考虑错分代价的ADASVM-CSLINEX模型及应用

doi:10.3778/j.issn.1002-8331.2210-0379

摘要/Abstract

摘要： 在二分类预测中存在对两类样本的两类分类错误，在现实应用中这两类错误的代价往往是不同的，该文考虑了两类错误的错分代价问题。通过引入一种具有非对称性的LINEX损失函数，可以实现对低错分代价的样本进行线性级惩罚，对高错分代价的样本进行指数级惩罚。模型以SVM作为AdaBoost的基分类器，再将LINEX损失函数嵌入到AdaBoost-SVM的权重更新方程中，根据对正负类样本错分代价的不同以及样本是否错分重新更新样本权重。对2011年1月至2020年12月的沪深300指数成分股进行了实证研究，利用所提出的模型方法进行涨跌预测，研究发现所构建的ADASVM-CSLINEX模型可以获得更高的投资绩效。

关键词: 量化选股, 错分代价, LINEX损失函数, 支持向量机, AdaBoost

Abstract: In binary classification prediction,there are two types of errors that inevitably occur in the prediction of stocks,but the misclassification costs of these two types of errors are often different in practical applications, and this article focuses on this issue. This paper introduces an asymmetric LINEX (Linear-exponential) loss function, which uses LINEX loss to achieve cost sensitive learning by penalizing the low cost of misclassification class linearly and punishing the high cost of misclassification class exponentially.The model uses SVM as the base classifier for AdaBoost, embedding LINEX loss function into AdaBoost-SVM weight update equation and updating the samples weights according to the different misclassification costs of positive and negative samples and whether the samples are misclassified or not. This paper takes the components of HS300 from January 2011 to December 2020 as samples for empirical research, and the proposed model is used to predict the rise and fall. The result shows that the ADASVM-CSLINEX model can obtain higher investment performance.

Key words: quantitative stock selection, misclassification cost, LINEX loss function, support vector machine, AdaBoost

杨园园, 鲁统宇, 崔俊, 许文甫. 考虑错分代价的ADASVM-CSLINEX模型及应用[J]. 计算机工程与应用, 2024, 60(3): 348-356.

YANG Yuanyuan, LU Tongyu, CUI Jun, XU Wenfu. Application of ADASVM-CSLINEX Model Considering Misclassification Cost[J]. Computer Engineering and Applications, 2024, 60(3): 348-356.

参考文献

[1] MEYER H, KüHNLEIN M, APPELHANS T, et al. Comparison of four machine learning algorithms for their applicability in satellite-based optical rainfall retrievals[J].Atmospheric Research, 2016, 169: 424-433.
[2] ABAYOMI-ALLI O, MISRA S, ABAYOMI-ALLI A, et al. A review of soft techniques for SMS spam classification: methods, approaches and applications[J].Engineering Applications of Artificial Intelligence, 2019, 86: 197-212.
[3] KAYMAK S, HELWAN A, UZUN D. Breast cancer image classification using artificial neural networks[J].Procedia Computer Science, 2017, 120: 126-131.
[4] VLAHOU A, SCHORGEW J O, GREGORY B W, et al. Diagnosis of ovarian cancer using decision tree classification of mass spectral data[J].Journal of Biomedicine and Biotechnology, 2003(5): 308-314.
[5] VIAENE S, DERRIG R A, DEDENE G. Cost-sensitive learning and decision making for Massachusetts PIP claim fraud data[J].International Journal of Intelligent Systems, 2004, 19(12): 1197-1215.
[6] SAADALLAH A, BüSCHER J, ABDULAATY O, et al. Explainable predictive quality inspection using deep learning in electronics manufacturing[J].Procedia CIRP, 2022, 107: 594-599.
[7] SUN J, FJITA H, CHEN P, et al. Dynamic financial distress prediction with concept drift based on time weighting combined with Adaboost support vector machine ensemble[J]. Knowledge-Based Systems, 2017, 120: 4-14.
[8] HAN Y T, SUN Q, YU Z X. Research on financial early warning of listed companies based on Lasso-logistic model[C]//Proceedings of the Third International Conference on Economic and Business Management (FEBM), 2018: 263-267.
[9] HUANG C L, CHEN M C, WANG C J. Credit scoring with a data mining approach based on support vector machines[J].Expert Systems with Applications, 2007, 33(4): 847-856.
[10] 谢琪, 程耕国, 徐旭.基于神经网络集成学习股票预测模型的研究[J].计算机工程与应用, 2019, 55(8): 238-243.
XIE Q, CHENG G G, XU X. Research based on stock predicting model of neural networks ensemble learning[J].Computer Engineering and Applications, 2019, 55(8): 238-243.
[11] BASAK S, KAR S, SAHA S, et al. Predicting the direction of stock market prices using tree-based classifiers[J].The North American Journal of Economics and Finance, 2019, 47: 552-567.
[12] CHENG Z W, CHEN C S, QIU X H, et al. An improved KNN classification algorithm based on sampling[C]//Proceeding of the Advances in Materials, Machinery, Electrical Engineering (AMMEE), 2017: 220-225.
[13] CHEN R, ZHANG C X, GUO J, et al. Application of Naive Bayesian algorithms in E-mail classification[C]//Chinese Automation Congress (CAC), 2019: 3933-3938.
[14] KHAIDEM L, SAHA S, DEY S R. Predicting the direction of stock market prices using random forest[J].arXiv:1605. 00003, 2016.
[15] SUN Y T, ZHAO H Q. Stock selection model based on advanced AdaBoost algorithm[C]//Proceedings of the Seventh International Conference on Modelling, Identification and Control (ICMIC), 2015: 290-296.
[16] 罗泽南.基于集成树模型的Stacking量化选股策略研究[J].中国物价, 2021(2): 81-84.
LUO Z N. Research on quantitative stock selection strategy based on Stacking ensemble tree model[J].China Price, 2021(2): 81-84.
[17] LAN J, HU M Y, PATUWO E, et al. An investigation of neural network classifiers with unequal misclassification costs and group sizes[J]. Decision Support Systems, 2010, 48(4): 582-591.
[18] ELKAN C. The foundations of cost-sensitive learning[C]// Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence, 2001: 973-978.
[19] 王超发, 孙静春.考虑错分代价的LogitBoost算法及其在手机用户价值分类中的应用[J].系统工程理论与实践, 2019, 39(10): 2702-2712.
WANG C F, SUN J C. LogitBoost algorithm considering the cost of misclassification and its application in the classification of mobile user value[J].Systems Engineering-Theory & Practice, 2019, 39(10): 2702-2712.
[20] ZHOU Z H, LIU X Y. On multi‐class cost‐sensitive learning[J]. Computational Intelligence, 2010, 26(3): 232-257.
[21] 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.
[22] ZADROZNY B, LANGFORD J, ABE A. Cost-sensitive learning by cost-proportionate example weighting[C]//Third IEEE International Conference on Data Mining, 2003: 435-442.
[23] TING K M. An instance-weighting method to induce cost-sensitive trees[J].IEEE Transactions on Knowledge and Data Engineering, 2002, 14(3): 659-665.
[24] DOMINGOS P. MetaCost: a general method for making classifiers cost-sensitive[C]//Proceedings of the Fifth International Conference on Knowledge Discovery and Data Mining, 1999: 155-164.
[25] 凌晓峰, SHENG Victor S. 代价敏感分类器的比较研究 (英文)[J].计算机学报, 2007, 30(8): 1203-1211.
LING C X, SHENG V S. A comparative study of cost-sensitive classifiers[J].Chinese Journal of Computers, 2007, 30(8): 1203-1211.
[26] VADERA S. CSNL: a cost-sensitive non-linear decision tree algorithm[J].ACM Transactions on Knowledge Discovery from Data, 2010, 4(2): 1-35.
[27] SAHIN Y, BULKAN S, DUMAN E. A cost-sensitive decision tree approach for fraud detection[J].Expert Systems with Applications, 2013, 40(15): 5916-5923.
[28] QIN Z X, WANG A T, ZHANG C Q, et al. Cost-sensitive classification with k-nearest neighbors[C]//International Conference on Knowledge Science, Engineering and Management, 2013: 112-131.
[29] BAHNSEN A C, AOUADA D, OTTERSTEN B. Example-dependent cost-sensitive logistic regression for credit scoring[C]//Proceedings of the Thirteenth International Conference on Machine Learning and Applications (ICMLA), 2014: 263-269.
[30] LIN Y, LEE Y, WAHBA G. Support vector machines for classification in nonstandard situations[J].Machine Learning, 2002, 46: 191-202.
[31] IRANMEHR A, MASNADI-SHIRAZI H, VASCONCELOS N. Cost-sensitive support vector machines[J].Neurocomputing, 2019, 343: 50-64.
[32] MASNADI-SHIRAZI H, VASCONCELOS N. Cost-sensitive boosting[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(2): 294-309.
[33] FAN W, STOLFO S J, ZHANG J X, et al. AdaCost: misclassification cost-sensitive Boosting[C]//Proceedings of the Sixteenth International Conference on Machine Learning, 1999: 97-105.
[34] VARIAN H B. A Bayesian approach to real estate assessment[M]//Studies in Bayesian econometric and statistics in honor of Leonard J. savage.[S.l.]：North-Holland Public Co., 1975: 195-208.
[35] MA Y, ZHAO K, WANG Q, et al. Incremental cost-sensitive support vector machine with Linear-Exponential loss[J].IEEE Access, 2020, 8: 149899-149914.
[36] FU S J, YU X Y, TIAN Y J. Cost sensitive v-support vector machine with LINEX loss[J].Information Processing and Management, 2022, 59(2).
[37] FU Y, CAO S A, PANG T. A sustainable quantitative stock selection strategy based on dynamic factor adjustment[J]. Sustainability, 2020, 12(10).
[38] 王晓丹, 孙东延, 郑春颖, 等.一种基于AdaBoost的SVM分类器[J].空军工程大学学报(自然科学版), 2006(6): 54-57.
WANG X D, SUN D Y, ZHENG C Y, et al. A combined SVM classifier based on AdaBoost[J].Journal of Air Force Engineering University, 2006(6): 54-57.
[39] 李斌, 邵新月, 李玥阳.机器学习驱动的基本面量化投资研究[J].中国工业经济, 2019(8): 61-79.
LI B, SHAO X Y, LI Y Y. Research on machine learning driven quantamental investing[J].China Industrial Economics, 2019, 377(8): 61-79.