基于SMOTE-XGBoost的外贸企业财务危机预警模型

doi:10.3778/j.issn.1002-8331.2308-0007

摘要/Abstract

摘要： 外需萎缩和保护主义加剧大大提高了外贸企业的经营风险，外贸企业陷入财务危机的风险加大。针对外贸企业财务危机预警准确率不高的难题，优化预警指标体系，并提出基于SMOTE-XGBoost的组合模型。建立融合财务指标和宏观外贸指标的财务危机预警指标体系；构建合成少数类过采样技术（SMOTE）和极限梯度提升算法（XGBoost）的组合模型，对我国外贸企业数据进行分析。研究发现SMOTE-XGBoost组合模型能够有效提高预测准确率，ACC、recall、F1-score、AUC值均优于其他模型，且具有良好的稳定性。该模型能够帮助外贸企业提前发现可能的财务风险，避免陷入财务危机。

关键词: 财务危机预警, 外贸企业, 不平衡数据, XGBoost

Abstract: The operational risk of foreign trade enterprises is increasing under the context of external demand contraction and intensive protectionism, leading to a greater risk of financial crisis. In response to the challenge of low accuracy in predicting financial crises for foreign trade enterprises, the early warning indicator system is optimized, and a combined model based on SMOTE-XGBoost is proposed. Firstly, a financial crisis early warning indicator system is established by integrating financial indicators and macro foreign trade indicators. Secondly, a combined model integrating synthetic minority over-sampling technique (SMOTE) and extreme gradient boosting algorithm (XGBoost) is constructed to analyze data from foreign trade listed enterprises in China. The results show that this combined model can achieve more accurate prediction and better overall stability than other models, with superior ACC, recall, F1-score, and AUC. This model can be used to assist foreign trade enterprises in proactively identifying potential financial risks and avoiding falling into financial crises.

Key words: financial crisis early warning, foreign trade listed companies, imbalanced data, XGBoost

吴增源, 金灵敏, 韩香丽, 王泽林, 伍蓓. 基于SMOTE-XGBoost的外贸企业财务危机预警模型[J]. 计算机工程与应用, 2024, 60(11): 281-289.

WU Zengyuan, JIN Lingmin, HAN Xiangli, WANG Zelin, WU Bei. Research on Financial Crisis Early Warning Model for Foreign Trade Listed Companies Based on SMOTE-XGBoost Algorithm[J]. Computer Engineering and Applications, 2024, 60(11): 281-289.

参考文献

[1] 任婷婷, 鲁统宇, 崔俊. 基于改进AdaBoost算法的动态不平衡财务预警模型[J]. 数量经济技术经济研究, 2021, 38(11): 182-197.
REN T T, LU T Y, CUI J. Dynamic imbalanced financial distress prediction model based on improved AdaBoost algorithm[J]. Journal of Quantitative & Technological Economics, 2021, 38 (11): 182-197.
[2] 王宗胜, 尚姣姣. 我国制造业上市公司财务困境预警分析[J]. 统计与决策, 2015(3): 174-177.
WANG Z S, SHANG J J. Analysis financial crisis of China’s manufacturing listed companies[J]. Statistics and Decision, 2015(3): 174-177.
[3] 杨旸, 林辉. 基于离散Hopfield网络的上市公司财务困境预警研究[J]. 华东经济管理, 2016, 30(12): 156-162.
YANG Y, LIN H. An early warning research on financial distress of listed companies based on discrete Hopfield network [J]. East China Economic Management, 2016, 30(12): 156-162.
[4] 钱爱民, 张淑君, 程幸. 基于自由现金流量的财务预警指标体系的构建与检验——来自中国机械制造业A股上市公司的经验数据[J]. 中国软科学, 2008(9): 148-155.
QIAN A M, ZHANG S J, CHENG X. Construction and examination of financial early-warning system based on free cash flow: evidence from China’s a share listed companies in manufacturing industry[J]. China Soft Science, 2008(9): 148-155.
[5] 张亮, 张玲玲, 陈懿冰, 等. 基于信息融合的数据挖掘方法在公司财务预警中的应用[J]. 中国管理科学, 2015, 23(10): 170-176.
ZHANG L, ZHANG L L, CHEN Y B, et al. Based on information fusion technique with data mining in the application of financial early-warning[J]. Chinese Journal of Management Science, 2015, 23 (10): 170-176.
[6] 王成章, 白晓明. 基于图结构扩散界面理论的财务预警模型[J]. 数理统计与管理, 2020, 39(5): 893-901.
WANG C Z, BAI X M. Financial early-warning model based on diffuse interface theory on graphs[J]. Journal of Applied Statistics and Management, 2020, 39(5): 893-901.
[7] 郭斌, 戴小敏, 曾勇, 等. 我国企业危机预警模型研究—以财务与非财务因素构建[J]. 金融研究, 2006(2): 78-87.
GUO B, DAI X M, ZENG Y, et al. On the financial distress warning model[J]. Journal of Financial Research, 2006(2): 78-87.
[8] 杨子晖, 张平淼, 林师涵. 系统性风险与企业财务危机预警——基于前沿机器学习的新视角[J]. 金融研究, 2022(8): 152-170.
YANG Z H, ZHANG P M, LIN S H. Systemic risk and corporate financial distress forecasting from the new perspective of machine learning[J]. Journal of Financial Research, 2022 (8): 152-170.
[9] 余浪, 李乐, 李秉成, 等. 管理者能力、宏观经济周期与企业财务危机——基于调节、路径与预警的分析[J]. 软科学, 2022, 36(4): 118-124.
YU L, LI L, LI B C, et al. Managerial competence, macroeconomic cycle and corporate financial crisis: analysis based on regulation, path and early warning[J]. Soft Science, 2022, 36(4): 118-124.
[10] 唐千淇. 试论宏观经济政策对外贸企业商品流通管理的影响[J]. 商业经济研究, 2022(6): 160-163.
TANG Q Q. The impact of macroeconomic policies on the management of commodity circulation of foreign trade enterprises[J]. Journal of Commercial Economics, 2022(6): 160-163.
[11] 李惠青, 刘倩, 汪涛. 新贸易壁垒下外贸型中小企业财务风险预警机制[J]. 国际商务财会, 2020(3): 22-25.
LI H Q, LIU Q, WANG T. Financial risk early warning mechanism of small and medium-sized foreign trade enterprises under new trade barriers[J]. Finance and Accounting for International Commerce, 2020(3): 22-25.
[12] 卢永艳. 宏观经济因素对企业财务困境风险影响的实证分析[J]. 宏观经济研究, 2013(5): 53-58.
LU Y Y. Empirical analysis of the impact of macroeconomic factors on the risk of financial distress in enterprises[J]. Macroeconomics, 2013 (5): 53-58.
[13] ALTMAN E I. Financial ratios, discriminate analysis and the prediction of corporate bankruptcy[J]. The Journal of Finance, 1968, 23(4): 589-609.
[14] ALTMAN E I, HALDEMAN R G, NARAYANAN P. ZETA analysis: a new model to identify bankruptcy risk of corporations[J]. Journal of Banking and Finance, 1977(6): 29-54.
[15] 周首华, 杨济华, 王平. 论财务危机的预警分析——F分数模式[J]. 会计研究, 1996(8): 8-11.
ZHOU S H, YANG J H, WANG P. Analysis of financial crisis warning: failure score model[J]. Accounting Research, 1996(8): 8-11.
[16] BEAVER W H. Financial ratios as predictors of failure: empirical research in accounting[J]. Journal of Accounting Research, 1966, 32(5): 69-109.
[17] 杨淑娥, 徐伟刚. 上市公司财务预警模型——Y分数模型的实证研究[J]. 中国软科学, 2003(1): 56-60.
YANG S E, XU W G. Financial affairs in early warning model for listed companies——an empirical study on Y market’s model[J]. China Soft Science, 2003(1): 56-60.
[18] KIM S Y, UPNEJA A. Predicting restaurant financial distress using decision tree and AdaBoosted decision tree models[J]. Economic Modelling, 2014, 36: 354-362.
[19] 杨贵军, 周亚梦, 孙玲莉. 基于Benford-Logistic模型的企业财务风险预警方法[J]. 数量经济技术经济研究, 2019, 36(10): 149-165.
YANG G J, ZHOU Y M, SUN L L. Enterprise financial early warning method based on benford-logistic model[J]. Journal of Quantitative & Technological Economics, 2019, 36(10): 149-165.
[20] 倪志伟, 薛永坚, 倪丽萍, 等. 基于流形学习的多核SVM财务预警方法研究[J]. 系统工程理论与实践, 2014, 34(10): 2666-2674.
NI Z W, XUE Y J, NI L P, et al. Research of multiple kernel SVM based on manifold learning in financial distress prediction[J]. Systems Engineering-Theory & Practice, 2014, 34(10): 2666-2674.
[21] 孙玲莉, 杨贵军, 王禹童. 基于Benford律的随机森林模型及其在财务风险预警的应用[J]. 数量经济技术经济研究, 2021, 38(9): 159-177.
SUN L L, YANG G J, WANG Y T. Random forest model based on Benford’s law and its application in financial early warning[J]. Journal of Quantitative & Technological Economics, 2021, 38(9): 159-177.
[22] 梁龙跃, 刘波. 基于文本挖掘的上市公司财务风险预警研究[J]. 计算机工程与应用, 2022, 58(4): 255-266.
LIANG L Y, LIU B. Research on financial risk early warning of listed companies based on text mining[J]. Computer Engineering and Applications, 2022, 58 (4): 255-266.
[23] OHLSON J A. Financial ratios and the probabilistic prediction of bankruptcy[J]. Jounal of Accounting Research, 1980, 18(1): 109-131.
[24] RIBEIRO B, SILVA C, VIEIRA A, et al. Financial distress model prediction using SVM+[C]//Proceedings of the International Joint Conference on Neural Networks, 2010: 1-7.
[25] 张培荣. 基于XGBoost模型的企业财务危机预警研究[J]. 财会通讯, 2019(35): 109-112.
ZHANG P R. Research on early warning of enterprise financial crisis based on XGBoost model[J]. Communication of Finance and Accounting, 2019(35): 109-112.
[26] 郑玉华, 崔晓东. 公司财务预警LOGIT模型最优分界点实证研究[J]. 商业研究, 2014(6): 76-82.
ZHENG Y H, CUI X D. An empirical study on the optimal critical value of LOGIT model for company financial early warning[J]. Commercial Research, 2014(6): 76-82.
[27] 闫达文, 李存, 迟国泰. 基于混频数据的中国上市公司财务困境动态预测研究[J]. 中国管理科学, 2024, 32(1): 1-12.
YAN D W, LI C, CHI G T. Dynamic financial distress prediction for Chinese listed companies based on the mixed frequency data[J]. Chinese Journal of Management Science, 2024, 32(1): 1-12.
[28] 黎旭, 陈家兑, 吴永明, 等. 基于改进SMOTE的制造过程不平衡数据分类策略[J]. 计算机工程与应用, 2022, 58(16): 284-291.
LI X, CHEN J D, WU Y M, et al. Classification strategy of imbalanced data in manufacturing process based on improved SMOTE[J]. Computer Engineering and Applications, 2022, 58(16): 284-291.
[29] SUE K L, TSAI C F, CHIU A. The data sampling effect on financial distress prediction by single and ensemble learning techniques[J]. Communications in Statistics-Theory and Methods, 2021: 1-12.
[30] 罗康洋, 王国强. 基于改进的MRMR算法和代价敏感分类的财务预警研究[J]. 统计与信息论坛, 2020, 35(3): 77-85.
LUO K Y, WANG G Q. The research on financial early warning based on the improved MRMR algorithms and cost sensitive classification[J]. Journal of Statistics and Information, 2020, 35(3): 77-85.
[31] 王乐, 韩萌, 李小娟, 等. 不平衡数据集分类方法综述[J]. 计算机工程与应用, 2021, 57(22): 42-52.
WANG L, HAN M, LI X J, et al. Review of classification methods for unbalanced data sets[J]. Computer Engineering and Applications, 2021, 57(22): 42-52.
[32] 高燕, 杜玥, 曾森. 基于BP神经网络的制造企业财务风险预警研究[J]. 会计之友, 2023(1): 62-70.
GAO Y, DU Y, ZENG S. Research on financial risk early warning of manufacturing enterprises based on BP neural network[J]. Friends of Accounting, 2023(1): 62-70.
[33] 钟灵芝. 基于神经网络模型的我国外贸上市企业财务危机预警的研究[D]. 天津: 天津大学, 2012.
ZHONG L Z. Research on finance warning of China’s foreign trade enterprises based on neural network model[D]. Tianjin: Tianjin University, 2012.