Read the full-text of this article for free

Title: Life cycle prediction and survival model construction of digital economy enterprises integrating survival analysis

Authors: Shulei Yin

Addresses: School of Economics and Management, Qilu Normal University, Jinan, 250000, Shandong, China

Abstract: The life cycle of digital economy enterprises is affected by many complex and nonlinear factors. Traditional methods can only handle some simple linear relationships. This paper proposes an improved gradient boosting regression tree (GBRT) model to further enhance the prediction ability. Firstly, the Kaplan-Meier survival curve is used for descriptive statistics and exploratory analysis. Then, the accelerated failure time (AFT) model is used to model the enterprise life cycle. Finally, the GBRT model is used to predict the mean-square error (MSE) value, and it is compared with the MSE value of the linear regression model. The MSE value of the survival model is 0.015, much smaller than the MSE value of the linear regression model of 0.232, reflecting the superiority of the survival model.

Keywords: AFT; accelerated failure time; Kaplan-Meier survival curve; GBRT; gradient boosting regression tree; survival model; linear regression method.

DOI: 10.1504/IJDS.2025.146190

International Journal of Data Science, 2025 Vol.10 No.6, pp.1 - 19

Received: 20 Jan 2025
Accepted: 11 Mar 2025
Published online: 09 May 2025 *