Review of Neural Network Model in Prediction of Real Estate Prices at Global Level
Session
Management Business and Economics
Description
The purpose of this paper is to understand the importance of real estate evaluation, having into account the fact that it is quite necessary in the evaluation of the real estate valuation, and because it contributes to the regional economy of each country. This is a topic of great importance which must be studied carefully since it contains many individual subjective criteria, which often results in variations, and which make traditional evaluation methods inadequate.This paper aims to understand the complexity of real estate valuation, presenting and analyzing carefully the advantages of the neural network, which is known as one of the newest model of real estate valuation. In this paper, a continuous literature review was used, which helped us to compare traditional methods and neural network methods, as well as to prove that the neural network model is better than the previous traditional model. This work opens up a new and better understanding to the principle of real estate evaluation. Another purpose is to estimate real estate prices based on neural neural network models. Moreover, some features affecting the real estate value have been determined. Therefore, the valuation process also brings a level of uncertainty to the valuers and real estate developers. With the advancement of artificial intelligence, respectively neural network, it has become necessary to use these techniques to predict the real estate prices more precisely . These neural networks are trained to make a proper assessment because the results show an improvement of real estate evaluation, based on a listing price of housing market. The results can be promising and consistent with contemporary findings; however, the worst-case performance of patterns can make them unsuitable for many purposes. As a working methodology, this research used a continous literature review at the global level, using the analytical, descriptive and comparative approach.
Keywords:
neural networks, machine learning, real estate, property price prediction, valuation
Proceedings Editor
Edmond Hajrizi
ISBN
978-9951-982-41-2
Location
UBT Lipjan, Kosovo
Start Date
25-10-2025 9:00 AM
End Date
26-10-2025 6:00 PM
DOI
10.33107/ubt-ic.2025.393
Recommended Citation
Hoxha, Jehona; Spahi, Samina; Hoxha, Visar; and Pallaska, Fuat, "Review of Neural Network Model in Prediction of Real Estate Prices at Global Level" (2025). UBT International Conference. 8.
https://knowledgecenter.ubt-uni.net/conference/2025UBTIC/MBE/8
Review of Neural Network Model in Prediction of Real Estate Prices at Global Level
UBT Lipjan, Kosovo
The purpose of this paper is to understand the importance of real estate evaluation, having into account the fact that it is quite necessary in the evaluation of the real estate valuation, and because it contributes to the regional economy of each country. This is a topic of great importance which must be studied carefully since it contains many individual subjective criteria, which often results in variations, and which make traditional evaluation methods inadequate.This paper aims to understand the complexity of real estate valuation, presenting and analyzing carefully the advantages of the neural network, which is known as one of the newest model of real estate valuation. In this paper, a continuous literature review was used, which helped us to compare traditional methods and neural network methods, as well as to prove that the neural network model is better than the previous traditional model. This work opens up a new and better understanding to the principle of real estate evaluation. Another purpose is to estimate real estate prices based on neural neural network models. Moreover, some features affecting the real estate value have been determined. Therefore, the valuation process also brings a level of uncertainty to the valuers and real estate developers. With the advancement of artificial intelligence, respectively neural network, it has become necessary to use these techniques to predict the real estate prices more precisely . These neural networks are trained to make a proper assessment because the results show an improvement of real estate evaluation, based on a listing price of housing market. The results can be promising and consistent with contemporary findings; however, the worst-case performance of patterns can make them unsuitable for many purposes. As a working methodology, this research used a continous literature review at the global level, using the analytical, descriptive and comparative approach.