基于前景理论的网络消费者多属性行为决策模型
|
摘要
在电子商务环境下消费者由于受到网络参照群体的影响,表现出行为决策的"有限理性"或"非理性"。以B2C电子商务为研究对象,结合前景理论与模糊多属性决策,分析网络消费者复杂的行为决策过程及其影响因素。依据电子商务服务子流程分别建立改进的价值函数、权重函数和前景函数,同时定义多属性决策问题,通过构建针对网络口碑的服务流程分类器和挖掘网络口碑数据以量化行为决策模型,并以京东、1号店和当当为例实现了算例分析。研究结果表明:(1)与基于期望效用理论构建的决策行为模型相比较,基于前景理论的网络消费者行为决策模型更能反映现实情况;(2)算例结果表明,京东的综合前景得分最高,1号店次之,当当最低。网络口碑的聚类分析得到了13个评价指标,京东在其中7个指标的前景值最优,1号店有4个前景值最优。京东虽然总体得分最高,但其售后服务阶段的得分却最低,导致总得分差距被缩小。而1号店由于出色的服务补救,最终得分排名第二。实验结果充分表明良好的服务补救策略有助于提升服务质量。
Modeling the decision-making process of online consumers in a proper way can provide strategic suggestions on operation management and service marketing for electronic commerce firms. In recent years, many researches have tried to model the consumers' decision-making process from different perspectives, like considering consumers' behavior patterns, integrating consumption theories, and utilizing different methods or tools. Most of these researches build models based on the Expected Utility Theory which depends on the "Rational People" hypothesis. However, online consumers often make some "bounded rational" or "irrational" decisions in an electronic commerce environment, due to peers' influence.Therefore, Prospect Theory, which is dependent on the "Irrational People" hypothesis, is selected as the theoretical basis in this paper. We replace the traditional expected utility function with Prospect Theory's value function to build a reasonable behavioral decision-making model. Moreover, an improvement in value function is acquired by the introduction of intuitionistic triangular fuzzy number. We provide our approach in detail as follows.First, we construct the behavioral decision-making model based on Prospect Theory. Then the intuitionistic fuzzy number is introduced to express fuzzy decision-making information, which brings about improved value function, improved weight function as well as improved prospect function. We also build a more appropriate behavioral decision-making model. Therefore, we have determined the basic form of the model.Secondly, the whole service process of B2 C electronic commerce is divided into six sub-processes by using service blueprinting. Based on these six sub-processes, the multiple attribute decision-making problem is defined through the determination of the multiple attribute structure and the set of alternatives which includes three dominant B2 C platforms in China, e.g. Jingdong(jd.com), Yihaodian(yhd.com) and Dangdang(dangdang.com). Hence, the behavioral decision-making model of online consumers based on Prospect Theory has been determined.Thirdly, the behavioral model of decision-making is quantified by means of text mining of the collected eWOMs(Electronic Word-of-Mouth). The details of the process are showed as follows. First, we construct a SVM(Support Vector Machine) classifier for eWOMs, which classifies eWOMs into different service sub-processes. Then the eWOMs in different sub-processes are clustered by the use of Weka, which is a data mining kit. Based on the clustering results,we can define 13 evaluating indicators and their corresponding weights. Finally, we convert the eWOMs into intuitionistic triangular fuzzy numbers, which determine the parameters of our model according to the results of sentiment analysis. Therefore, the model is quantified.Finally, we take Jingdong, Yihaodian and Dangdang as examples to test the behavioral model of decision-making. Furthermore, the reliability of this behavioral decision-making model is identified by comparison with the model based on the Expected Utility Theory.The results show that:(1) Compared with the models which are based on Expected Utility Theory, the behavioral decision model proposed in this paper performs better to reveal the practical situation.(2) Results of the calculated examples show that Jingdong scores the highest prospect values, followed by Yihaodian and Dangdang. Clustering of eWOMs results in 13 indicators. Jingdong scores the highest prospect values in seven indicators, while Yihaodian scores the highest ones in four indicators. Though Jingdong takes the highest overall score, its score is the lowest one in after-sales stage, giving rise to a narrowed gap in total score. While Yihaodian's excellent service recovery help itself to rank second. The results show that proper service recovery strategies contribute to the improvement of service quality.
Modeling the decision-making process of online consumers in a proper way can provide strategic suggestions on operation management and service marketing for electronic commerce firms. In recent years, many researches have tried to model the consumers' decision-making process from different perspectives, like considering consumers' behavior patterns, integrating consumption theories, and utilizing different methods or tools. Most of these researches build models based on the Expected Utility Theory which depends on the "Rational People" hypothesis. However, online consumers often make some "bounded rational" or "irrational" decisions in an electronic commerce environment, due to peers' influence.Therefore, Prospect Theory, which is dependent on the "Irrational People" hypothesis, is selected as the theoretical basis in this paper. We replace the traditional expected utility function with Prospect Theory's value function to build a reasonable behavioral decision-making model. Moreover, an improvement in value function is acquired by the introduction of intuitionistic triangular fuzzy number. We provide our approach in detail as follows.First, we construct the behavioral decision-making model based on Prospect Theory. Then the intuitionistic fuzzy number is introduced to express fuzzy decision-making information, which brings about improved value function, improved weight function as well as improved prospect function. We also build a more appropriate behavioral decision-making model. Therefore, we have determined the basic form of the model.Secondly, the whole service process of B2 C electronic commerce is divided into six sub-processes by using service blueprinting. Based on these six sub-processes, the multiple attribute decision-making problem is defined through the determination of the multiple attribute structure and the set of alternatives which includes three dominant B2 C platforms in China, e.g. Jingdong(jd.com), Yihaodian(yhd.com) and Dangdang(dangdang.com). Hence, the behavioral decision-making model of online consumers based on Prospect Theory has been determined.Thirdly, the behavioral model of decision-making is quantified by means of text mining of the collected eWOMs(Electronic Word-of-Mouth). The details of the process are showed as follows. First, we construct a SVM(Support Vector Machine) classifier for eWOMs, which classifies eWOMs into different service sub-processes. Then the eWOMs in different sub-processes are clustered by the use of Weka, which is a data mining kit. Based on the clustering results,we can define 13 evaluating indicators and their corresponding weights. Finally, we convert the eWOMs into intuitionistic triangular fuzzy numbers, which determine the parameters of our model according to the results of sentiment analysis. Therefore, the model is quantified.Finally, we take Jingdong, Yihaodian and Dangdang as examples to test the behavioral model of decision-making. Furthermore, the reliability of this behavioral decision-making model is identified by comparison with the model based on the Expected Utility Theory.The results show that:(1) Compared with the models which are based on Expected Utility Theory, the behavioral decision model proposed in this paper performs better to reveal the practical situation.(2) Results of the calculated examples show that Jingdong scores the highest prospect values, followed by Yihaodian and Dangdang. Clustering of eWOMs results in 13 indicators. Jingdong scores the highest prospect values in seven indicators, while Yihaodian scores the highest ones in four indicators. Though Jingdong takes the highest overall score, its score is the lowest one in after-sales stage, giving rise to a narrowed gap in total score. While Yihaodian's excellent service recovery help itself to rank second. The results show that proper service recovery strategies contribute to the improvement of service quality.
引文
[1]艾瑞咨询.2015年中国网络购物市场数据[R].2016.5.
[2]冯芷艳,郭迅华,曾大军,陈煜波,陈国青.大数据背景下商务管理研究若干前沿课题[J].管理科学学报,2013,16(1):1-9.
[3]Nicosia F M.Consumer decision process:Marketing and advertising implication[M].New Jersey:Prentice-Hall Inc.,1966.
[4]Howard J A,Sheth J N.The theory of buyer behavior[M].New York:John Wiley&Sons,1969.
[5]Haubl G,Trifts V.Consumer decision making in online shopping environments:The effects of interactive decision aids[J].Marketing Science,2000,19(l):4-21.
[6]Jarvenpaa S L,Tractinsky N,Saarinen L,et al.Consumer trust in an internet store:Across-cultural validation[J].Journal of Computer-Mediated Communication,1999,5(2):1-5.
[7]Talluri K T,Van Ryzin G.The theory and practice of revenue management[M].Boston:Springer,2004.
[8]Simon H A.Theories of bounded rationality[J].Decision and Organization,1972,(1):161-176.
[9]Tversky A,Kahneman D.Judgment under uncertainty:Heuristics and biases[J].Science,1974,185(4157):1124-1131.
[10]蔡付龄,廖貅武,杨娜.基于案例信息的多准则群决策分类方法[J].管理科学学报,2013,16(2):22-32.
[11]Chevalier J A,Mayzlin D.The effect of word of mouth on sales:Online book reviews[J].Journal of Marketing Research,2006,43(3):345-354.
[12]董大海,刘琰.口碑、网络口碑与鼠碑辨析[J].管理学报,2012,9(3):428-437.
[13]杨铭,祁巍,闫相斌,李一军.在线商品评论的效用分析研究[J].管理科学学报,2012,(5):65-75.
[14]Berger J.Word of mouth and interpersonal communication:A review and directions for future research[J].Journal of Consumer Psychology,2014,24(4):586-607.
[15]左文明,王旭,樊偿.社会化电子商务环境下基于社会资本的网络口碑与购买意愿关系[J].南开管理评论,2014,17(4):140-150+160.
[16]Tversky A,Kahneman D.Advances in prospect theory:Cumulative representation of uncertainty[J].Journal of Risk and Uncertainty,1992,5(4):297-323.
[17]陈之宁,王安,周存宝等.直觉三角模糊数距离及其在多属性决策上的应用[J].重庆理工大学学报(自然科学),2012,26(3):130-134.
[18]高岩,周德群,刘晨琛,章玲.基于关联的三角模糊数直觉模糊集成算子及其应用[J].系统工程理论与实践,2012,32(9):1964-1972.
[19]Zuo W M,Huang Q P,Fan C,Zhang Z P.Quality management of B2CE-commerce service based on human factors engineering[J].Electronic Commerce Research and Applications,2013,12(5):309-320.
[20]苏金树,张博锋,徐昕.基于机器学习的文本分类技术研究进展[J].软件学报,2006,17(9):1848-1859.
[21]Chang C C,Lin C J.LIBSVM:a library for support vector machines[J].ACM Transactions on Intelligent Systems and Technology,2011,2(3):27.
[22]沈阳.ROST CM[EB/OL].武汉大学,2008.
[23]Zadeh L.A.Fuzzy sets[J].Information and Control,1965,(8):338-356.
[24]Chen S J,Hwang C L.Fuzzy multiple attribute decision making:methods and applications[M].Springer-Verlag New York,Inc.,1992.
[25]Kahneman D,Tversky A.Prospect theory:An analysis of decision under risk[J].Econometrica:Journal of the Econometric Society,1979,47(2):263-291.
[26]郭文英.期望效用理论的发展[J].首都经济贸易大学学报,2005,7(5):11-14.
[27]中国互联网络信息中心.第35次中国互联网络发展状况统计报告[R].2015.1.
[28]Mc Collough MA,Bharadwaj SG.The recovery paradox:An examination of consumer satisfaction in relation to disconfirmation,service quality,and attribution based theories[J].Marketing Theory and Applications,1992,(3):119.
[29]陈可,涂平.顾客参与服务补救:基于MOA模型的实证研究[J].管理科学,2014,(3):105-113.
[30]曹忠鹏,马钦海,赵晓煜.服务补救悖论的研究综述及管理启示[J].预测,2012,31(5):74-80.
(1)此处运费是指物品运送费的计算费率及免邮费的起征金额。
[2]冯芷艳,郭迅华,曾大军,陈煜波,陈国青.大数据背景下商务管理研究若干前沿课题[J].管理科学学报,2013,16(1):1-9.
[3]Nicosia F M.Consumer decision process:Marketing and advertising implication[M].New Jersey:Prentice-Hall Inc.,1966.
[4]Howard J A,Sheth J N.The theory of buyer behavior[M].New York:John Wiley&Sons,1969.
[5]Haubl G,Trifts V.Consumer decision making in online shopping environments:The effects of interactive decision aids[J].Marketing Science,2000,19(l):4-21.
[6]Jarvenpaa S L,Tractinsky N,Saarinen L,et al.Consumer trust in an internet store:Across-cultural validation[J].Journal of Computer-Mediated Communication,1999,5(2):1-5.
[7]Talluri K T,Van Ryzin G.The theory and practice of revenue management[M].Boston:Springer,2004.
[8]Simon H A.Theories of bounded rationality[J].Decision and Organization,1972,(1):161-176.
[9]Tversky A,Kahneman D.Judgment under uncertainty:Heuristics and biases[J].Science,1974,185(4157):1124-1131.
[10]蔡付龄,廖貅武,杨娜.基于案例信息的多准则群决策分类方法[J].管理科学学报,2013,16(2):22-32.
[11]Chevalier J A,Mayzlin D.The effect of word of mouth on sales:Online book reviews[J].Journal of Marketing Research,2006,43(3):345-354.
[12]董大海,刘琰.口碑、网络口碑与鼠碑辨析[J].管理学报,2012,9(3):428-437.
[13]杨铭,祁巍,闫相斌,李一军.在线商品评论的效用分析研究[J].管理科学学报,2012,(5):65-75.
[14]Berger J.Word of mouth and interpersonal communication:A review and directions for future research[J].Journal of Consumer Psychology,2014,24(4):586-607.
[15]左文明,王旭,樊偿.社会化电子商务环境下基于社会资本的网络口碑与购买意愿关系[J].南开管理评论,2014,17(4):140-150+160.
[16]Tversky A,Kahneman D.Advances in prospect theory:Cumulative representation of uncertainty[J].Journal of Risk and Uncertainty,1992,5(4):297-323.
[17]陈之宁,王安,周存宝等.直觉三角模糊数距离及其在多属性决策上的应用[J].重庆理工大学学报(自然科学),2012,26(3):130-134.
[18]高岩,周德群,刘晨琛,章玲.基于关联的三角模糊数直觉模糊集成算子及其应用[J].系统工程理论与实践,2012,32(9):1964-1972.
[19]Zuo W M,Huang Q P,Fan C,Zhang Z P.Quality management of B2CE-commerce service based on human factors engineering[J].Electronic Commerce Research and Applications,2013,12(5):309-320.
[20]苏金树,张博锋,徐昕.基于机器学习的文本分类技术研究进展[J].软件学报,2006,17(9):1848-1859.
[21]Chang C C,Lin C J.LIBSVM:a library for support vector machines[J].ACM Transactions on Intelligent Systems and Technology,2011,2(3):27.
[22]沈阳.ROST CM[EB/OL].武汉大学,2008.
[23]Zadeh L.A.Fuzzy sets[J].Information and Control,1965,(8):338-356.
[24]Chen S J,Hwang C L.Fuzzy multiple attribute decision making:methods and applications[M].Springer-Verlag New York,Inc.,1992.
[25]Kahneman D,Tversky A.Prospect theory:An analysis of decision under risk[J].Econometrica:Journal of the Econometric Society,1979,47(2):263-291.
[26]郭文英.期望效用理论的发展[J].首都经济贸易大学学报,2005,7(5):11-14.
[27]中国互联网络信息中心.第35次中国互联网络发展状况统计报告[R].2015.1.
[28]Mc Collough MA,Bharadwaj SG.The recovery paradox:An examination of consumer satisfaction in relation to disconfirmation,service quality,and attribution based theories[J].Marketing Theory and Applications,1992,(3):119.
[29]陈可,涂平.顾客参与服务补救:基于MOA模型的实证研究[J].管理科学,2014,(3):105-113.
[30]曹忠鹏,马钦海,赵晓煜.服务补救悖论的研究综述及管理启示[J].预测,2012,31(5):74-80.
(1)此处运费是指物品运送费的计算费率及免邮费的起征金额。
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |