Financial prediction of real estate based on random forest

Zixiao He; Lang Pan

doi:10.1117/12.2653425

20 October 2022 Financial prediction of real estate based on random forest

Zixiao He, Lang Pan

Proceedings Volume 12350, 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022); 123500U (2022) https://doi.org/10.1117/12.2653425
Event: 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 2022, Qingdao, China

Abstract

With the development of economy and society, the competition among companies is becoming more and more fierce. In order to effectively protect the interests of enterprises and investors, it is particularly important to predict the financial distress of companies. There are many ways to complete a financial distress prediction, e.g. logistic regression, K-Nearest Neighbor, random forest etc. But it is a little hard to know which algorithm is the most suitable in this task. This paper will consider this issue by using eight algorithms consisting of four single algorithms and four ensemble learning algorithms. During the research, this paper has collected more than 3,800 pieces of data from 95 Chinese real estate listed companies. Four indicators namely Accuracy, Precision, Recall, F1-score was employed to evaluate the performance of different algorithms. The results show that the accuracy of the Random Forest algorithm is as high as 90%, which is the highest of these eight algorithms.

Citation Download Citation

Zixiao He and Lang Pan "Financial prediction of real estate based on random forest", Proc. SPIE 12350, 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500U (20 October 2022); https://doi.org/10.1117/12.2653425

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available