基于离散Bass模型的双十一销售预测
|
摘要
阿里巴巴双十一购物节的销售额走势,不仅是相关企业规划决策的依据,也是我国经济活动的重要方向性指标,运用Bass模型预测双十一销售额具有十分重要的意义.对普通正向的离散Bass模型采用普通最小二乘法得到的参数估计值偏离于原连续模型参数的真实值,因为存在着多重共线性和时间区间偏差.为克服这两个缺点,根据一类黎卡提方程构建精确的离散Bass模型.研究显示该模型及其解均收敛于原连续模型.给出基于非线性最小二乘法则的搜索算法,估计模型参数,拟合效果较好.最后将模型结果运用到阿里巴巴双十一的销售额预测,结果表明2018销售额将迎来拐点,增速将放缓.
The future tendency of Alibaba Double Eleven shopping concerns not only the related enterprises to make planning and decision,but also involves important directional leading indicator for economic activity of our country.It is significant to apply Bass model to forecast the Double Eleven sales.However,for ordinary forward discrete Bass model,parameter estimation obtained by using the ordinary least squares procedure may deviate from the true value due to multicollinearity and the time-interval bias.To overcome the two shortcoming,a discrete exact Bass model followed discrete Riccati Equation is constructed.Research shows that the discrete exact Bass model and its' solution converge almost surely to the original continuous model.This paper builds a nonlinear least squares-based search algorithm to estimate the parameters,which produces a good fitting effect.Then it is applied to forecast the Alibaba Double Eleven shopping sales and the results indicate that sales will meet a turning point in 2018 and then will slow down gradually
The future tendency of Alibaba Double Eleven shopping concerns not only the related enterprises to make planning and decision,but also involves important directional leading indicator for economic activity of our country.It is significant to apply Bass model to forecast the Double Eleven sales.However,for ordinary forward discrete Bass model,parameter estimation obtained by using the ordinary least squares procedure may deviate from the true value due to multicollinearity and the time-interval bias.To overcome the two shortcoming,a discrete exact Bass model followed discrete Riccati Equation is constructed.Research shows that the discrete exact Bass model and its' solution converge almost surely to the original continuous model.This paper builds a nonlinear least squares-based search algorithm to estimate the parameters,which produces a good fitting effect.Then it is applied to forecast the Alibaba Double Eleven shopping sales and the results indicate that sales will meet a turning point in 2018 and then will slow down gradually
引文
[1]中国电子商务研究中心. http://b2b.toocle.com/detail-6432423.html.
[2]王日爽,董大海,郭艳红.Bass模型在新生活方式扩散预测应用的研究——以中国网上购物为例[J].现代管理科学,2011(08):35-37+116.
[3]Satoh D.A discrete bass model and its parameter estimation[J].Journal of the Operations Research Society of Japan,2001,44(1):1-18.
[4]Bass F M.A new product growth model for consumer durables[J].Management Science,1969,15:215-227.
[5]Dodds W.An application of the bass model in long-term new product forecasting[J].Journal of Marketing Research,1973,10(3):308-311.
[6]Tanny S M,Derzko N A.Innovators and imitators in innovation diffusion modelling[J].Journal of Forecasting,2010,7(4):225-234.
[7]龙子泉,常静敏,陈植元.激励政策对新能源汽车推广的影响研究——基于修正Bass模型的实证分析[J].科技管理研究,2016,36(04):138-144.
[8]刘颖琦,王萌,王静宇.中国新能源汽车市场预测研究[J].经济与管理研究,2016,37(04):86-91.
[9]徐琪,刘峥.基于SVM的短生命周期产品供应链双渠道需求预测模型[J].系统管理学报,2014,23(02):255-262+270.
[10]王核成,应波.基于消费者采纳网络的网上购物扩散模型——以中国网上购物为例[J].系统工程,2013,31(01):78-84.
[11]石泉龙,王丽亚,吴明兴.基于Bass模型的产品功能疲劳预测[J].工业工程与管理,2014,19(02):62-67+74.
[12]曹宏铎,李,张晓云.面向文化资产证券化定价的G-Bass随机扩散预测模型研究[J].管理工程学报,2017,31(01):192-200.
[13]卢铭凯.厂商采用新技术的最优时机研究——基于Bass模型和实物期权理论[J].华东经济管理,2012,26(02):155-157.
[14]冉晓斌,刘跃文,姜锦虎.数据驱动下的个体移动服务产品采纳行为的扩散研究[J].中国管理科学,2017,25(09):141-147.
[15]Bernhardt I,and MacKenzie K M.Some problems in using diffusion models for new products[J].Management Science,1972(19):187-200.
[16]Heeler R M,and Hustad T P.Problems in predicting new product growth for consumer durables[J].Management Science,1980(26):1007-1020.
[17]杨敬辉,武春友.基于Bass模型的两种参数估算算法比较研究[J].数量经济技术经济研究,2005,22(12):125-132.
[18]Hirota R.Nonlinear partial difference equations.v.nonlinear equations reducible to linear equations[J].Journal of the Physical Society of Japan,1979,46(1):312-319.
[19]中国统计年鉴,http://www.stats.gov.cn/tjsj/ndsj/,2009-2017.
[2]王日爽,董大海,郭艳红.Bass模型在新生活方式扩散预测应用的研究——以中国网上购物为例[J].现代管理科学,2011(08):35-37+116.
[3]Satoh D.A discrete bass model and its parameter estimation[J].Journal of the Operations Research Society of Japan,2001,44(1):1-18.
[4]Bass F M.A new product growth model for consumer durables[J].Management Science,1969,15:215-227.
[5]Dodds W.An application of the bass model in long-term new product forecasting[J].Journal of Marketing Research,1973,10(3):308-311.
[6]Tanny S M,Derzko N A.Innovators and imitators in innovation diffusion modelling[J].Journal of Forecasting,2010,7(4):225-234.
[7]龙子泉,常静敏,陈植元.激励政策对新能源汽车推广的影响研究——基于修正Bass模型的实证分析[J].科技管理研究,2016,36(04):138-144.
[8]刘颖琦,王萌,王静宇.中国新能源汽车市场预测研究[J].经济与管理研究,2016,37(04):86-91.
[9]徐琪,刘峥.基于SVM的短生命周期产品供应链双渠道需求预测模型[J].系统管理学报,2014,23(02):255-262+270.
[10]王核成,应波.基于消费者采纳网络的网上购物扩散模型——以中国网上购物为例[J].系统工程,2013,31(01):78-84.
[11]石泉龙,王丽亚,吴明兴.基于Bass模型的产品功能疲劳预测[J].工业工程与管理,2014,19(02):62-67+74.
[12]曹宏铎,李,张晓云.面向文化资产证券化定价的G-Bass随机扩散预测模型研究[J].管理工程学报,2017,31(01):192-200.
[13]卢铭凯.厂商采用新技术的最优时机研究——基于Bass模型和实物期权理论[J].华东经济管理,2012,26(02):155-157.
[14]冉晓斌,刘跃文,姜锦虎.数据驱动下的个体移动服务产品采纳行为的扩散研究[J].中国管理科学,2017,25(09):141-147.
[15]Bernhardt I,and MacKenzie K M.Some problems in using diffusion models for new products[J].Management Science,1972(19):187-200.
[16]Heeler R M,and Hustad T P.Problems in predicting new product growth for consumer durables[J].Management Science,1980(26):1007-1020.
[17]杨敬辉,武春友.基于Bass模型的两种参数估算算法比较研究[J].数量经济技术经济研究,2005,22(12):125-132.
[18]Hirota R.Nonlinear partial difference equations.v.nonlinear equations reducible to linear equations[J].Journal of the Physical Society of Japan,1979,46(1):312-319.
[19]中国统计年鉴,http://www.stats.gov.cn/tjsj/ndsj/,2009-2017.