考虑产品特征属性的替代性需求预测方法

doi:10.12066/j.issn.1007-2861.2173

Abstract

Abstract:

The current e-commerce sales business is developing rapidly, and the rapid and accurate prediction of demands has become a necessary research direction. The substitution of products has a significant influence on demand, and applied research in this aspect is increasing. Based on the ranking of best-selling predictive attribute values, proximity replacement rate estimation and the Adaboost prediction model were applied in this study to develop an improved demand forecasting method with higher accuracy, considering product feature attributes. The experimental findings confirm that the proposed method is accurate and reliable.

Key words: demand forecast, substitution rate, logistic regression, adaptive boosting

CLC Number:

TP391

GAO Junjun, NI Ziyue. Alternative demand forecasting considering product feature attribute[J]. Journal of Shanghai University（Natural Science Edition）, 2021, 27(3): 573-582.

Figures/Tables 7

Fig. 1

Fig. 2

Table 1

Table 2

Table 3

Fig. 3

Fig. 4

References 16

[1]	Kök A G. Management of product variety in retail operations[D]. Philadelphia: University of Pennsylvania, 2003.
[2]	Smith S A, Agrawal N. Optimal retail assortment for substitutable items purchased in sets[J]. Naval Research Logistics, 2003,50:793-822. doi: 10.1002/(ISSN)1520-6750
[3]	Smith S A, Agrawal N. Management of multi-item retail inventory systems with demand substitution[M]. Catonsville: INFORMS, 2000.
[4]	高峻峻, 俞莱若. 替代性需求下一类产品的品种选择与库存控制的联合决策[J]. 系统工程理论与实践, 2009,29(3):76-83.
	Gao J J, Yu L R. Joint decision model of product variety and inventory control for an assortment under demand with substitution[J]. System Engineering Theory and Practice, 2009,29(3):76-83. doi: 10.1016/S1874-8651(10)60083-X
[5]	滕在霞, 刘悦, 高峻峻. 基于加权欧式距离的替代率估算方法[J]. 计算机工程, 2010,36(15):283-285.
	Teng Z X, Liu Y, Gao J J. Substitution rate estimation method based on weighted Euclid distance[J]. Computer Engineering, 2010,36(15):283-285. doi: 10.1007/s00366-018-00700-1
[6]	王蓓蓓, 刘文金, 陈耿, 等. 基于Holt-Winters算法的定制家具生产需求预测研究[J]. 林产工业, 2018(1):44-47.
	Wang B B, Liu W J, Chen G, et al. Demand forecasting in customization furniture production based on Holt-Winters algorithm[J]. China Forest Products Industry, 2018(1):44-47.
[7]	张颖, 陈卓. 改进 ARIMA 模型在医药需求预测中的研究[J]. 计算机工程与设计, 2018(1):183-188.
	Zhang Y, Chen Z. Study of improved ARIMA model in medical demand forecasting[J]. Computer Engineering and Design, 2018(1):183-188.
[8]	高峻峻, 谭崇利, 刘悦, 等. 一类产品需求预测的支持向量机方法[J]. 上海大学学报(自然科学版), 2009,15(1):71-76.
	Gao J J, Tan C L, Liu Y, et al. Demand forecast using support vector machine for a product category[J]. Journal of Shanghai University (Natural Science Edition), 2009,15(1):71-76.
[9]	李长春. 大数据背景下的商品需求预测与分仓规划[J]. 数学的实践与认识, 2017,47(7):70-79.
	Li C C. Forecasting of commodities demand and warehouse planning under the background of big data[J]. Mathematics in Practice and Theory, 2017,47(7):70-79.
[10]	高月芳, 梁永生, 唐飞, 等. 基于神经网络的需求预测模型[J]. 计算机工程与应用, 2011,47(22):240-243.
	Gao Y F, Liang Y S, Tang F, et al. Forecasting model based on neural network[J]. Computer Engineering and Applications, 2011,47(22):240-243.
[11]	Shin H, Park S, Lee E, et al. A classification of the literature on the planning of substitutable products[J]. European Journal of Operational Research, 2015,246(3):686-699. doi: 10.1016/j.ejor.2015.04.013
[12]	Maalouf M. Logistic regression in data analysis: an overview[J]. International Journal of Data Analysis Techniques and Strategies, 2011,3(3):281-299. doi: 10.1504/IJDATS.2011.041335
[13]	Kök A G, Fisher M L, Vaidyanathan R. Assortment planning: review of literature and industry practice[M]// Retail Supply Chain Management. 2015: 175-236.
[14]	Drucker H. Improving regressors using boosting techniques[C]// 14th International Conference on Machine Learning. 1997: 107-115.
[15]	Bradley A P. The use of the area under the ROC curve in the evaluation of machine learning algorithms[J]. Pattern Recognition, 1997,30(7):1145-1159. doi: 10.1016/S0031-3203(96)00142-2
[16]	Healy M J R. The use of $R^2$ as a measure of goodness of fit[J]. Journal of the Royal Statistical Society, 1984,147(4):608-609.

Alternative demand forecasting considering product feature attribute

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 7

References 16

Related Articles 3

Recommended Articles

Metrics

Comments

[1]	XI Yinfei, LIU Zhongkai, YANG Peiyun, YU Ye, ZHANG Qi, LIU Zhiyuan. Travel demand forecast methods for Internet private hire vehicles [J]. Journal of Shanghai University（Natural Science Edition）, 2020, 26(3): 328-341.
[2]	CHEN Gaopan, XU Meihua, WANG Qi, GUO Aiying. Front-vehicle detection method based on monocular vision [J]. Journal of Shanghai University（Natural Science Edition）, 2019, 25(1): 56-65.
[3]	GAO Jun-jun1，TAN Chong-li1，LIU Yue2，YIN Ya-feng2. Demand Forecast Using Support Vector Machine for a Product Category [J]. Journal of Shanghai University（Natural Science Edition）, 2009, 15(1): 71-76.