Forecasting Monthly Sales of White Goods Using Hybrid Arimax and Ann Models

Year 2018, Volume: 22 Issue: 4, 2603 - 2617, 31.12.2018

Melih Yücesan

Abstract

In
this study, hybrid ARIMAX-ANN and SARIMAX-ANN sales forecasting models are proposed
for a white goods wholesaler. White goods industry which is one of the durable
goods sub-sector includes washing machines, dishwashers, refrigerators and
small home appliances. In making forecasts, 46-month sales data of a white
goods wholesaler are used. Factors influencing sales such as exchange rate,
holidays, consumer confidence index (CCI), producer price index (PPI) and
residential sales of the region are used as explanatory variables. The study
contributes to the current literature by some aspects. First, there is no
attempts applying the ARIMAX-ANN and SARIMAX-ANN hybrid models to forecast
sales data in white goods industry. Second, the hybrid models combine the
advantages of times series and ANN models. ARIMAX models are insufficient to solve
complex nonlinear problems. On the other hand, ANN is sufficient to explain
nonlinear relationships. On conclusion, use of hybrid models can increase the
accuracy of the models.

Keywords

ARIMAX, SARIMAX, Aylık satışlar, Beyaz eşya

Forecasting Monthly Sales of White Goods Using Hybrid Arimax and Ann Models

Abstract

In this study, hybrid ARIMAX-ANN and SARIMAX-ANN sales
forecasting models are proposed for a white goods wholesaler. White goods industry
which is one of the durable goods sub-sector includes washing machines,
dishwashers, refrigerators and small home appliances. In making forecasts, 46-month
sales data of a white goods wholesaler are used. Factors influencing sales such
as exchange rate, holidays, consumer confidence index (CCI), producer price
index (PPI) and residential sales of the region are used as explanatory
variables. The study contributes to the current literature by some aspects.
First, there is no attempts applying the ARIMAX-ANN and SARIMAX-ANN hybrid
models to forecast sales data in white goods industry. Second, the hybrid
models combine the advantages of times series and ANN models. ARIMAX models are
insufficient to solve complex nonlinear problems. On the other hand, ANN is
sufficient to explain nonlinear relationships. On conclusion, use of hybrid
models can increase the accuracy of the models.

Keywords

ARIMAX, SARIMAX, Monthly sales, White goods

References

• Aburto, L., & Weber, R. (2007). A sequential hybrid forecasting system for demand prediction. Machine Learning and Data Mining in Pattern Recognition, 518-532.
• Alon, I,; Qi, M,; Sadowski, R. J. 2001: Forecasting aggregate retail sales: A comparison of artificial neural networks and traditional methods. Journal of retailing and consumer services, 8(3): 147-156
• Alptekin, N. (2010). Analitik ağ süreci yaklaşımı ile Türkiye’de beyaz eşya sektörünün pazar payı tahmini
• Anggraeni, W., Vinarti, R. A., & Kurniawati, Y. D. (2015). Performance Comparisons Between Arima and Arimax Method in Moslem Kids Clothes Demand Forecasting: Case Study. Procedia Computer Science, 72, 630-637.
• Areekul, P., Senjyu, T., Toyama, H., & Yona, A. (2010). Notice of violation of IEEE publication principles a hybrid ARIMA and neural network model for short-term price forecasting in deregulated market. IEEE Transactions on Power Systems, 25(1), 524-530.
• Armstrong J. Scott, (2001), ―Combining Forecasts. Principles of Forecasting‖, A Handbook for Researchers and Practitioners, Norwell, MA: Lower Academic Publishers.
• Arunraj, N. S., & Ahrens, D. (2015). A hybrid seasonal autoregressive integrated moving average and quantile regression for daily food sales forecasting. International Journal of Production Economics, 170, 321-335.
• Arya, P.; Paul, R. K.; Kumar, A.; Singh, K. N.; Sivaramne, N.; Chaudhary, P., 2015: Predicting pest population using weather variables: an ARIMAX time series framework. International Journal of Agricultural and Statistics Sciences, 11(2), 381-386.
• Bierens, H. J. (1987). ARMAX model specification testing, with an application to unemployment in the Netherlands. Journal of Econometrics, 35(1), 161-190.
• Chang, P. C., & Lai, K. R. (2005, May). Combining SOM and fuzzy rule base for sale forecasting in printed circuit board industry. In International Symposium on Neural Networks (pp. 947-954). Springer, Berlin, Heidelberg.
• Díaz-Robles, L. A., Ortega, J. C., Fu, J. S., Reed, G. D., Chow, J. C., Watson, J. G., & Moncada-Herrera, J. A. (2008). A hybrid ARIMA and artificial neural networks model to forecast particulate matter in urban areas: The case of Temuco, Chile. Atmospheric Environment, 42(35), 8331-8340. Economics, 43(2), 175-192.
• Doganis, P., Aggelogiannaki, E., & Sarimveis, H. (2008). A combined model predictive control and time series forecasting framework for production-inventory systems. International Journal of Production Research, 46(24), 6841-6853.
• Espinoza, M., Joye, C., Bemans, R., De Moor, B., 2005. Short-term load forecasting, profile identification and customer segmentation: A methodology based on periodic time series. IEEE Transactions on Power Systems 20 (3), 1622–1630.
• EViews 10 tutorial. (2017). http://www.eviews.com/Learning/basics.html, access (26.03.2018)
• Gahirwal, M. (2013). Inter Time series sales forecasting. arXiv preprint arXiv:1303.0117.
• Gilliland, M., & Sglavo, U. (2010). Worst Practices in Business Forecasting. Analytics, 12–17.
• Gul, M., & Guneri, A. F. (2016). Planning the future of emergency departments: Forecasting ED patient arrivals by using regression and neural network models. International Journal of Industrial Engineering, 23(2), 137-154.
• Hahn, H., Meyer-Nieberg, S., & Pickl, S. (2009). Electric load forecasting methods: Tools for decision making. European journal of operational research, 199(3), 902-907.
• Herbig, P. a., Milewicz, J., & Golden, J. E. (1993). The do’s and don'ts of sales forecasting. Industrial Marketing Management, 22(1), 49–57.
• Karaatlı, M., Helvacıoğlu, Ö. C., Ömürbek, N., & Tokgöz, G. (2012). Yapay Sinir Ağları Yöntemi İle Otomobil Satış Tahmini. Uluslararası Yönetim İktisat ve İşletme Dergisi, 8(17), 87-100.
• Murlidharan, V., & Menezes, B. (2013). Frequent pattern mining-based sales forecasting. Opsearch, 50(4), 455-474.
• Ni, Y., & Fan, F. (2011). A two-stage dynamic sales forecasting model for the fashion retail. Expert Systems with Applications, 38(3), 1529-1536.
• Qin, L. X., & Shi, Z. Z. (2006). Efficiently mining association rules from time series. International Journal of Information Technology, 12(4), 30-38.
• Ramos, P., Santos, N., & Rebelo, R. (2015). Performance of state space and ARIMA models for consumer retail sales forecasting. Robotics and computer-integrated manufacturing, 34, 151-163.Republic of Turkey Prime Ministry Investment Support and Promotion Agency, 2010, Turkey and Electronic Appliances Sector Report retrieve from: ww.iso.org.tr/file/BEYAZ.ESYA.ELEKTRONIK.SEKTORU_INVEST-469.pdf
• Shukla, M., & Jharkharia, S. (2013). Applicability of ARIMA models in wholesale vegetable market: an investigation. International Journal of Information Systems and Supply Chain Management (IJISSCM), 6(3), 105-119.
• Stevenson, W. J., & Hojati, M. (2007). Operations management (Vol. 8). Boston: McGraw-Hill/Irwin.
• Suhartono, L. MH, & Prastyo, DD,(2015),“Two levels ARIMAX and Regression Models for Forecasting Time Series Data with Calendar Variation Effects”. In AIP Conference Proceedings (Vol. 1691, p. 050026).
• Sutthichaimethee, P., & Ariyasajjakorn, D. (2017). Forecasting energy consumption in short-term and long-term period by using arimax model in the construction and materials sector in thailand. Journal of Ecological Engineering, 18(4).
• Yucesan, M., Gul, M., & Celik, E. (2017). Application of Artificial Neural Networks Using Bayesian Training Rule in Sales Forecasting for Furniture Industry. Wood Industry/Drvna Industrija, 68(3).
• Yucesan M. (2018), Beyaz Eşya Sektöründe YSA, ARIMA ve ARIMAX Yöntemleriyle Satış Tahmini, Journal of Business Research (Submitted Manuscript)
• Zhang, G. P. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50, 159-175.