Hybrid intelligent model for fashion sales forecasting based on discrete grey forecasting model and artificial neural network

doi:10.11772/j.issn.1001-9081.2016.12.3378

Abstract

Abstract: Fashion sales forecasting is very important for the retail industry and accurate sales forecasting can improve the final fashion sales profits greatly. The current fashion sales forecast data is limited and the data volatility makes it harder to accurately forecast. In order to solve the problems, a new hybrid intelligent prediction algorithm comprising Artificial Neural Network (ANN) and Discrete Grey forecasting Model (DGM(1,1)) was proposed. The Correlation Analysis (CA) was used to get important influence variables with large correlation and DGM(1,1)+ANN were used to forecast the sales data. Then the residual of real sales data and the forecasting results of DGM(1,1)+ANN was added into influence variables for forecasting the second residual by using ANN and adopting an idea of secondary residual. Finally, the experiments based on real data sets of fashion sales were conducted to evaluate the feasibility and accuracy of the proposed hybrid algorithm. The experimental results show that, in forecasting fashion sales data, the forecasting Mean Absolute Percent Error (MAPE) of the proposed algorithm is about 25%. The forecast accuracy has greatly improved, compared to AutoregRessive Integrated Moving Average model (ARIMA), Extended Extreme Learning Machine (EELM), DGM(1,1), DGM(1,1)+ANN algorithm, the average forecasting accuracy is improved about 8 percentage points. The proposed hybrid intelligent algorithm for fashion sales can be used for real-time sales forecasting and improve sales greatly.

Key words: fashion sales forecasting, neural network algorithm, Discrete Grey forecasting Model (DGM), Correlation Analysis (CA), AutoregRessive Integrated Moving Average model (ARIMA)

摘要： 时尚销售预测对零售领域十分重要，准确的销售情况预测有助于大幅度提高最终时尚销售利润。针对目前时尚销售预测数据量有限并且数据波动大导致难以进行准确预测的问题，提出了一种结合人工神经网络（ANN）算法和离散灰色预测模型（DGM（1，1））算法的混合智能预测算法。该算法通过关联度分析得到关联度大的影响变量，在利用DGM（1，1）+ANN预测之后，引入二次残差的思想，将实际销售数据与DGM（1，1）+ANN预测结果的残差加入影响变量利用ANN进行第二次残差预测。最后通过真实的时尚销售数据验证算法预测的可行性及准确性。实验结果表明，该算法在时尚销售数据的预测中，预测平均绝对百分误差（MAPE）在25%左右，预测性能优于自回归积分滑动平均模型（ARIMA）、扩展极限学习机（EELM）、DGM（1，1）、DGM（1，1）+ANN算法，相较于以上几种算法平均预测精度大约提高8个百分点。所提混合智能算法可用于时尚销售即时预测，且能够大幅度提高销售的效益。

关键词: 时尚销售预测, 神经网络算法, 离散灰色模型, 关联度分析, 自回归积分滑动平均模型

CLC Number:

TP183

LIU Weixiao. Hybrid intelligent model for fashion sales forecasting based on discrete grey forecasting model and artificial neural network[J]. Journal of Computer Applications, 2016, 36(12): 3378-3384.

刘卫校. 基于离散灰色预测模型与人工神经网络混合智能模型的时尚销售预测[J]. 计算机应用, 2016, 36(12): 3378-3384.

References

[1] XIA M, WONG W K. A seasonal discrete grey forecasting model for fashion retailing[J]. Knowledge-Based Systems, 2014, 57(2):119-126.
[2] CHASE C W. Ways to improve sales forecasts[J]. The Journal of Business Forecasting Methods & Systems, 1993, 12(3):15-17.
[3] ADYA M, COLLOPY F. How effective are neural networks at forecasting and prediction? A review and evaluation[J]. Journal of Forecasting, 1998, 17(5/6):481-495.
[4] BODYANSKIY Y, POPOV S. Neural network approach to forecasting of quasiperiodic financial time series[J]. European Journal of Operational Research, 2006, 175(3):1357-1366.
[5] STUBBINGS P, VIRGINAS B, OWUSU G, et al. Modular neural networks for recursive collaborative forecasting in the service chain[J]. Knowledge-Based Systems, 2008, 21(6):450-457.
[6] HUARNG K, YU T H. Ratio-based lengths of intervals to improve fuzzy time series forecasting[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B:Cybernetics, 2006, 36(2):328-340.
[7] LI S Y, CHENG Y C. Deterministic fuzzy time series model for forecasting enrollments[J]. Computers & Mathematics with Applications, 2007, 53(12):1904-1920.
[8] CHANG P C, LIU C H, FAN C Y, et al. Data clustering and fuzzy neural network for sales forecasting in printed circuit board industry[C]//CIDM 2007:Proceedings of the 2007 IEEE Symposium on Computational Intelligence and Data Mining.Piscataway, NJ:IEEE, 2007:107-113..
[9] WONG W, BAI E, CHU A W C. Adaptive time-variant models for fuzzy-time-series forecasting[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B:Cybernetics, 2010, 40(6):1531-1542.
[10] ZHANG G P. Time series forecasting using a hybrid ARIMA and neural network model[J]. Neurocomputing, 2003, 50(1):159-175.
[11] SUN Z L, CHOI T M, AU K F, et al. Sales forecasting using extreme learning machine with applications in fashion retailing[J]. Decision Support Systems, 2008, 46(1):411-419.
[12] SUN Z L, AU K F, CHOI T M. A neuro-fuzzy inference system through integration of fuzzy logic and extreme learning machines[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B:Cybernetics, 2007, 37(5):1321-1331.
[13] WONG W K, GUO Z X. A hybrid intelligent model for medium-term sales forecasting in fashion retail supply chains using extreme learning machine and harmony search algorithm[J]. International Journal of Production Economics, 2010, 128(2):614-624.
[14] HSU C C, CHEN C Y. Applications of improved grey prediction model for power demand forecasting[J]. Energy Conversion and Management, 2003, 44(14):2241-2249.
[15] 谢乃明,刘思峰.离散GM(1,1)模型与灰色预测模型建模机理[J].系统工程理论与实践,2005,25(1):93-99.(XIE N M, LIU S F. Discrete GM (1, 1) and mechanism of grey forecasting model[J].Systems Engineering-Theory & Practice, 2005, 25(1):93-99.)
[16] 任柏青.基于关系数据库的领域本体构建方法的研究与实践[D].北京:北京邮电大学,2009:34-72.(REN B Q. Research and practice on a mechanism of generating ontology based on relational database[D]. Beijing:Beijing University of Posts and Telecommunications, 2009:34-72.)
[17] 王珊,张延松.面向并发OLAP的数据库查询处理方法:中国,201210113665.4[P].2012-04-17.(WANG S, ZHANG Y S. Query processing method for paralleled OLAP database:China, 201210113665.4[P]. 2012-04-17.)
[18] 张平平,伍俊良,胡兴凯,等.Gerschgorin圆盘的分离[J].西南师范大学学报(自然科学版),2011,36(3):1-3.(ZHANG P P, WU J L, HU X K, et al. On the separation of Gerschgorin circular discs[J]. Journal of Southwest China Normal University (Natural Science Edition), 2011, 36(3):1-3.)
[19] WANG C, FAN J. Medical relation extraction with manifold models[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA:Association for Computational Linguistics, 2014:828-838.
[20] 姚富强.通信抗干扰工程与实践[M].北京:电子工业出版社,2008:7-8.(YAO F Q. Communication Anti-jamming Engineering and Practice[M]. Beijing:Publishing House of Electronics Industry, 2008:7-8.)