Machine Learning Algorithms with Intermittent Demand Forecasting: An Application in Retail Apparel with Plenty of Predictors

Year 2021, Volume: 31 Issue: 2, 99 - 110, 30.06.2021

İlker Güven , Özer Uygun , Fuat Şimşir

https://doi.org/10.32710/tekstilvekonfeksiyon.809867

Cited By: 2

Abstract

Demand forecasting is a key factor for apparel retail stores to sustain their business, especially where there are variety of products and intermittent demand.
In this study, two of the most popular machine learning methods, random forest (RF) and k-nearest neighbour (KNN), have been used to forecast retail apparel’s intermittent demand. Numerous variables that may have an effect on the sales, have been taken into account one of which is defined as “special day” that might trigger intermittence in the demand. During the application of the forecast, four different datasets were used to provide reliability. 28 different variables were used to increase accuracy of the forecasting and experience of the behaviours of the algorithms. Root mean square error (RMSE) was used to evaluate performance of the methods and as a result of this study, RF showed better performance in all four datasets comparing to KNN.

Keywords

Intermittent demand, random forest, k-nearest neighbour, retail apparel, textile

Thanks

Thank you for your valuable time and effort to evaluate.

References

• 1. J. Huber and H. Stuckenschmidt, 2020. Daily retail demand forecasting using machine learning with emphasis on calendric special days. International Journal of Forecasting. vol. 36, no. 4. pp. 1420–1438. doi: 10.1016/j.ijforecast.2020.02.005.
• 2. İ. Güven and F. Şimşir, 2020. Demand forecasting with color parameter in retail apparel industry using artificial neural networks (ANN) and support vector machines (SVM) methods. Computers & Industrial Engineering. vol. 147. p. 106678. doi: 10.1016/j.cie.2020.106678.
• 3. M. Kück and M. Freitag, 2021. Forecasting of customer demands for production planning by local k - nearest neighbor models. International Journal of Production Economics. vol. 231. p. 107837. doi: 10.1016/j.ijpe.2020.107837.
• 4. C.-H. Wang and J.-Y. Chen, 2019. Demand forecasting and financial estimation considering the interactive dynamics of semiconductor supply-chain companies. Computers & Industrial Engineering. vol. 138. p. 106104. doi: 10.1016/j.cie.2019.106104.
• 5. P. Vroman, M. Happiette, and B. Rabenasolo, 1998. Fuzzy Adaptation of the Holt–Winter Model for Textile Sales-forecasting. Journal of the Textile Institute. vol. 89, no. 1. pp. 78–89. doi: 10.1080/00405009808658668.
• 6. S. Thomassey, M. Happiette, N. Dewaele, and J. M. Castelain, 2002. A Short and Mean Term Forecasting System Adapted to Textile Items’ Sales. Journal of the Textile Institute. vol. 93, no. 3. pp. 95–104. doi: 10.1080/00405000208658360.
• 7. C. Li and A. Lim, 2018. A greedy aggregation–decomposition method for intermittent demand forecasting in fashion retailing. European Journal of Operational Research. vol. 269, no. 3. pp. 860–869. doi: 10.1016/j.ejor.2018.02.029.
• 8. K. Nikolopoulos, 2020. We need to talk about intermittent demand forecasting. European Journal of Operational Research. doi: 10.1016/j.ejor.2019.12.046.
• 9. S. Beheshti-Kashi, H. R. Karimi, K.-D. Thoben, M. Lütjen, and M. Teucke, 2015. A survey on retail sales forecasting and prediction in fashion markets. Systems Science & Control Engineering. vol. 3, no. 1. pp. 154–161. doi: 10.1080/21642583.2014.999389.
• 10. S. Ma and R. Fildes, 2021. Retail sales forecasting with meta-learning. European Journal of Operational Research. vol. 288, no. 1. pp. 111–128. doi: 10.1016/j.ejor.2020.05.038.
• 11. A. L. D. Loureiro, V. L. Miguéis, and L. F. M. da Silva, 2018. Exploring the use of deep neural networks for sales forecasting in fashion retail. Decision Support Systems. vol. 114. pp. 81–93. doi: 10.1016/j.dss.2018.08.010.
• 12. P.-S. Yu, T.-C. Yang, S.-Y. Chen, C.-M. Kuo, and H.-W. Tseng, 2017. Comparison of random forests and support vector machine for real-time radar-derived rainfall forecasting. Journal of Hydrology. vol. 552. pp. 92–104. doi: 10.1016/j.jhydrol.2017.06.020.
• 13. R. Cui, S. Gallino, A. Moreno, and D. J. Zhang, 2018. The Operational Value of Social Media Information. Production and Operations Management. vol. 27, no. 10. pp. 1749–1769. doi: 10.1111/poms.12707.
• 14. F. Martínez, M. P. Frías, M. D. Pérez-Godoy, and A. J. Rivera, 2018. Dealing with seasonality by narrowing the training set in time series forecasting with k NN. Expert Systems with Applications. vol. 103. pp. 38–48. doi: 10.1016/j.eswa.2018.03.005.
• 15. D. V Souza et al., 2019. k -Nearest Neighbor Regression in the Estimation of Tectona G randis Trunk Volume in the State of Pará, Brazil. Journal of Sustainable Forestry. vol. 38, no. 8. pp. 755–768. doi: 10.1080/10549811.2019.1607391.
• 16. M. Ghiassi, F. Fa’al, and A. Abrishamchi, 2017. Large metropolitan water demand forecasting using DAN2, FTDNN, and KNN models: A case study of the city of Tehran, Iran. Urban Water Journal. vol. 14, no. 6. pp. 655–659. doi: 10.1080/1573062X.2016.1223858.
• 17. N. J. Johannesen, M. Kolhe, and M. Goodwin, 2019. Relative evaluation of regression tools for urban area electrical energy demand forecasting. Journal of Cleaner Production. vol. 218. pp. 555–564. doi: 10.1016/j.jclepro.2019.01.108.
• 18. T. Fang and R. Lahdelma, 2016. Evaluation of a multiple linear regression model and SARIMA model in forecasting heat demand for district heating system. Applied Energy. vol. 179. pp. 544–552. doi: 10.1016/j.apenergy.2016.06.133.
• 19. M. Sebri, 2016. Forecasting urban water demand: A meta-regression analysis. Journal of Environmental Management. vol. 183. pp. 777–785. doi: 10.1016/j.jenvman.2016.09.032.
• 20. F.-L. Chu, 2014. Using a logistic growth regression model to forecast the demand for tourism in Las Vegas. Tourism Management Perspectives. vol. 12. pp. 62–67. doi: 10.1016/j.tmp.2014.08.003.
• 21. P. Ramos, N. Santos, and R. Rebelo, 2015. Performance of state space and ARIMA models for consumer retail sales forecasting. Robotics and Computer-Integrated Manufacturing. vol. 34. pp. 151–163. doi: 10.1016/j.rcim.2014.12.015.
• 22. W. Anggraeni, R. A. Vinarti, and Y. D. Kurniawati, 2015. Performance Comparisons between Arima and Arimax Method in Moslem Kids Clothes Demand Forecasting: Case Study. Procedia Computer Science. vol. 72. pp. 630–637. doi: 10.1016/j.procs.2015.12.172.
• 23. I. Khandelwal, R. Adhikari, and G. Verma, 2015. Time Series Forecasting Using Hybrid ARIMA and ANN Models Based on DWT Decomposition. Procedia Computer Science. vol. 48. pp. 173–179. doi: 10.1016/j.procs.2015.04.167.
• 24. L. A. Díaz-Robles et al., 2008. A hybrid ARIMA and artificial neural networks model to forecast particulate matter in urban areas: The case of Temuco, Chile. Atmospheric Environment. vol. 42, no. 35. pp. 8331–8340. doi: 10.1016/j.atmosenv.2008.07.020.
• 25. M. Khashei and M. Bijari, 2011. A novel hybridization of artificial neural networks and ARIMA models for time series forecasting. Applied Soft Computing. vol. 11, no. 2. pp. 2664–2675. doi: 10.1016/j.asoc.2010.10.015.
• 26. W. J. Wang and Q. Xu, 2014. A Bayesian Combination Forecasting Model for Retail Supply Chain Coordination. Journal of Applied Research and Technology. vol. 12, no. 2. pp. 315–324. doi: 10.1016/S1665-6423(14)72347-8.
• 27. A. Kulshrestha, V. Krishnaswamy, and M. Sharma, 2020. Bayesian BILSTM approach for tourism demand forecasting. Annals of Tourism Research. vol. 83. p. 102925. doi: 10.1016/j.annals.2020.102925.
• 28. F.-L. Chu, 2008. A fractionally integrated autoregressive moving average approach to forecasting tourism demand. Tourism Management. vol. 29, no. 1. pp. 79–88. doi: 10.1016/j.tourman.2007.04.003.
• 29. K. Nakade and Y. Aniyama, 2019. Bullwhip Effect of Weighted Moving Average Forecast under Stochastic Lead Time. IFAC-PapersOnLine. vol. 52, no. 13. pp. 1277–1282. doi: 10.1016/j.ifacol.2019.11.374.
• 30. Z. Michna, S. M. Disney, and P. Nielsen, 2020. The impact of stochastic lead times on the bullwhip effect under correlated demand and moving average forecasts. Omega. vol. 93. p. 102033. doi: 10.1016/j.omega.2019.02.002.
• 31. G. Sbrana and A. Silvestrini, 2019. Random switching exponential smoothing: A new estimation approach. International Journal of Production Economics. vol. 211. pp. 211–220. doi: 10.1016/j.ijpe.2019.01.038.
• 32. T. M. Dantas and F. L. Cyrino Oliveira, 2018. Improving time series forecasting: An approach combining bootstrap aggregation, clusters and exponential smoothing. International Journal of Forecasting. vol. 34, no. 4. pp. 748–761. doi: 10.1016/j.ijforecast.2018.05.006.
• 33. G. Sbrana and A. Silvestrini, 2013. Forecasting aggregate demand: Analytical comparison of top-down and bottom-up approaches in a multivariate exponential smoothing framework. International Journal of Production Economics. vol. 146, no. 1. pp. 185–198. doi: 10.1016/j.ijpe.2013.06.022.
• 34. R. Tsaur, 2009. Seasonal forecasting of a decomposed fuzzy exponential smoothing model using grey estimated values. Journal of the Chinese Institute of Engineers. vol. 32, no. 1. pp. 17–31. doi: 10.1080/02533839.2009.9671479.
• 35. Y. Zhu, W. XU, G. Luo, H. Wang, J. Yang, and W. Lu, 2020. Random Forest enhancement using improved Artificial Fish Swarm for the medial knee contact force prediction. Artificial Intelligence in Medicine. vol. 103. p. 101811. doi: 10.1016/j.artmed.2020.101811.
• 36. E. Izquierdo-Verdiguier and R. Zurita-Milla, 2020. An evaluation of Guided Regularized Random Forest for classification and regression tasks in remote sensing. International Journal of Applied Earth Observation and Geoinformation. vol. 88. p. 102051. doi: 10.1016/j.jag.2020.102051.
• 37. X. Zhou, P. Lu, Z. Zheng, D. Tolliver, and A. Keramati, 2020. Accident Prediction Accuracy Assessment for Highway-Rail Grade Crossings Using Random Forest Algorithm Compared with Decision Tree. Reliability Engineering & System Safety. vol. 200. p. 106931. doi: 10.1016/j.ress.2020.106931.
• 38. J. E. Pesantez, E. Z. Berglund, and N. Kaza, 2020. Smart meters data for modeling and forecasting water demand at the user-level. Environmental Modelling & Software. vol. 125. p. 104633. doi: 10.1016/j.envsoft.2020.104633.
• 39. M. Fernández-Delgado, E. Cernadas, S. Barro, and D. Amorim, 2014. Do we Need Hundreds of Classifiers to Solve Real World Classification Problems? Journal of Machine Learning Research. vol. 15, no. 90. pp. 3133–3181. [Online]. Available: http://jmlr.org/papers/v15/delgado14a.html.
• 40. M. Aghaabbasi, Z. A. Shekari, M. Z. Shah, O. Olakunle, D. J. Armaghani, and M. Moeinaddini, 2020. Predicting the use frequency of ride-sourcing by off-campus university students through random forest and Bayesian network techniques. Transportation Research Part A: Policy and Practice. vol. 136. pp. 262–281. doi: 10.1016/j.tra.2020.04.013.
• 41. X. Wang, K. An, L. Tang, and X. Chen, 2015. Short Term Prediction of Freeway Exiting Volume Based on SVM and KNN. International Journal of Transportation Science and Technology. vol. 4, no. 3. pp. 337–352. doi: 10.1260/2046-0430.4.3.337.
• 42. E. Mangalova and E. Agafonov, 2014. Wind power forecasting using the k-nearest neighbors algorithm. International Journal of Forecasting. vol. 30, no. 2. pp. 402–406. doi: 10.1016/j.ijforecast.2013.07.008.
• 43. L. A. Teixeira and A. L. I. de Oliveira, 2010. A method for automatic stock trading combining technical analysis and nearest neighbor classification. Expert Systems with Applications. vol. 37, no. 10. pp. 6885–6890. doi: 10.1016/j.eswa.2010.03.033.
• 44. Z. Pang, F. Niu, and Z. O’Neill, 2020. Solar radiation prediction using recurrent neural network and artificial neural network: A case study with comparisons. Renewable Energy. vol. 156. pp. 279–289. doi: 10.1016/j.renene.2020.04.042.
• 45. H. Tang, P. Dong, and Y. Shi, 2019. A new approach of integrating piecewise linear representation and weighted support vector machine for forecasting stock turning points. Applied Soft Computing. vol. 78. pp. 685–696. doi: 10.1016/j.asoc.2019.02.039.