Improved Demand Forecasting of a Retail Store Using a Hybrid Machine Learning Model
DOI:
https://doi.org/10.13052/jgeu0975-1416.1212Keywords:
Demand forecasting, inventory optimisation, machine learning, hybrid model, price elasticityAbstract
Accurate demand forecasting is a competitive advantage for all supply chain components, including retailers. Approaches like naïve, moving average, weighted average, and exponential smoothing are commonly used to forecast demand. However, these simple approaches may lead to higher inventory and lost sales costs when the trend in demand is non-linear. Additionally, price strongly influences demand, and we can’t neglect the impact of price on demand. Similarly, the demand for a stock keeping unit (SKU) depends on the price of the competitor for the same SKU and the price of the competitive SKU. We thus propose a demand prediction model that considers historical demand data and the SKU price to forecast the demand. Our approach uses different machine-learning regressor algorithms and identifies the best machine-learning algorithm for the SKU with the lowest forecasting error. We further extend the forecasting model by training a hybrid model from the best two regression algorithms individually for each SKU. Forecasting error minimisation is the driving criterion for our literature. We evaluated the approach on 1000 SKUs, and the result showed that the Random Forest is the best-performing regressor algorithm with the lowest mean absolute percentage error (MAPE) of 8%. Furthermore, the hybrid model resulted in a lower inventory and lost sales cost with a MAPE of 7.74%. Overall, our proposed hybrid demand forecasting model can help retailers make informed decisions about inventory management, leading to improved operational efficiency and profitability.
Downloads
References
Luis Aburto, Richard Weber, Improved supply chain management based on hybrid demand forecasts, Applied Soft Computing, Volume 7, Issue 1, 2007, Pages 136–144, ISSN 1568-4946, https://doi.org/10.1016/j.asoc.2005.06.001. (https://www.sciencedirect.com/science/article/pii/S1568494605000311).
Sushil Punia, Konstantinos Nikolopoulos, Surya Prakash Singh, Jitendra K. Madaan and Konstantia Litsiou (2020) Deep learning with long short-term memory networks and random forests for demand forecasting in multi-channel retail, International Journal of Production Research, 58:16, 4964–4979, DOI: 10.1080/00207543.2020.1735666. (https://www.tandfonline.com/doi/full/10.1080/00207543.2020.1735666).
Massimo Pacella, Gabriele Papadia, Evaluation of deep learning with long short-term memory networks for time series forecasting in supply chain management, Procedia CIRP, Volume 99, 2021, Pages 604–609, ISSN 2212-8271, https://doi.org/10.1016/j.procir.2021.03.081. (https://www.sciencedirect.com/science/article/pii/S2212827121003711).
Nau R., Forecasting with moving averages (2014) Forecasting with Moving Averages, pp. 1–3, Cited 21 times. https://www.scopus.com/inward/record.uri?eid=2-s2.0-85043601148&partnerID=40&md5=c240c46f7140525d662649472cc1efdf. (https://www.scopus.com/record/display.uri?eid=2-s2.0-85043601148&origin=inward&txGid=40f299263bbaa50af2e32b1bb25dfb9e).
Liljana Ferbar Tratar, Blaž Mojškerc, Aleš Toman, Demand forecasting with four-parameter exponential smoothing, International Journal of Production Economics, Volume 181, Part A, 2016, Pages 162–173, ISSN 0925-5273, https://doi.org/10.1016/j.ijpe.2016.08.004. (https://www.sciencedirect.com/science/article/pii/S0925527316301839).
Mulhern, F. J., Williams, J. D., and Leone, R. P. (1998). Variability of brand price elasticities across retail stores: Ethnic, income, and brand determinants. Journal of Retailing, 74(3), 427–446. doi: 10.1016/s0022-4359(99)80103-1. (https://sci-hub.se/10.1016/s0022-4359(99)80103-1).
Kimitoshi Sato, Katsushige Sawaki, A continuous-time dynamic pricing model knowing the competitor’s pricing strategy, European Journal of Operational Research, Volume 229, Issue 1, 2013, Pages 223–229, ISSN 0377-2217, https://doi.org/10.1016/j.ejor.2013.02.022. (https://www.sciencedirect.com/science/article/pii/S0377221713001550).
Sethuraman, R., Srinivasan, V., and Kim, D. (1999). Asymmetric and Neighborhood Cross-Price Effects: Some Empirical Generalizations. Marketing Science, 18(1), 23–41. http://www.jstor.org/stable/193249. (Asymmetric and Neighborhood Cross-Price Effects: Some Empirical Generalizations on JSTOR).
Kris Johnson Ferreira, Bin Hong Alex Lee, David Simchi-Levi (2015) Analytics for an Online Retailer: Demand Forecasting and Price Optimization. Manufacturing & Service Operations Management 18(1): 69–88. (https://doi.org/10.1287/msom.2015.0561).
Yue, Liu et al. ‘Product Life Cycle Based Demand Forecasting by Using Artificial Bee Colony Algorithm Optimized Two-stage Polynomial Fitting’. 1 Jan. 2016 : 825–836. (https://ip.ios.semcs.net/articles/journal-of-intelligent-and-fuzzy-systems/ifs169014).
Jakob Huber, Heiner Stuckenschmidt, Daily retail demand forecasting using machine learning with emphasis on calendric special days, International Journal of Forecasting, Volume 36, Issue 4, 2020, Pages 1420–1438, ISSN 0169-2070, https://doi.org/10.1016/j.ijforecast.2020.02.005. (https://www.sciencedirect.com/science/article/pii/S0169207020300224).
Silaparasetti, Teja, Das Adhikari, Nimai, Domakonda, Nishanth, Garg, Rajat and Gupta, Gaurav. (2017). An Intelligent Approach to Demand Forecasting. (https://www.researchgate.net/publication/327225380_An_Intelligent_Approach_to_Demand_Forecasting).
Yunishafira, A. (2018). Determining the Appropriate Demand Forecasting Using Time Series Method: Study Case at Garment Industry in Indonesia. KnE Social Sciences, 3(10), 553–564. https://doi.org/10.18502/kss.v3i10.3156. (https://knepublishing.com/index.php/Kne-Social/article/view/3156).
Ravinder, Handanhal. (2016). Determining The Optimal Values Of Exponential Smoothing Constants – Does Solver Really Work?. American Journal of Business Education (AJBE). 9. 39. DOI: 10.19030/ajbe.v9i1.9574. (https://files.eric.ed.gov/fulltext/EJ1054363.pdf).
Elcio Tarallo, Getúlio K. Akabane, Camilo I. Shimabukuro, Jose Mello, Douglas Amancio, Machine Learning in Predicting Demand for Fast-Moving Consumer Goods: An Exploratory Research, IFAC-PapersOnLine, Volume 52, Issue 13, 2019, Pages 737–742, ISSN 2405–8963, https://doi.org/10.1016/j.ifacol.2019.11.203. (https://www.sciencedirect.com/science/article/pii/S240589631931153X).
Real Carbonneau, Kevin Laframboise, Rustam Vahidov, Application of machine learning techniques for supply chain demand forecasting, European Journal of Operational Research, Volume 184, Issue 3, 2008, Pages 1140–1154, ISSN 0377-2217, https://doi.org/10.1016/j.ejor.2006.12.004. (https://www.sciencedirect.com/science/article/pii/S0377221706012057).
Punit Gupta et al. 2021 J. Phys.: Conf. Ser. 1714 012003. DOI: 10.1088/1742-6596/1714/1/012003. (https://iopscience.iop.org/article/10.1088/1742-6596/1714/1/012003).
Luciano Viverit, Cindy Yoonjoung Heo, Luís Nobre Pereira, Guido Tiana, Application of machine learning to cluster hotel booking curves for hotel demand forecasting, International Journal of Hospitality Management, Volume 111, 2023, 103455, ISSN 0278-4319, https://doi.org/10.1016/j.ijhm.2023.103455. (https://www.sciencedirect.com/science/article/pii/S0278431923000294).
Smirnov, P and Sudakov, Vladimir. (2021). Forecasting new product demand using machine learning. Journal of Physics: Conference Series. 1925. 012033. DOI: 10.1088/1742-6596/1925/1/012033. (https://www.researchgate.net/publication/352614910_Forecasting_new_product_demand_using_machine_learning).
Kologlu, Yunus, Birinci, Hasan, Ilgaz, Sevde and Ozyilmaz, Burhan. (2018). A Multiple Linear Regression Approach For Estimating the Market Value of Football Players in Forward Position. (https://arxiv.org/ftp/arxiv/papers/1807/1807.01104.pdf).
Vaardini, Sindhu. (2015). An Assessment on the Building Demand Forecasting by Linear Regression Analysis. DOI: 10.13140/RG.2.1.1510.4484. (https://www.researchgate.net/publication/282003676_An_Assessment_on_the_Building_Demand_Forecasting_by_Linear_Regression_Analysis).
Martha Flores-Sosa, Ernesto León-Castro, José M. Merigó, Ronald R. Yager, Forecasting the exchange rate with multiple linear regression and heavy ordered weighted average operators, Knowledge-Based Systems, Volume 248, 2022, 108863, ISSN 0950-7051, https://doi.org/10.1016/j.knosys.2022.108863. (https://www.sciencedirect.com/science/article/pii/S0950705122004129).
Noa Ohana-Levi, Alon Ben-Gal, Sarel Munitz, Yishai Netzer, Grapevine crop evapotranspiration and crop coefficient forecasting using linear and non-linear multiple regression models, Agricultural Water Management, Volume 262, 2022, 107317, ISSN 0378-3774, https://doi.org/10.1016/j.agwat.2021.107317. (https://www.sciencedirect.com/science/article/pii/S0378377421005941).
Filippo Maria Ottaviani, Alberto De Marco, Multiple Linear Regression Model for Improved Project Cost Forecasting, Procedia Computer Science, Volume 196, 2022, Pages 808–815, ISSN 1877-0509, https://doi.org/10.1016/j.procs.2021.12.079. (https://www.sciencedirect.com/science/article/pii/S1877050921023024).
Mutaz AlShafeey, Csaba Csáki, Evaluating neural network and linear regression photovoltaic power forecasting models based on different input methods, Energy Reports, Volume 7, 2021, Pages 7601–7614, ISSN 2352-4847, https://doi.org/10.1016/j.egyr.2021.10.125. (https://www.sciencedirect.com/science/article/pii/S2352484721011446)
G. Ciulla, A. D’Amico, Building energy performance forecasting: A multiple linear regression approach, Applied Energy, Volume 253, 2019, 113500, ISSN 0306-2619, https://doi.org/10.1016/j.apenergy.2019.113500. (https://www.sciencedirect.com/science/article/pii/S0306261919311742).
Aliyeh Kazemi, Amir Foroughi. A, Mahnaz Hosseinzadeh, A Multi-Level Fuzzy Linear Regression Model for Forecasting Industry Energy Demand of Iran, Procedia – Social and Behavioral Sciences, Volume 41, 2012, Pages 342–348, ISSN 1877-0428, https://doi.org/10.1016/j.sbspro.2012.04.039. (https://www.sciencedirect.com/science/article/pii/S1877042812009196).
Metin İfraz, Adnan Aktepe, Süleyman Ersöz, Tahsin Çetinyokuş, Demand forecasting of spare parts with regression and machine learning methods: Application in a bus fleet, Journal of Engineering Research, Volume 11, Issue 2, 2023, 100057, ISSN 2307-1877, https://doi.org/10.1016/j.jer.2023.100057. (https://www.sciencedirect.com/science/article/pii/S2307187723000585).
S. Thomas Ng, Martin Skitmore, Keung Fai Wong, Using genetic algorithms and linear regression analysis for private housing demand forecast, Building and Environment, Volume 43, Issue 6, 2008, Pages 1171–1184, ISSN 0360-1323, https://doi.org/10.1016/j.buildenv.2007.02.017. (https://www.sciencedirect.com/science/article/pii/S0360132307000923).
Sushil Punia, Sonali Shankar, Predictive analytics for demand forecasting: A deep learning-based decision support system, Knowledge-Based Systems, Volume 258, 2022, 109956, ISSN 0950-7051, https://doi.org/10.1016/j.knosys.2022.109956. (https://www.sciencedirect.com/science/article/pii/S0950705122010498).
Sunthornjittanon, Supichaya, “Linear Regression Analysis on Net Income of an Agrochemical Company in Thailand” (2015). University Honors Theses. Paper 131. https://doi.org/10.15760/honors.137. https://pdxscholar.library.pdx.edu/cgi/viewcontent.cgi?article=1156&context=honorstheses.
Ostertagova, Eva. (2012). Modelling Using Polynomial Regression. Procedia Engineering. 48. 500–506. DOI: 10.1016/j.proeng.2012.09.545. https://www.researchgate.net/publication/256089416_Modelling_Using_Polynomial_Regression/citation/download.
Chu, F.-L. (2004). Forecasting tourism demand: a cubic polynomial approach. Tourism Management, 25(2), 209–218. doi: 10.1016/s0261-5177(03)00086-4. https://sci-hub.se/10.1016/S0261-5177(03)00086-4.
Mahdi Abolghasemi, Eric Beh, Garth Tarr, Richard Gerlach, Demand forecasting in supply chain: The impact of demand volatility in the presence of promotion, Computers & Industrial Engineering, Volume 142, 2020, 106380, ISSN 0360-8352, https://doi.org/10.1016/j.cie.2020.106380. (https://www.sciencedirect.com/science/article/pii/S0360835220301145).
Galina Merkuryeva, Aija Valberga, Alexander Smirnov, Demand forecasting in pharmaceutical supply chains: A case study, Procedia Computer Science, Volume 149, 2019, Pages 3–10, ISSN 1877-0509, https://doi.org/10.1016/j.procs.2019.01.100. (https://www.sciencedirect.com/science/article/pii/S1877050919301061).
Jing Shi, Application of the model combining demand forecasting and inventory decision in feature-based newsvendor problem, Computers & Industrial Engineering, Volume 173, 2022, 108709, ISSN 0360-8352, https://doi.org/10.1016/j.cie.2022.108709. (https://www.sciencedirect.com/science/article/pii/S0360835222006970).
David L. Banks, Stephen E. Fienberg- Polynomial Regression in Encyclopedia of Physical Science and Technology (Third Edition), 2003. https://www.sciencedirect.com/topics/computer-science/polynomial-regression.
Loh, Wei-Yin. (2011). Classification and Regression Trees. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery. 1. 14–23. DOI: 10.1002/widm.8. https://www.researchgate.net/publication/227658748_Classification_and_Regression_Trees.
Kris Johnson Ferreira, Bin Hong Alex Lee, David Simchi-Levi Analytics for an Online Retailer: Demand Forecasting and Price Optimization. https://www.hbs.edu/ris/Publication%20Files/kris%20Analytics%20for%20an%20Online%20Retailer_6ef5f3e6-48e7-4923-a2d4-607d3a3d943c.pdf.
Ida Rezaei, Seyed Hossein Amirshahi, Ali Akbar Mahbadi, Utilizing support vector and kernel ridge regression methods in spectral reconstruction, Results in Optics, Volume 11, 2023, 100405, ISSN 2666-9501, https://doi.org/10.1016/j.rio.2023.100405. (https://www.sciencedirect.com/science/article/pii/S2666950123000573).
Congjun Rao, Yue Zhang, Jianghui Wen, Xinping Xiao, Mark Goh, Energy demand forecasting in China: A support vector regression-compositional data second exponential smoothing model, Energy, Volume 263, Part C, 2023, 125955, ISSN 0360-5442, https://doi.org/10.1016/j.energy.2022.125955. (https://www.sciencedirect.com/science/article/pii/S0360544222028419).
Chi-Jie Lu, Yen-Wen Wang, Combining independent component analysis and growing hierarchical self-organizing maps with support vector regression in product demand forecasting, International Journal of Production Economics, Volume 128, Issue 2, 2010, Pages 603–613, ISSN 0925-5273, https://doi.org/10.1016/j.ijpe.2010.07.004. (https://www.sciencedirect.com/science/article/pii/S092552731000229X).
A.A. Levis, L.G. Papageorgiou, Customer Demand Forecasting via Support Vector Regression Analysis, Chemical Engineering Research and Design, Volume 83, Issue 8, 2005, Pages 1009–1018, ISSN 0263-8762, https://doi.org/10.1205/cherd.04246. (https://www.sciencedirect.com/science/article/pii/S0263876205727945).
Wang Guanghui, Demand Forecasting of Supply Chain Based on Support Vector Regression Method, Procedia Engineering, Volume 29, 2012, Pages 280–284, ISSN 1877-7058, https://doi.org/10.1016/j.proeng.2011.12.707. (https://www.sciencedirect.com/science/article/pii/S1877705811065441)
Robin Singh Bhadoria, Manish Kumar Pandey, Pradeep Kundu, RVFR: Random vector forest regression model for integrated & enhanced approach in forest fires predictions, Ecological Informatics, Volume 66, 2021, 101471, ISSN 1574-9541, https://doi.org/10.1016/j.ecoinf.2021.101471. (https://www.sciencedirect.com/science/article/pii/S1574954121002624).
Sehoon Kim, Innovating knowledge and information for a firm-level automobile demand forecast system: A machine learning perspective, Journal of Innovation & Knowledge, Volume 8, Issue 2, 2023, 100355, ISSN 2444-569X, https://doi.org/10.1016/j.jik.2023.100355. (https://www.sciencedirect.com/science/article/pii/S2444569X23000513).
R.M. van Steenbergen, M.R.K. Mes, Forecasting demand profiles of new products, Decision Support Systems, Volume 139, 2020, 113401, ISSN 0167-9236, https://doi.org/10.1016/j.dss.2020.113401. (https://www.sciencedirect.com/science/article/pii/S0167923620301561).
Matthias Ulrich, Hermann Jahnke, Roland Langrock, Robert Pesch, Robin Senge, Distributional regression for demand forecasting in e-grocery, European Journal of Operational Research, Volume 294, Issue 3, 2021, Pages 831–842, ISSN 0377-2217, https://doi.org/10.1016/j.ejor.2019.11.029. (https://www.sciencedirect.com/science/article/pii/S0377221719309403).
Takashi Tanizaki, Tomohiro Hoshino, Takeshi Shimmura, Takeshi Takenaka, Restaurants store management based on demand forecasting, Procedia CIRP, Volume 88, 2020, Pages 580–583, ISSN 2212-8271, https://doi.org/10.1016/j.procir.2020.05.101. (https://www.sciencedirect.com/science/article/pii/S2212827120304236).
Abigail Bola Adetunji, Oluwatobi Noah Akande, Funmilola Alaba Ajala, Ololade Oyewo, Yetunde Faith Akande, Gbenle Oluwadara, House Price Prediction using Random Forest Machine Learning Technique, Procedia Computer Science, Volume 199, 2022, Pages 806–813, ISSN 1877-0509, https://doi.org/10.1016/j.procs.2022.01.100. (https://www.sciencedirect.com/science/article/pii/S1877050922001016).
D. Rohaan, E. Topan, C.G.M. Groothuis-Oudshoorn, Using supervised machine learning for B2B sales forecasting: A case study of spare parts sales forecasting at an after-sales service provider, Expert Systems with Applications, Volume 188, 2022, 115925, ISSN 0957-4174, https://doi.org/10.1016/j.eswa.2021.115925. (https://www.sciencedirect.com/science/article/pii/S0957417421012793).
Juan D. Díaz, Erwin Hansen, Gabriel Cabrera, A random walk through the trees: Forecasting copper prices using decision learning methods, Resources Policy, Volume 69, 2020, 101859, ISSN 0301-4207, https://doi.org/10.1016/j.resourpol.2020.101859. (https://www.sciencedirect.com/science/article/pii/S0301420720308904).
Yifei He, Chao Chen, Bin Li, Zili Zhang, Prediction of near-surface air temperature in glacier regions using ERA5 data and the random forest regression method, Remote Sensing Applications: Society and Environment, Volume 28, 2022, 100824, ISSN 2352-9385, https://doi.org/10.1016/j.rsase.2022.100824. (https://www.sciencedirect.com/science/article/pii/S235293852200132X).
Robin Singh Bhadoria, Manish Kumar Pandey, Pradeep Kundu, RVFR: Random vector forest regression model for integrated & enhanced approach in forest fires predictions, Ecological Informatics, Volume 66, 2021, 101471, ISSN 1574-9541, https://doi.org/10.1016/j.ecoinf.2021.101471. (https://www.sciencedirect.com/science/article/pii/S1574954121002624).
Seungmi Kwak, Jaehwang Kim, Hongsheng Ding, Xuesong Xu, Ruirun Chen, Jingjie Guo, Hengzhi Fu, Machine learning prediction of the mechanical properties of γ
-TiAl alloys produced using random forest regression model, Journal of Materials Research and Technology, Volume 18, 2022, Pages 520–530, ISSN 2238-7854, https://doi.org/10.1016/j.jmrt.2022.02.108. (https://www.sciencedirect.com/science/article/pii/S2238785422002800).
Mitra, A., Jain, A., Kishore, A. et al. A Comparative Study of Demand Forecasting Models for a Multi-Channel Retail Company: A Novel Hybrid Machine Learning Approach. Oper. Res. Forum 3, 58 (2022). https://doi.org/10.1007/s43069-022-00166-4. https://link.springer.com/article/10.1007/s43069-022-00166-4.
