W2-2023-1379-2023, 2023
M. Tzouvaras, S. Alatza, M. Prodromou, C. Theocharidis, K. Fotiou, A. Argyriou, C. Loupasakis, A. Apostolakis, Z. Pittaki, M. Kaskara, C. Kontoes, and D. Hadjimitsis
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLVIII-1-W2-2023, 1581–1587, https://doi.org/10.5194/isprs-archives-XLVIII-1-W2-2023-1581-2023, https://doi.org/10.5194/isprs-archives-XLVIII-1-W2-2023-1581-2023, 2023
Rodanthi-Elisavet Mamouri, Albert Ansmann, Kevin Ohneiser, Daniel A. Knopf, Argyro Nisantzi, Johannes Bühl, Ronny Engelmann, Annett Skupin, Patric Seifert, Holger Baars, Dragos Ene, Ulla Wandinger, and Diofantos Hadjimitsis
Atmos. Chem. Phys., 23, 14097–14114, https://doi.org/10.5194/acp-23-14097-2023, https://doi.org/10.5194/acp-23-14097-2023, 2023
Short summary
Short summary
For the first time, rather clear evidence is found that wildfire smoke particles can trigger strong cirrus formation. This finding is of importance because intensive and large wildfires may occur increasingly often in the future as climate change proceeds. Based on lidar observations in Cyprus in autumn 2020, we provide detailed insight into the cirrus formation at the tropopause in the presence of aged wildfire smoke (here, 8–9 day old Californian wildfire smoke).
Evagoras Evagorou, Christodoulos Mettas, Athos Agapiou, Kyriacos Themistocleous, and Diofantos Hadjimitsis
Adv. Geosci., 45, 397–407, https://doi.org/10.5194/adgeo-45-397-2019, https://doi.org/10.5194/adgeo-45-397-2019, 2019
Short summary
Short summary
Freely and open distributed optical satellite images used to obtain bathymetric data for shallow waters based on timeseries analysis of multispectral Sentinel-2 datasets. The ratio transform algorithm was implemented for twelve monthly images covering a year. Bathymetric maps were generated and compared with LIDAR measurements. The results showed that bathymetry can be obtained from satellite data within a Root Mean Square Error while more accurate results were generated during the summer.
Maroula N. Alverti, Kyriakos Themistocleous, Phaedon C. Kyriakidis, and Diofantos G. Hadjimitsis
Adv. Geosci., 45, 305–320, https://doi.org/10.5194/adgeo-45-305-2018, https://doi.org/10.5194/adgeo-45-305-2018, 2018
Short summary
Short summary
The scientific objective is to find a simple understandable model linking human smart characteristics to a group of socio-demographic and urban environment indices, applied to the case of Limassol Urban Complex, Cyprus. The results reveal that the human smart characteristics are significantly correlated with demographic dynamics and built infrastructure characteristics. For instance creativity and open-mindedness appear in most densely urban areas.
Georgia A. Papacharalampous and Hristos Tyralis
Adv. Geosci., 45, 201–208, https://doi.org/10.5194/adgeo-45-201-2018, https://doi.org/10.5194/adgeo-45-201-2018, 2018
Short summary
Short summary
The predictive performance of random forests (a machine learning algorithm)
and three configurations of Prophet (a method largely implemented in
Facebook) is assessed in daily streamflow forecasting in a river in the US.
Random forests perform better compared to the utilized benchmarks, i.e. a naïve
method and a multiple regression linear model, while Prophet's performance is
subject to improvements. Random forests are recommended for daily streamflow
forecasting.
Hristos Tyralis and Georgia A. Papacharalampous
Adv. Geosci., 45, 147–153, https://doi.org/10.5194/adgeo-45-147-2018, https://doi.org/10.5194/adgeo-45-147-2018, 2018
Short summary
Short summary
We use the CAMELS dataset to compare two different approaches in multi-step ahead forecasting of monthly streamflow. The first approach uses past monthly streamflow information only, while the second approach additionally uses past information about monthly precipitation and/or temperature (exogenous information). The incorporation of exogenous information is made by utilizing Prophet, a model largely implemented in Facebook. The findings suggest that the compared approaches are equally useful.
Rodanthi-Elisavet Mamouri, Albert Ansmann, Argyro Nisantzi, Stavros Solomos, George Kallos, and Diofantos G. Hadjimitsis
Atmos. Chem. Phys., 16, 13711–13724, https://doi.org/10.5194/acp-16-13711-2016, https://doi.org/10.5194/acp-16-13711-2016, 2016
Cited articles
Antipov, E. A. and Pokryshevskaya, E. B.: Mass appraisal of residential
apartments: An application of Random forest for valuation and a CART-based
approach for model diagnostics, Expert Syst. Appl., 39, 1772–1778, 2012.
Benjamin, J. D., Guttery, R. S., and Sirmans, C. F.: Mass appraisal: An
introduction to multiple regression analysis for real estate valuation,
Journal of Real Estate Practice and Education, 7, 65–77, 2004
Breiman, L.: Random forests, Mach. Learn., 45, 5–32, 2001.
Dimopoulos, T. and Moulas, A: A proposal of a mass appraisal system in Greece
with CAMA system. Evaluating GWR and MRA techniques. The case study of
Thessaloniki Municipality, Open Geosci., 8.1, https://doi.org/10.1515/geo-2016-0064,
2016.
Liu, X., Deng, Z., and Wang, T.: Real estate appraisal system based on GIS
and BP neural network, T. Nonferr. Metal. Soc., 21, s626–s630, 2011.
Plevris, V., Bakas, N., Markeset, G., and Bellos, J.: Literature review of
masonry structures under earthquake excitation utilizing machine learning
algorithms, COMPDYN, https://doi.org/10.7712/120117.5598.18688, 2017.
Pokryshevskaya, E. B. and Antipov, E. A.: Applying a CART-based approach for
the diagnostics of mass appraisal models, Econ. Bull., 31, 2521–2528, 2011.
Robnik-Šikonja, M. and Kononenko, I.: Theoretical and empirical analysis
of ReliefF and RReliefF, Mach. Learn., 53, 23–69, 2003.
SCOPUS database: available at:
https://www.scopus.com/search/form.uri?display=basic, last access: 12
August 2018.
Wheeler, D. and Tiefelsdorf, M.: Multicollinearity and correlation among
local regression coefficients in geographically weighted regression, J.
Geogr. Syst., 7, 161–187, 2005.
Download
The requested paper has a corresponding corrigendum published. Please read the corrigendum first before downloading the article.
- Article
(1729 KB) - Full-text XML
- Corrigendum
-
Supplement
(603 KB) - BibTeX
- EndNote
Short summary
The paper examines a machine learning algorithm (Random Forests) in comparison with Multivariate Linear Regression, for a data-set of 3500 transactions of residential apartments in Nicosia District in Cyprus. The methodology suggested, indicated high accuracy of the Random Forests Method, that can be applied in automated valuation models and CAMA systems.
The paper examines a machine learning algorithm (Random Forests) in comparison with Multivariate...