基于机器学习的信用卡交易欺诈检测研究综述

doi:10.3778/j.issn.1002-8331.2302-0129

摘要/Abstract

摘要： 机器学习在信用卡交易检测中有其特殊性，面对的环境更为复杂。由于有人的智力介入，战胜信用卡交易欺诈，其挑战性比人脸识别、无人驾驶等工程问题的难度更高，照搬工程学科的机器学习方法往往会失败。综述了2000年以来基于机器学习的信用卡欺诈检测研究历程，辨析了该领域的研究范畴、应用场景、技术流派等相关概念及其联系；解构了机器学习欺诈识别的一般性研究架构，从特征工程、模型算法、评价指标三个环节归纳总结了领域内研究的最新进展；从数据集是否具备标签角度，着重列举了面向欺诈识别的有监督的、无监督和半监督三类主流机器学习模型，讨论了这些模型的出发点、核心思想、求解方法以及优缺点；还分析了强化学习模型模拟欺诈者与机构之间的动态博弈过程；探讨了机器学习面临的海量数据、样本偏斜和概念漂移三大难点问题，并汇集整理了缓解这些问题的最新进展；总结了面向欺诈检测的机器学习研究目前存在的局限、争议和挑战，并为未来的研究方向提供趋势分析与建议。

关键词: 信用卡欺诈识别, 机器学习, 数据挖掘, 样本偏斜, 概念漂移

Abstract: Machine learning has its distinctiveness in credit card transaction detection and faces a more complex environment. Since the intervention of human intelligence, machine learning encounters harder challenges in fraud detection than the ones of face recognition and driverlessness, which leads to failures if only applying the processes of engineering disciplines. This paper depicts the 2000-since research history of credit card anti-fraud; identifies the definition, scope, technical streams, applications, and other key concepts, and their interconnections in the field of detection oriented machine learning; analyzes the general architecture of fraud detection and summarizes the state-of-the-art of transaction fraud detection research in terms of feature engineering, models/algorithms, and evaluation metrics; discusses various detection algorithms of credit card transaction fraud and enumerates their original intention, core ideas, solution methods, advantages or disadvantages, and relevant extensions; highlights unsupervised, supervised, and semi-supervised learning models of fraud recognition, as well as various ensembles such as models cascading and aggregation; addresses three major challenges, i.e., massive data, sample skew, and concept drift, and compiles the latest progresses to alleviate these problems. This paper concludes with the limitations, controversies, and challenges of machine learning on credit card fraud recognition, and provides the trend analysis and suggestions for future research directions.

Key words: credit fraud detection, machine learning, data mining, sample skew, concept drift

蒋洪迅, 江俊毅, 梁循. 基于机器学习的信用卡交易欺诈检测研究综述[J]. 计算机工程与应用, 2023, 59(21): 1-25.

JIANG Hongxun, JIANG Junyi, LIANG Xun. Survey on Credit Card Transaction Fraud Detection Based on Machine Learning[J]. Computer Engineering and Applications, 2023, 59(21): 1-25.

参考文献

[1] VAN VLASSELAER V，BRAVO C，CAELEN O，et al.APATE：a novel approach for automated credit card transaction fraud detection using network-based extensions[J].Decision Support Systems，2015，75：38-48.
[2] CARNEIROA N，FIGUEIRA G，COSTA M.A data mining based system for credit-card fraud detection in e-tail[J].Decision Support Systems，2017，95：91-101.
[3] BHATTACHARYYA S，JHA S，THARAKUNNEL K，et al.Data mining for credit card fraud：a comparative study[J].Decision Support Systems，2011，50（3）：602-613.
[4] ZHANG X W，HAN Y C，XU W，et al.HOBA：a novel feature engineering methodology for credit card fraud detection with a deep learning architecture[J].Information Sciences，2021，557：302-316.
[5] FRAUD-THE FACTS 2021[EB/OL].（2021）.https：//www.ukfinance.org.uk/system/files/Fraud%20The%20Facts%202021-%20FINAL.pdf.
[6] DAL POZZOLO A，CAELEN O，LE BORGNE Y A，et al.Learned lessons in credit card fraud detection from a practitioner perspective[J].Expert Systems with Applications，2014，41（10）：4915-4928.
[7] LI Z C，HUANG M，LIU G J，et al.A hybrid method with dynamic weighted entropy for handling the problem of class imbalance with overlap in credit card fraud detection[J].Expert Systems with Applications，2021，175：10.
[8] CARCILLO F，LE BORGNE Y A，CAELEN O，et al.Combining unsupervised and supervised learning in credit card fraud detection[J].Information Sciences，2021，557：317-331.
[9] BOLTON R J，HAND D J.Statistical fraud detection：a review[J].Statistical Science，2002，17（3）：235-249.
[10] NGAI E W T，HU Y，WONG Y H，et al.The application of data mining techniques in financial fraud detection：a classification framework and an academic review of literature[J].Decision Support Systems，2011，50（3）：559-569.
[11] WEST J，BHATTACHARYA M.Intelligent financial fraud detection：a comprehensive review[J].Computers & Security，2016，57：47-66.
[12] CHOI D，LEE K.An artificial intelligence approach to financial fraud detection under iot environment：a survey and implementation[J].Security and Communication Networks，2018（4）：1-15.
[13] BASIT A，ZAFAR M，LIU X，et al.A comprehensive survey of AI-enabled phishing attacks detection techniques[J].Telecommunication Systems，2021，76（1）：139-154.
[14] AL-HASHEDI K G，MAGALINGAM P.Financial fraud detection applying data mining techniques：a comprehensive review from 2009 to 2019[J].Computer Science Review，2021，40：23.
[15] GIANINI G，FOSSI L G，MIO C，et al.Managing a pool of rules for credit card fraud detection by a game theory based approach[J].Future Generation Computer Systems-the International Journal of Escience，2020，102：549-561.
[16] PORTER D.Reusable analysis and design components for knowledge-based system-development[J].Lecture Notes in Artificial Intelligence，1992，599：373-391.
[17] VATSA V，SURAL S，MAJUMDAR A K.A game-theoretic approach to credit card fraud detection[C]//International Conference on Information Systems Security.Berlin：Springer-Verlag，2005：263-276.
[18] ABDALLAH A，MAAROF M A，ZAINAL A.Fraud detection system：a survey[J].Journal of Network and Computer Applications，2016，68：90-113.
[19] SEEJA K R，ZAREAPOOR M.FraudMiner：a novel credit card fraud detection model based on frequent itemset mining[J].Scientific World Journal，2014（3）：252797.
[20] KUNDU A，PANIGRAHI S，SURAL S，et al.BLAST-SSAHA hybridization for credit card fraud detection[J].IEEE Transactions on Dependable and Secure Computing，2009，6（4）：309-315.
[21] SHI P，ZHAO Z，ZHONG H Q，et al.An improved agglomerative hierarchical clustering anomaly detection method for scientific data[J].Concurrency and Computation-Practice & Experience，2021，33（6）：16.
[22] XU X D，LIU H W，LI L，et al.A comparison of outlier detection techniques for high-dimensional data[J].International Journal of Computational Intelligence Systems，2018，11（1）：652-662.
[23] DUMAN E，OZCELIK M H.Detecting credit card fraud by genetic algorithm and scatter search[J].Expert Systems with Applications，2011，38（10）：13057-13063.
[24] REN H R，YE Z X，LI Z W.Anomaly detection based on a dynamic Markov model[J].Information Sciences，2017，411：52-65.
[25] HUANG J L，ZHU Q S，YANG L J，et al.A novel outlier cluster detection algorithm without top-n parameter[J].Knowledge-Based Systems，2017，121：32-40.
[26] WU J J，XIONG H，CHEN J.COG：local decomposition for rare class analysis[J].Data Mining and Knowledge Discovery，2010，20（2）：191-220.
[27] DORRONSORO J R，GINEL F，SANCHEZ C，et al.Neural fraud detection in credit card operations[J].IEEE Transactions on Neural Networks，1997，8（4）：827-834.
[28] DIEZ-PASTOR J F，RODRIGUEZ J J，GARCIA-OSORIO C I，et al.Diversity techniques improve the performance of the best imbalance learning ensembles[J].Information Sciences，2015，325：98-117.
[29] FIORE U，DE SANTIS A，PERLA F，et al.Using generative adversarial networks for improving classification effectiveness in credit card fraud detection[J].Information Sciences，2019，479：448-455.
[30] LI W F，CHEN H C，NUNAMAKER J F.Identifying and profiling key sellers in cyber carding community：azsecure text mining system[J].Journal of Management Information Systems，2016，33（4）：1059-1086.
[31] NASCIMENTO D C，BARBOSA B，PEREZ A M，et al.Risk management in e-commerce-a fraud study case using acoustic analysis through its complexity[J].Entropy，2019，21（11）：12.
[32] WHITROW C，HAND D J，JUSZCZAK P，et al.Transaction aggregation as a strategy for credit card fraud detection[J].Data Mining and Knowledge Discovery，2009，18（1）：30-55.
[33] JHA S，GUILLEN M，WESTLAND J C.Employing transaction aggregation strategy to detect credit card fraud[J].Expert Systems with Applications，2012，39（16）：12650-12657.
[34] DAL POZZOLO A，BORACCHI G，CAELEN O，et al.Credit card fraud detection：a realistic modeling and a novel learning strategy[J].IEEE Transactions on Neural Networks and Learning Systems，2018，29（8）：3784-3797.
[35] GOMEZ J A，AREVALO J，PAREDES R，et al.End-to-end neural network architecture for fraud scoring in card payments[J].Pattern Recognition Letters，2018，105：175-181.
[36] FAWCETT T，PROVOST F.Adaptive fraud detection[J].Data Mining and Knowledge Discovery，1997，1（3）：291-316.
[37] CHEN R C，CHEN T S，CHIEN Y，et al.Novel questionnaire-responded transaction approach with SVM for credit card fraud detection[C]//Advances in Neural Networks.Berlin：Springer-Verlag，2005：916-921.
[38] CHEN R C，CHEN T S，LIN C C.A new binary support vector system for increasing detection rate of credit card fraud[J].International Journal of Pattern Recognition and Artificial Intelligence，2006，20（2）：227-239.
[39] DESHMEH G，RAHMATI M.Distributed anomaly detection，using cooperative learners and association rule analysis[J].Intelligent Data Analysis，2008，12（4）：339-357.
[40] BAHNSEN A C，AOUADA D，STOJANOVIC A，et al.Feature engineering strategies for credit card fraud detection[J].Expert Systems with Applications，2016，51：134-142.
[41] SAIA R，CARTA S.Evaluating the benefits of using proactive transformed-domain-based techniques in fraud detection tasks[J].Future Generation Computer Systems-the International Journal of Escience，2019，93：18-32.
[42] WU Y，XU Y J，LI J Y.Feature construction for fraudulent credit card cash-out detection[J].Decision Support Systems，2019，127：11.
[43] LUCAS Y，PORTIER P E，LAPORTE L，et al.Towards automated feature engineering for credit card fraud detection using multi-perspective HMMs[J].Future Generation Computer Systems-the International Journal of Escience，2020，102：393-402.
[44] BRAVO C，THOMAS L C，WEBER R.Improving credit scoring by differentiating defaulter behaviour[J].Journal of the Operational Research Society，2015，66（5）：771-781.
[45] 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.
[46] BAHNSEN A C，AOUADA D，OTTERSTEN B.Example-dependent cost-sensitive decision trees[J].Expert Systems with Applications，2015，42（19）：6609-6619.
[47] SEERA M，LIM C P，KUMAR A，et al.An intelligent payment card fraud detection system[J].Annals of Operations Research，2021：23.
[48] WONG N，RAY P，STEPHENS G，et al.Artificial immune systems for the detection of credit card fraud：an architecture，prototype and preliminary results[J].Information Systems Journal，2012，22（1）：53-76.
[49] JURGOVSKY J，GRANITZER M，ZIEGLER K，et al.Sequence classification for credit-card fraud detection[J].Expert Systems with Applications，2018，100：234-245.
[50] DARWISH S M.An intelligent credit card fraud detection approach based on semantic fusion of two classifiers[J].Soft Computing，2020，24（2）：1243-1253.
[51] MAHMOUDI N，DUMAN E.Detecting credit card fraud by modified fisher discriminant analysis[J].Expert Systems with Applications，2015，42（5）：2510-2516.
[52] QUAH J T S，SRIGANESH M.Real-time credit card fraud detection using computational intelligence[J].Expert Systems with Applications，2008，35（4）：1721-1732.
[53] XIONG Z Y，GAO Q Q，GAO Q，et al.ADD：a new average divergence difference-based outlier detection method with skewed distribution of data objects[J].Applied Intelligence，2022，52：5100-5124.
[54] WANG D S，CHEN B T，CHEN J.Credit card fraud detection strategies with consumer incentives[J].Omega-International Journal of Management Science，2019，88：179-195.
[55] MOHAMMED M，KHAN M B，BASHIER E B M.Machine learning：algorithms and applications[M].[S.l.]：CRC Press，2016.
[56] HALVAIEE N S，AKBARI M K.A novel model for credit card fraud detection using artificial immune systems[J].Applied Soft Computing，2014，24：40-49.
[57] HARVEY D Y，TODD M D.Automated feature design for numeric sequence classification by genetic programming[J].IEEE Transactions on Evolutionary Computation，2015，19（4）：474-489.
[58] ZAKARYAZAD A，DUMAN E.A profit-driven artificial neural network（ANN） with applications to fraud detection and direct marketing[J].Neurocomputing，2016，175：121-131.
[59] WANG S，LIU G J，LI Z C，et al.Credit card fraud detection using capsule network[C]//IEEE International Conference on Systems，Man，and Cybernetics（SMC），2018：3679-3684.
[60] FOROUGH J，MOMTAZI S.Sequential credit card fraud detection：a joint deep neural network and probabilistic graphical model approach[J].Expert Systems，2021：13.
[61] FOROUGH J，MOMTAZI S.Ensemble of deep sequential models for credit card fraud detection[J].Applied Soft Computing，2021，99：11.
[62] ACHITUVE I，KRAUS S，GOLDBERGER J，et al.Interpretable online banking fraud detection based on hierarchical attention mechanism[C]//IEEE 29th International Workshop on Machine Learning for Signal Processing，2019.
[63] CHENG D W，XIANG S，SHANG C C，et al.Spatio-temporal attention-based neural network for credit card fraud detection[C]//34th AAAI Conference on Artificial Intelligence / 32nd Innovative Applications of Artificial Intelligence Conference / 10th AAAI Symposium on Educational Advances in Artificial Intelligence，2020：362-369.
[64] AHMED M，MAHMOOD A N，ISLAM M R.A survey of anomaly detection techniques in financial domain[J].Future Generation Computer Systems-the International Journal of Escience，2016，55：278-288.
[65] BOLTON R J，HAND D J.Unsupervised profiling methods for fraud detection[C]//Proceedings of Credit Scoring Credit Control，2001：235-255.
[66] PANIGRAHI S，KUNDU A，SURAL S，et al.Credit card fraud detection：a fusion approach using Dempster-Shafer theory and Bayesian learning[J].Information Fusion，2009，10（4）：354-363.
[67] SUDJIANTO A，NAIR S，YUAN M，et al.Statistical methods for fighting financial crimes[J].Technometrics，2010，52（1）：5-19.
[68] JU C，LU Q.Research on credit card fraud detection model based on class weighted support vector machine[J].Journal of Convergence Information Technology，2011，6（1）：62-68.
[69] LEE Y J，YEH Y R，WANG Y C F.Anomaly detection via online oversampling principal component analysis[J].IEEE Transactions on Knowledge and Data Engineering，2013，25（7）：1460-1470.
[70] KNORR E M，NG R T，TUCAKOV V.Distance-based outliers：algorithms and applications[J].VLDB Journal，2000，8（3/4）：237-253.
[71] 陈溟.基于模糊局部离群因子（LOF）的信用卡欺诈检测研究[J].金融理论与实践，2016（10）：54-57.
CHEN M.Research on credit card fraud detection based on fuzzy local outlier factor（LOF）[J].Financial Theory and Practice，2016（10）：54-57.
[72] YU J X，QIAN W N，LU H J，et al.Finding centric local outliers in categorical/numerical spaces[J].Knowledge and Information Systems，2006，9（3）：309-338.
[73] TANG J，CHEN Z X，FU A W C，et al.Capabilities of outlier detection schemes in large datasets，framework and methodologies[J].Knowledge and Information Systems，2007，11（1）：45-84.
[74] KOUFAKOU A，GEORGIOPOULOS M.A fast outlier detection strategy for distributed high-dimensional data sets with mixed attributes[J].Data Mining and Knowledge Discovery，2010，20（2）：259-289.
[75] JIANG F，SUI Y F，CAO C G.A hybrid approach to outlier detection based on boundary region[J].Pattern Recognition Letters，2011，32（14）：1860-1870.
[76] KOUFAKOU A，SECRETAN J，GEORGIOPOULOS M.Non-derivable itemsets for fast outlier detection in large high-dimensional categorical data[J].Knowledge and Information Systems，2011，29（3）：697-725.
[77] GREKOUSIS G，FOTIS Y N.A fuzzy index for detecting spatiotemporal outliers[J].Geoinformatica，2012，16（3）：597-619.
[78] JIANG F，CHEN Y M.Outlier detection based on granular computing and rough set theory[J].Applied Intelligence，2015，42（2）：303-322.
[79] HUANG J L，ZHU Q S，YANG L J，et al.A non-parameter outlier detection algorithm based on natural neighbor[J].Knowledge-Based Systems，2016，92：71-77.
[80] SRIVASTAVA A，KUNDU A，SURAL S，et al.Credit card fraud detection using hidden Markov model[J].IEEE Transactions on Dependable and Secure Computing，2008，5（1）：37-48.
[81] ROBINSON W N，ARIA A.Sequential fraud detection for prepaid cards using hidden Markov model divergence[J].Expert Systems with Applications，2018，91：235-251.
[82] OLSZEWSKI D.Fraud detection using self-organizing map visualizing the user profiles[J].Knowledge-Based Systems，2014，70：324-334.
[83] 刘建伟，刘媛，罗雄麟.半监督学习方法[J].计算机学报，2015，35（8）：1592-1617.
LIU J W，LIU Y，LUO X L，et al.Semi-supervised learning methods[J].Chinese Journal of Computers，2015，35（8）：1592-617.
[84] SALAZAR A，SAFONT G，VERGARA L，et al.Semi-supervised learning for imbalanced classification of credit card transaction[C]//International Joint Conference on Neural Networks（IJCNN），2018.
[85] LANGEVIN A，CODY T，ADAMS S，et al.Generative adversarial networks for data augmentation and transfer in credit card fraud detection[J].Journal of the Operational Research Society，2021：28.
[86] GOODFELLOW I J，POUGET-ABADIE J，MIRZA M，et al.Generative adversarial nets[C]//Advances in Neural Information Processing Systems 27（NIPS 2014），2014：2672-2680.
[87] HERR D，OBERT B，ROSENKRANZ M.Anomaly detection with variational quantum generative adversarial networks[J].Quantum Science and Technology，2021，6（4）：13.
[88] CARCILLO F，LE BORGNE Y A，CAELEN O，et al.An assessment of streaming active learning strategies for real-life credit card fraud detection[C]//4th IEEE/ACM/ASA International Conference on Data Science and Advanced Analytics（DSAA），2017：631-639.
[89] AKINYELU A A，EZUGWU A E，ADEWUMI A O.Ant colony optimization edge selection for support vector machine speed optimization[J].Neural Computing & Applications，2020，32（15）：11385-11417.
[90] LI C L，DING N，ZHAI Y M，et al.Comparative study on credit card fraud detection based on different support vector machines[J].Intelligent Data Analysis，2021，25（1）：105-119.
[91] MEAD A，LEWRIS T，PRASANTH S，et al.Detecting fraud in adversarial environments：a reinforcement learning approach[C]//2018 Systems and Information Engineering Design Symposium（SIEDS），2018：118-122.
[92] NAMI S，SHAJARI M.Cost-sensitive payment card fraud detection based on dynamic random forest and k-nearest neighbors[J].Expert Systems with Applications，2018，110：381-392.
[93] JANS M，VAN DER WERF J M，LYBAERT N，et al.A business process mining application for internal transaction fraud mitigation[J].Expert Systems with Applications，2011，38（10）：13351-13359.
[94] 刘颖，杨轲.基于深度集成学习的类极度不均衡数据信用欺诈检测算法[J].计算机研究与发展，2021，58（3）：539-547.
LIU Y，YANG K.Credit fraud detection for extremely imbalanced data based on ensembled deep learning[J].Journal of Computer Research and Development，2021，58（3）：539-547.
[95] 陈荣荣，詹国华，李志华.基于XGBoost算法模型的信用卡交易欺诈预测研究[J].计算机应用研究，2020，37（S1）：111-112.
CHEN R R，ZHAN G H，LI Z H，et al.Research on credit card transaction fraud prediction based on XGBoost algorithm model[J].Application Research of Computers，2020，37（S1）：111-112.
[96] KULTUR Y，CAGLAYAN M U.Hybrid approaches for detecting credit card fraud[J].Expert Systems，2017，34（2）：13.
[97] KIM E，LEE J，SHIN H，et al.Champion-challenger analysis for credit card fraud detection：hybrid ensemble and deep learning[J].Expert Systems with Applications，2019，128：214-224.
[98] XIE Y L，LI A P，GAO L Q，et al.A heterogeneous ensemble learning model based on data distribution for credit card fraud detection[J].Wireless Communications & Mobile Computing，2021：13.
[99] YU S，LI X F，WANG H C，et al.BIDI：a classification algorithm with instance difficulty invariance[J].Expert Systems with Applications，2021，165：13.
[100] SOMASUNDARAM A，REDDY S.Parallel and incremental credit card fraud detection model to handle concept drift and data imbalance[J].Neural Computing & Applications，2019，31：3-14.
[101] HAND D J，WHITROW C，ADAMS N M，et al.Performance criteria for plastic card fraud detection tools[J].Journal of the Operational Research Society，2008，59（7）：956-962.
[102] GUO H Y，VIKTOR H L.Learning from skewed class multi-relational databases[J].Fundamenta Informaticae，2008，89（1）：69-94.
[103] VIAENE S，DERRIG R A，DEDENE G.A case study of applying boosting naive Bayes to claim fraud diagnosis[J].IEEE Transactions on Knowledge and Data Engineering，2004，16（5）：612-620.
[104] SANOBER S，ALAM I，PANDE S，et al.An enhanced secure deep learning algorithm for fraud detection in wireless communication[J].Wireless Communications & Mobile Computing，2021：14.
[105] DEL RIO S，LOPEZ V，MANUEL BENITEZ J，et al.On the use of MapReduce for imbalanced big data using Random Forest[J].Information Sciences，2014，285：112-137.
[106] TRIGUERO I，DEL RIO S，LOPEZ V，et al.ROSEFW-RF：the winner algorithm for the ECBDL’14 big data competition：an extremely imbalanced big data bioinformatics problem[J].Knowledge-Based Systems，2015，87：69-79.
[107] HORMOZI E，HORMOZI H，AKBARI M K，et al.Accuracy evaluation of a credit card fraud detection system on hadoop mapReduce[C]//5th Conference on Information and Knowledge Technology（IKT），2013：35-39.
[108] PALIT I，REDDY C K.Scalable and parallel boosting with MapReduce[J].IEEE Transactions on Knowledge and Data Engineering，2012，24（10）：1904-1916.
[109] HUNG E，CHEUNG D W.Parallel mining of outliers in large database[J].Distributed and Parallel Databases，2002，12（1）：5-26.
[110] CARCILLO F，DAL POZZOLO A，LE BORGNE Y A，et al.SCARFF：a scalable framework for streaming credit card fraud detection with spark[J].Information Fusion，2018，41：182-194.
[111] ZHAI J H，ZHANG S F，ZHANG M Y，et al.Fuzzy integral-based ELM ensemble for imbalanced big data classification[J].Soft Computing，2018，22（11）：3519-3531.
[112] ZHU H H，LIU G J，ZHOU M C，et al.Optimizing weighted extreme learning machines for imbalanced classification and application to credit card fraud detection[J].Neurocomputing，2020，407：50-62.
[113] 莫赞，盖彦蓉，樊冠龙.基于GAN-AdaBoost-DT不平衡分类算法的信用卡欺诈分类[J].计算机应用，2019，39（2）：618-622.
MO Z，GAI Y R，FAN G L，et al.Credit card fraud classification based on GAN-AdaBoost-DT imbalance classification algorithm[J].Journal of Computer Applications，2019，39（2）：618-622.
[114] GAMA J，ZLIOBAITE I，BIFET A，et al.A survey on concept drift adaptation[J].ACM Computing Surveys，2014，46（4）：1-37.