Neural network hyperparameter optimization for prediction of real estate prices in Helsinki
Accurate price evaluation of real estate is beneficial for many parties involved in real estate business such as real estate companies, property owners, investors, banks, and financial institutes. Artificial Neural Networks (ANNs) have shown promising results in real estate price evaluation. However...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2021-04-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-444.pdf |
| _version_ | 1818954024416706560 |
|---|---|
| author | Jussi Kalliola Jurgita Kapočiūtė-Dzikienė Robertas Damaševičius |
| author_facet | Jussi Kalliola Jurgita Kapočiūtė-Dzikienė Robertas Damaševičius |
| author_sort | Jussi Kalliola |
| collection | DOAJ |
| description | Accurate price evaluation of real estate is beneficial for many parties involved in real estate business such as real estate companies, property owners, investors, banks, and financial institutes. Artificial Neural Networks (ANNs) have shown promising results in real estate price evaluation. However, the performance of ANNs greatly depends upon the settings of their hyperparameters. In this paper, we apply and optimize an ANN model for real estate price prediction in Helsinki, Finland. Optimization of the model is performed by fine-tuning hyper-parameters (such as activation functions, optimization algorithms, etc.) of the ANN architecture for higher accuracy using the Bayesian optimization algorithm. The results are evaluated using a variety of metrics (RMSE, MAE, R2) as well as illustrated graphically. The empirical analysis of the results shows that model optimization improved the performance on all metrics (reaching the relative mean error of 8.3%). |
| first_indexed | 2024-12-20T10:15:35Z |
| format | Article |
| id | doaj.art-f5edb6be428444d88e5b9ca9ae2c8c3c |
| institution | Directory Open Access Journal |
| issn | 2376-5992 |
| language | English |
| last_indexed | 2024-12-20T10:15:35Z |
| publishDate | 2021-04-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj.art-f5edb6be428444d88e5b9ca9ae2c8c3c2022-12-21T19:44:05ZengPeerJ Inc.PeerJ Computer Science2376-59922021-04-017e44410.7717/peerj-cs.444Neural network hyperparameter optimization for prediction of real estate prices in HelsinkiJussi Kalliola0Jurgita Kapočiūtė-Dzikienė1Robertas Damaševičius2Department of Applied Informatics, Vytautas Magnus University, Kaunas, LithuaniaDepartment of Applied Informatics, Vytautas Magnus University, Kaunas, LithuaniaDepartment of Applied Informatics, Vytautas Magnus University, Kaunas, LithuaniaAccurate price evaluation of real estate is beneficial for many parties involved in real estate business such as real estate companies, property owners, investors, banks, and financial institutes. Artificial Neural Networks (ANNs) have shown promising results in real estate price evaluation. However, the performance of ANNs greatly depends upon the settings of their hyperparameters. In this paper, we apply and optimize an ANN model for real estate price prediction in Helsinki, Finland. Optimization of the model is performed by fine-tuning hyper-parameters (such as activation functions, optimization algorithms, etc.) of the ANN architecture for higher accuracy using the Bayesian optimization algorithm. The results are evaluated using a variety of metrics (RMSE, MAE, R2) as well as illustrated graphically. The empirical analysis of the results shows that model optimization improved the performance on all metrics (reaching the relative mean error of 8.3%).https://peerj.com/articles/cs-444.pdfArtificial neural networkHyperparameter optimisationPrediction modelReal estate prices |
| spellingShingle | Jussi Kalliola Jurgita Kapočiūtė-Dzikienė Robertas Damaševičius Neural network hyperparameter optimization for prediction of real estate prices in Helsinki PeerJ Computer Science Artificial neural network Hyperparameter optimisation Prediction model Real estate prices |
| title | Neural network hyperparameter optimization for prediction of real estate prices in Helsinki |
| title_full | Neural network hyperparameter optimization for prediction of real estate prices in Helsinki |
| title_fullStr | Neural network hyperparameter optimization for prediction of real estate prices in Helsinki |
| title_full_unstemmed | Neural network hyperparameter optimization for prediction of real estate prices in Helsinki |
| title_short | Neural network hyperparameter optimization for prediction of real estate prices in Helsinki |
| title_sort | neural network hyperparameter optimization for prediction of real estate prices in helsinki |
| topic | Artificial neural network Hyperparameter optimisation Prediction model Real estate prices |
| url | https://peerj.com/articles/cs-444.pdf |
| work_keys_str_mv | AT jussikalliola neuralnetworkhyperparameteroptimizationforpredictionofrealestatepricesinhelsinki AT jurgitakapociutedzikiene neuralnetworkhyperparameteroptimizationforpredictionofrealestatepricesinhelsinki AT robertasdamasevicius neuralnetworkhyperparameteroptimizationforpredictionofrealestatepricesinhelsinki |