Impact analysis of intra-firm factors on share prices of Chinese construction SMEs based on the XGBoost algorithm

Authors

  • Xinyi Liu
  • Yeqin Xiong

DOI:

https://doi.org/10.54097/hbem.v12i.8349

Keywords:

XGBoost, Share price, Small and medium-sized construction companies, Identification of factors.

Abstract

At this stage, small and medium-sized construction enterprises (construction SMEs) are in a difficult position due to fierce competition and severe homogenization. However, current studies on China's construction industry are mainly from the macro perspective of regions and policies. There is a lack of studies that can guide business managers to improve enterprises' performance. This paper constructs a 5-dimensional and 18-indicator system of factors influencing the share price of construction SMEs from an intra-firm micro perspective. Based on this, several XGBoost models were trained, and the highest accuracy was selected as the criterion for feature importance ranking using  and RMSE to output the importance ranking of internal factors influencing the share price of Chinese construction SMEs. The results show that the most critical intra-firm factors for the share price of Chinese construction SMEs are the growth capacity of capital, especially the growth ability of shareholders' equity, and the long-term and short-term solvency. This study provides an actionable starting point for Chinese construction SME managers. It uses the XGBoost algorithm, which has higher predictive accuracy than the linear regression commonly used in existing studies, to obtain more reliable factor importance rankings.

Downloads

Download data is not yet available.

References

Dong Xinxin. An empirical study on the factors influencing share price based on principal component analysis: empirical data from the SME board [J]. Communication of Finance and Accounting, 2011 (36): 64 - 67.

Zhu Xiping, Zhu Wei. Analysis of factors influencing the share price of listed companies breaking net[J]. Communication of Finance and Accounting, 2015 (33): 91 - 94.

Dai Qingwen. Analysis of factors influencing the share price return of listed companies in China [J]. Friends of Accounting, 2012 (10): 114 - 116.

He Qinhua,Jiao Anyong. Analysis of factors influencing share prices of power listed companies[J]. Finance and Accounting Monthly,2008(35):41 - 42.

Xu Shuitai, Ma Caiwei, Zhang Shenglong, Yuan Beifei. Measurement of eco-economic efficiency and influencing factors in China's construction industry [J]. Environmental Pollution & Control, 2022, 44 (06): 833 - 840.

Chen Ke, Gao Liangfei,Yu Hongliang. A study on the level of technological innovation in China's construction industry: a cross-time and cross-industry perspective [J]. Science and Technology Management Research, 2021, 41 (19): 56 - 61.

Ji Hongmei, Wang Xiaoping, Luo Biao. Comprehensive evaluation and analysis of regional construction industry science and technology competitiveness: an empirical study based on panel data of Chinese provinces and cities[J]. World Sci-Tech R & D, 2012, 34 (02): 349 - 354.

Xiang Yong, Zheng Mao, Dai Tianhui. Research on the dynamic factors and influencing mechanism of high-quality development of China's construction industry [J]. Construction Economy, 2019, 40 (12): 15 - 20.

WU Xiang-Hua,CHU Xin-Yi. Research on the efficiency and influencing factors of the construction industry's science and technology innovation of listed enterprises: based on data envelopment analysis and Tobin's model [J]. Science and Technology Management Research, 2022, 42 (13): 89 - 96.

Liu W, Ma Q, Liu X. Research on the dynamic evolution and its influencing factors of stock correlation network in the Chinese new energy market[J]. Finance Research Letters, 2022, 45: 102138.

Vuong P H, Dat T T, Mai T K, et al. Stock-price forecasting based on XGBoost and LSTM [J]. Computer Systems Science and Engineering, 2022, 40 (1): 237 - 246.

Zhou J, Qiu Y, Khandelwal M, et al. Developing a hybrid model of Jaya algorithm-based extreme gradient boosting machine to estimate blast-induced ground vibrations[J]. International Journal of Rock Mechanics and Mining Sciences, 2021, 145: 104856.

Parsa A B, Movahedi A, Taghipour H, et al. Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis [J]. Accident Analysis & Prevention, 2020, 136: 105405.

Dong W, Huang Y, Lehane B, et al. XGBoost algorithm-based prediction of concrete electrical resistivity for structural health monitoring [J]. Automation in Construction, 2020, 114: 103155.

Zheng H, Yuan J, Chen L. Short-term load forecasting using EMD-LSTM neural networks with a Xgboost algorithm for feature importance evaluation [J]. Energies, 2017, 10 (8): 1168.

Zhou J, Qiu Y, Zhu S, et al. Estimation of the TBM advance rate under hard rock conditions using XGBoost and Bayesian optimization[J]. Underground Space, 2021, 6 (5): 506 - 515.

Zhang W, Wu C, Zhong H, et al. Prediction of undrained shear strength using extreme gradient boosting and random forest based on Bayesian optimization [J]. Geoscience Frontiers, 2021, 12 (1): 469 - 477.

Downloads

Published

16-05-2023

How to Cite

Liu, X., & Xiong, Y. (2023). Impact analysis of intra-firm factors on share prices of Chinese construction SMEs based on the XGBoost algorithm. Highlights in Business, Economics and Management, 12, 191-200. https://doi.org/10.54097/hbem.v12i.8349