Abstract
In this paper we aim to explore the Real Estate Market in Germany, and particularly we have taken a dataset of Berlin and applied various advanced neural network and optimisation techniques. It’s always difficult for people to estimate what price is best for a property and there are various categorical and numerical features involved in it. And the main challenge is to choose the model, loss function and customize the neural network to best fit for the marketplace data. We have developed a project that can be used to predict the property price in Berlin. Firstly, we have worked on procuring the online current market price of the property by web scraping. Then we did intensive exploratory Data Analysis on it, prepared the best data for experiments. Then we build four different models and worked on the best loss functions which can suite our model and tabulated the mean squared and mean absolute errors for the same. We have tested our model with the current on the market properties, and the sample results are plotted. This methodology can be applied efficiently, and the results can be used by the people who are interested in investing in real estate in Berlin, Germany.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kauskale, L.: Integrated approach of real estate market analysis in sustainable development context for decision making. Procedia Eng. 172, 505–512 (2017)
Jha, S.B.: Machine learning approaches to real estate market prediction problem: a case study arXiv:2008.09922 (2020)
Tabales, J.M.N.: Artificial neural networks for predicting real estate prices. Revista De Methodos Cuantitativos para la economia y la empresa 15, 29–44 (2013)
Hamzaoi, Y.E., Hernandez, J.A.: Application of artificial neural networks to predict the selling price in the real estate valuation. In: 10th Mexican International Conference on Artificial Intelligence, pp. 175–181 (2011)
Kauko, T., Hooimaijer, P., Hakfoort, J.: Capturing housing market segmentation: an alternative approach based on neural network modelling. Hous. Stud. 17(6), 875–894 (2002)
Fukumizu, K.: Influence function and robust variant of kernel canonical correlation analysis. Neurocomputig, 304–307 (2017)
Rahimi, I., Bahmanesh, R.: Using combination of optimized recurrent neural network with design of experiments and regression for control chart forecasting. Int. J. Sci. Eng. Invest. 1(1), 24–28 (2012)
Cook, D.F., Ragsdale, C.T., Major, R.L.: Combining a neural network with a genetic algorithm for process parameter optimization. Eng. Appl. Artif. Intell. 13, 391–396 (2000)
Kingma, D.P.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2015)
Lee, E.W.M.: A hybrid neural network model for noisy data regression. IEEE Trans. Cybern. 34, 951–960 (2004)
Williamson, J.R.: Gaussian artmap: a neural network for fast incremental learning of noisy multidimensional maps. Neural Netw. 9(5), 881–897 (1996)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Iliev, A.I., Anand, A. (2023). Huber Loss and Neural Networks Application in Property Price Prediction. In: Arai, K. (eds) Advances in Information and Communication. FICC 2023. Lecture Notes in Networks and Systems, vol 652. Springer, Cham. https://doi.org/10.1007/978-3-031-28073-3_17
Download citation
DOI: https://doi.org/10.1007/978-3-031-28073-3_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-28072-6
Online ISBN: 978-3-031-28073-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)