• • 上一篇    下一篇

基于GA-BP神经网络的信息技术业上市公司的成长性预测

李山海1, 吴艳雄1, 王蓓2, 徐岩2, 刘玉龙3   

  1. 1. 中华全国工商业联合会信息中心 北京 100082;
    2. 北京科 技大学信息与计算科学系 北京 100083;
    3. 中国电子科技集团公司第十五研究所 北京 100083
  • 收稿日期:2021-02-08 修回日期:2021-05-10 出版日期:2022-04-25 发布日期:2022-06-18
  • 通讯作者: 刘玉龙,Email:lyl_nci@126.com.
  • 基金资助:
    科技部科技创新2030-“新一代人工智能”重大项目(2020AAA0105103),国家自然科学基金(12071024)资助课题.

李山海, 吴艳雄, 王蓓, 徐岩, 刘玉龙. 基于GA-BP神经网络的信息技术业上市公司的成长性预测[J]. 系统科学与数学, 2022, 42(4): 854-866.

LI Shanhai, WU Yanxiong, WANG Bei, XU Yan, LIU Yulong. Prediction of Enterprise Growth in Information Technology Listed Campanies Based on GA-BP Network[J]. Journal of Systems Science and Mathematical Sciences, 2022, 42(4): 854-866.

Prediction of Enterprise Growth in Information Technology Listed Campanies Based on GA-BP Network

LI Shanhai1, WU Yanxiong1, WANG Bei2, XU Yan2, LIU Yulong3   

  1. 1. All-China Federation of Industry and Commerce, Beijing 100082;
    2. University of Science and Technology Beijing, Beijing 100083;
    3. No. 15 Research Institute, China Electronics Technology Group Corporation, Beijing 100083
  • Received:2021-02-08 Revised:2021-05-10 Online:2022-04-25 Published:2022-06-18
In this work, the index system of the information technology industry in private enterprises is established, which includes six aspects: Profitability, operation ability, solvency, expansion ability, innovation ability, and company scale. Then, the GA-BP algorithm combining genetic algorithm and neural network is introduced to analyze and predict the growth of the enterprise. After preprocessing the data gained from Wind dataset, the model is trained and the coefficient of determination R2 on the test set is 0.9997, showing its outperformance than other five machine learning algorithms. Through the correlation coefficient analysis between the growth rate of market value and the growth value predicted, the validity of the established model is tested. Finally, the index system is simplified by ranking the importance of the features via Random Forest Algorithm. The coefficient of determination R2 on the test set is 0.8929 when eight features are selected, proving the rationality of the initial index selection again.

MR(2010)主题分类: 

()
[1] 李四海,罗月乔.审计质量、债务融资与企业投资行为——来自我国上市公司的经验证据.投资研究, 2012, 31(10):14-26.(Li S H, Luo Y Q. Auditing quality, debt financing and investment. Review of Investment Studies, 2012, 31(10):14-26.)
[2] 朱彦杰.中小企业成长性评价指标及实证研究.科技管理研究, 2013, 33(13):75-78.(Zhu Y J. Growth evaluation index of small and medium-sized enterprise and empirical study. Science and Technology Management Research, 2013, 33(13):75-78.)
[3] 李飞,朱永明.云南省上市公司成长性综合评价与分析.商丘师范学院学报, 2019, 35(10):76-82.(Li F, Zhu Y M. Comprehensive evaluation and analysis of growth of listed companies in Yunnan Province. Journal of Shangqiu Normal University, 2019, 35(10):76-82.)
[4] 李娇.基于熵权法-GRA的房地产上市公司成长性评价研究.价值工程, 2018, 37(3):59-62.(Li J. An evaluation research on the growth of the listed real estate companies based on entropy weight and grey relational analysis. Value Engineering, 2018, 37(3):59-62.)
[5] 陈晓红,周颖,佘坚.考虑在险价值的中小企业成长性评价研究——基于沪深中小上市公司的实证.南开管理评论, 2008,(4):4-11.(Chen X H, Zhou Y, She J. A study of SMEs growth evaluation considering value at risk:Empirical research of listed SMEs. Nankai Business Review, 2008,(4):4-11.)
[6] 王青燕,何有世.影响中国上市公司成长性的主要因素分析.统计与决策, 2005,(1):61-63.(Wang Q Y, He Y S. Analysis of the main factors affecting the growth of China's listed companies. Statistics&Decision, 2005,(1):61-63.)
[7] 张秀生,刘伟.创业板上市企业成长性影响因素研究.统计与决策, 2013,(15):181-183.(Zhang X S, Liu W. Research on factors affecting growth of listed enterprises on GEM. Statistics&Decision, 2013,(15):181-183.)
[8] 樊明雪,谢赤,黄维亮.基于门槛模型的风险投资进入创新型企业时机与方式研究.管理学报, 2019, 16(7):1035-1043.(Fan M X, Xie C, Huang W L. Analysis on opportunity and mode of venture capital entering innovative enterprises based on threshold model. Chinese Journal of Management, 2019, 16(7):1035-1043.)
[9] 程燕,马晨.基于层次分析赋权法的上市公司成长性评价——以旅游业为例.财会通讯, 2015,(2):58-60.(Cheng Y, Ma C. Growth evaluation of listed companies based on AHP weighting method:A case study of tourism industry. Communication of Finance and Accounting, 2015,(2):58-60.)
[10] 郭晓铃.我国节能环保类上市公司成长性评价.山西财经大学学报, 2011, 33(S3):166-168.(Guo X L. Growth evaluation on domestic listed companies in energy saving and environmental protection industry. Journal of Shanxi University of Finance and Economics, 2011, 33(S3):166-168.)
[11] 崔璐,钟书华.基于层次分析-灰色关联度综合评价法的高技术中小企业成长性测度.科技进步与对策, 2011, 28(24):148-152.(Cui L, Zhong S H. Measurement of growth ability of small and medium-sized high-tech enterprises with AHP and GRA. Science&Technology Progress and Policy, 2011, 28(24):148-152.)
[12] 国家经济贸易委员会中小企业司,国家统计局工业交通司,中国企业评价协会联合课题组.成长型中小企业评价的方法体系.北京统计, 2001,(5):9-10.(Department of Small and Medium Enterprises, State Economic and Trade Commission, Department of Industrial Transportation, National Bureau of Statistics, Joint Research Group of China Enterprise Evaluation Association. The evaluation method system of growing small and medium-sized enterprises. Beijing Statistics, 2001,(5):9-10.)
[13] 赵志伟,乔晗.基于两阶段学习的专家群体评价信息集成方法研究.统计与信息论坛, 2018,33(6):19-25.(Zhao Z W, Qiao H. An expert group evaluation method based on two-step learning. Statistics&Information Forum, 2018, 33(6):19-25.)
[14] 王璐,王沁,何平.基于复杂系统综合评价的二重主成分分析法.统计与决策, 2006,(22):145-146.(Wang L, Wang Q, He P. Dual principal component analysis based on complex system comprehensive evaluation. Statistics&Decision, 2006,(22):145-146.)
[15] 刘艳.基于AHP加权主成分分析的企业绩效评价研究.硕士论文.哈尔滨工业大学,哈尔滨, 2006.(Liu Y. A study on the performance of enterprise based on the method of PCA with weighted by AHP. Master's thesis. Harbin Institute of Technology, Harbin, 2006.)
[16] 李益娟.基于Logistic回归模型的上市公司成长性判定.财会月刊, 2009,(6):64-66.(Li Y J. The growth judgement of listed companies based on logistic regression model. Finance and Accounting Monthly, 2009,(6):64-66.)
[17] 李广春.基于主成分和BP神经网络的创业板企业财务绩效评价.商业时代, 2013,(15):75-77.(Li G C. The financial performance evaluation of GEM enterprises based on principal component and BP neural network. Journal of Commercial Economics, 2013,(15):75-77.)
[18] 乔晗,蔡高远,赵志伟.基于大数据技术的中小企业成长性评价方法研究.统计与信息论坛, 2019, 34(7):123-128.(Qiao H, Cai G Y, Zhao Z W. Research on applied big data technique in the method of evaluation of small and medium-sized enterprise growth. Statistics&Information Forum, 2019, 34(7):123-128.)
[19] 王贝贝.基于CPM-BP神经网络的科技型中小企业成长性价值评估.硕士论文.石家庄铁道大学,石家庄, 2018.(Wang B B. Evaluation of the growth of technological SMEs based on CPM-BP neural network. Master's thesis. Shijiazhuang Tiedao University, Shijiazhuang, 2018.)
[20] 杨奕.信息技术业上市公司最优资本结构实证研究.财会通讯, 2017,(11):35——39.(Yang Y. Empirical study on optimal capital structure of listed companies in information technology industry. Communication of Finance and Accounting, 2017,(11):35-39.)
[21] 李晓婷,孙静稳. BP神经网络在我国创业板公司成长性预测中的应用.商业会计, 2012,(21):113-115.(Li X T, Sun J W. Application of BP neural network in Growth Prediction of GEM Companies in China. Commercial Accounting, 2012,(21):113-115.)
[22] 屈小华.信息技术业上市公司成长性影响因素的财务指标分析.现代经济信息, 2010,(9):95.(Qu X H. Financial index analysis of the factors influencing the growth of listed companies in information technology industry. Modern Economic Information, 2010,(9):95.)
[23] 姚旭,王晓丹,张玉玺,等.特征选择方法综述.控制与决策, 2012, 27(2):161-166, 192.(Yao X, Wang X D, Zhang Y X, et al. Summary of feature selection algorithms. Control and Decision, 2012, 27(2):161-166, 192.)
[24] 姚登举,杨静,詹晓娟.基于随机森林的特征选择算法.吉林大学学报(工学版), 2014, 44(1):137-141.(Yao D J, Yang J, Zhan X J. Feature selection algorithm based on random forest. Journal of Jilin University (Engineering and Technology Edition), 2014, 44(1):137-141.)
[25] 王钰、赵晓艳、杨杏丽,等.基于K折交叉验证Beta分布的AUC度量的置信区间.系统科学与数学, 2020, 40(9):51-64.(Wang Y, Zhao X Y, Yang X L, et al. Confidence interval of AUC measure based on K-fold cross-validated Beta distribution. Journal of Systems Science and Mathematical Sciences, 2020, 40(9):51-64.)
[1] 郭海湘, 赵佳佳, 黎金玲. 滑坡灾害临时避难所区位布局规划方法[J]. 系统科学与数学, 2021, 41(2): 401-419.
[2] 姜伟, 徐贝灵, 王天文. B2C配送中心分散存储优化问题研究[J]. 系统科学与数学, 2021, 41(11): 3170-3180.
[3] 陆文星,戴一茹,李楚,李克卿. 基于改进PSO-BP神经网络的旅游客流量预测方法[J]. 系统科学与数学, 2020, 40(8): 1407-1419.
[4] 张培文,吴江,汪瑜,孙宏. 机队运力配置和USApHMP问题的联合决策模型与算法[J]. 系统科学与数学, 2020, 40(8): 1432-1446.
[5] 张大斌,蔡超敏,凌立文,陈善盈. 基于CEEMD与GA-SVR的猪肉价格集成预测模型[J]. 系统科学与数学, 2020, 40(6): 1061-1073.
[6] 张玉州,徐廷政,郑军帅. 基于混合遗传算法的紧急程度不确定应急物流问题求解[J]. 系统科学与数学, 2020, 40(4): 714-728.
[7] 林志炳,王贵用. 基于三层编码遗传算法求解同种产品存在多个工件的FJSP[J]. 系统科学与数学, 2020, 40(12): 2401-2415.
[8] 王雷,王欣,刘德海,胡卉. 智能网联下无人驾驶汽车配送路径优化方法[J]. 系统科学与数学, 2020, 40(11): 1984-1998.
[9] 常思琳,岳德权,张玉英. 两类顾客的生产服务库存模型的稳态分析及最优生产策略[J]. 系统科学与数学, 2020, 40(11): 2093-2107.
[10] 山珊,刘颖琦,叶顺心. 面向付费类交通PPP项目的价格设计与补贴动态调整方案研究[J]. 系统科学与数学, 2019, 39(6): 944-953.
[11] 贾凯,倪志伟,李敬明,陆玉佳,朱旭辉. 基于改进二进制人工蜂群的BP神经网络并行集成学习算法及其应用研究[J]. 系统科学与数学, 2019, 39(3): 477-494.
[12] 相鑫,刘秀丽. 四层参数自调整BP神经网络模型及其在人口死亡率预测中的应用[J]. 系统科学与数学, 2018, 38(6): 702-710.
[13] 冯盼峰,温永仙. 基于随机森林算法的两阶段变量选择研究[J]. 系统科学与数学, 2018, 38(1): 119-130.
[14] 张雷. 基于优先等级的震后应急物资LRP 优化决策模型[J]. 系统科学与数学, 2017, 37(2): 491-501.
[15] 方兴华,宋明顺,鲁伟. 测量不确定度信息约束下的最大熵分布研究[J]. 系统科学与数学, 2017, 37(12): 2337-2346.
阅读次数
全文


摘要