This study examines whether the number of hidden layers in a deep neural network significantly influences the model accuracy and efficiency for appraising housing prices. We provide empirical evidence that the deep neural network can achieve high accuracy with a small number of hidden layers on our dataset, which contains various hedonic variables. Furthermore, we show that adding layers does not necessarily guarantee the model's accuracy and effectiveness of the computing time.
|Journal||Journal of Physics: Conference Series|
|Publication status||Published - 2022|
|Event||2022 12th International Conference on Applied Physics and Mathematics, ICAPM 2022 - Singapore, Virtual, Singapore|
Duration: 2022 Feb 18 → 2022 Feb 20
Bibliographical noteFunding Information:
This work was supported by (i) the Technology Innovation Program ATC+ (20014125, Development of Intelligent Management Solution for Nuclear Decommissioning Site Characterization) funded by the Ministry of Trade, Industry & Energy (MOTIE, Republic of Korea) and (ii) the Future-leading Research Initiative (Grant Number: 2021-22-0306) funded by Yonsei University.
© Published under licence by IOP Publishing Ltd.
All Science Journal Classification (ASJC) codes
- Physics and Astronomy(all)