역전파 알고리즘을 응용한 인구통계학 기반 서울 주택가격 변화 예측 연구

국문 초록 (Abstract)

본 논문에서는 대한민국의 연도별 출생아 수 데이터와 머신러닝 알고리즘을 활용하여 서울 주택가격 변화를 예측하였다. 더 정확한 예측을 위하여 머신러닝 알고리즘 중에서 역전파 (Back propagation) 알고리즘을 사용하였으며, 가상 GDP 성장률과 예상 수명 연장률이 고려되었다. 예측 결과, 서울 주택가격은 2025년까지 꾸준히 증가하며, 2025년부터 2033년까지는 큰 상승없이 유지가 되다가 2033년 이후부터는 다시 하락할 것으로 예측되었다. 결국, 2040년경에는 2020년 현재의 주택가격과 비슷한 수준으로 돌아올 것이 전망되었는데, 이는 저출산 영향으로 앞으로 만 25세 이상의 인구수가 점차 감소하여 주택의 수요 또한 감소할 것이기 때문으로 해석되었다.

다국어 초록 (Multilingual Abstract)

In this paper, housing price in Seoul of Republic of Korea was predicted by utilizing annual birthrate data in Republic of Korea and machine learning algorithm. In order to conduct more accurate prediction, a back propagation algorithm was used among machine learning algorithms, and virtual GDP growth rate and expected life extension rate were considered. As a result, house price in Seoul is expected to increase steadily until 2025, and remain almost unchanged from 2025 to 2033, and then fall again after 2033. Eventually, it was expected that the house price of Seoul will return to a level similar to current house price of Seoul. This result was due to decrease in the number of people over the age of 25 from low fertility phenomenon, which results in decrease in demand for house.

목차 (Table of Contents)

• 요약
• Abstract
• Ⅰ. 서론
• Ⅱ. 본론
• Ⅲ. 실험 및 분석
• Ⅳ. 결론
• REFERENCES

참고문헌 (Reference)

1 한정희, "인구구조와 주택가격 : 동아시아와 유럽 비교 연구" 한국부동산학회 (64) : 184-198, 2016

2 박공주, "은퇴 후 귀농인의 농촌 이주준비 및 농촌 적응과정 실태에 관한 연구" 대한가정학회 45 (45): 9-21, 2007

3 송영서, "역전파 알고리즘을 이용한 대한민국 국민연금 고갈 시기 예측 연구" 대한전자공학회 57 (57): 37-44, 2020

4 Y. S. Song, "Tunneling oxide engineering for improving retention in nonvolatile chargetrapping memory with TAHOAOS (TaN/Al2O3/HfO2/SiO2/Al2O3/SiO2/Si) structure" 59 (59): 061006-1-061006-7, 2020

5 Q. Ye, "Text Detection and Recognition in Imagery : A Survey" 37 (37): 1480-1500, 2015

6 Y. Choi, "Simulation of the effect of parasitic channel height on characteristics of stacked gate-all-around nanosheet FET" 164 : 107686-1-107686-7, 2020

7 K. Kwon, "Post-crisis Slowdown in the Korean Economy and Long-term Outlook"

8 T. Kim, "Overflow handling integrate-and-fire silicon-on-insulator neuron circuit incorporating a Schmitt trigger implemented by back-gate effect" 19 (19): 6183-6186, 2019

9 Z. Zhao, "Object Detection With Deep Learning : A Review" 30 (30): 3212-3232, 2019

10 T. Sadayuki, "Measuring the spatial effect of multiple sites : An application to housing rent and public transportation in Tokyo, Japan" 70 : 155-173, 2018

11 J. H. Han, "Machine learning-based self-powered acoustic sensor for speaker recognition" 53 : 658-665, 2018

12 S. Lee, "Lowest-Low Fertility and Policy Responses in South Korea" 107-123, 2015

13 S. -S. Lee, "Low Fertility and Policy Responses in Korea" 7 (7): 57-70, 2009

14 Z. Boger, "Knowledge extraction from artificial neural network models" 1997

15 H. Phang, "Issues and challenges facing population ageing in Korea : productivity, economic growth, and old-age income security" 27 (27): 51-62, 2011

16 J. Yu, "Investigation of Ambipolar Current Suppression Using Dual Work Function Metal Gate in L-Shaped Tunnel Field Effect Transistor" 71-73, 2019

17 T. Kim, "Input-modulating adaptive neuron circuit employing asymmetric floatinggate MOSFET with two independent control gates" 163 : 107667-1-107667-5, 2020

18 D. M. Brasington, "House Price Impacts of Racial, Income, Education, and Age Neighborhood Segregation" 55 (55): 442-467, 2014

19 B. Case, "Frequency of Transaction and House Price Modeling" 14 : 173-187, 1997

20 J. Chen, "Forecasting smog-related health hazard based on social media and physical sensor" 64 : 281-291, 2017

21 Y. S. Song, "Electrical and Thermal Performances of Omega-Shaped-Gate Nanowire Field Effect Transistors for Low Power Operation" 20 (20): 4092-4096, 2020

22 H. Kim, "Determinants of house prices in Seoul : A quantile regression approach" 21 (21): 91-113, 2015

23 W. Wu, "Convergence of gradient method with momentum for back-propagation neural networks" 26 (26): 613-623, 2008

24 L. Wang, "Back propagation neural network with adaptive differential evolution algorithm for time series forecasting" 42 (42): 855-863, 2015

25 S. Karsoliya, "Approximating Number of Hidden layer neurons in Multiple Hidden Layer BPNN Architecture" 3 (3): 714-717, 2012

26 Y. Kim, "An Area Efficient Adaptive Neuron Circuit Exploiting Tunnel Field-Effect Transistor" 71-73, 2019