×

Iterative prediction-and-optimization for e-logistics distribution network design. (English) Zbl 1492.90020

Summary: The emergence of online retailers has brought new opportunities to the design of their distribution networks. Notably, for online retailers that do not operate offline stores, their target customers are more sensitive to the quality of logistic services, such as delivery speed and reliability. This paper is motivated by a leading online retailer for cosmetic products on Taobao.com that aimed to improve its logistics efficiency by redesigning its centralized distribution network into a multilevel one. The multilevel distribution network consists of a layer of primary facilities to hold stocks from suppliers and transshipment and a layer of secondary facilities to provide last-mile delivery. There are two major challenges of designing such a facility network. First, online customers can respond significantly to the change of logistics efficiency with the redesigned network, thereby rendering the network optimized under the original demand distribution suboptimal. Second, because online retailers have relatively small sales volumes and are very flexible in choosing facility locations, the facility candidate set can be large, causing the facility location optimization challenging to solve. To this end, we propose an iterative prediction-and-optimization strategy for distribution network design. Specifically, we first develop an artificial neural network (ANN) to predict customer demands, factoring in the logistic service quality given the network and the city-level purchasing power based on demographic statistics. Then, a mixed integer linear programming (MILP) model is formulated to choose facility locations with minimum transportation, facility setup, and package processing costs. We further develop an efficient two-stage heuristic for computing high-quality solutions to the MILP model, featuring an agglomerative hierarchical clustering algorithm and an expectation and maximization algorithm. Subsequently, the ANN demand predictor and two-stage heuristic are integrated for iterative network design. Finally, using a real-world data set, we validate the demand prediction accuracy and demonstrate the mutual interdependence between the demand and network design.
Summary of contribution: We propose an iterative prediction-and-optimization algorithm for multilevel distribution network design for e-logistics and evaluate its operational value for online retailers. We address the issue of the interplay between distribution network design and the demand distribution using an iterative framework. Further, combining the idea in operational research and data mining, our paper provides an end-to-end solution that can provide accurate predictions of online sales distribution, subsequently solving large-scale optimization problems for distribution network design problems.

MSC:

90B06 Transportation, logistics and supply chain management
90B80 Discrete location and assignment
68T07 Artificial neural networks and deep learning
90C11 Mixed integer programming
90C05 Linear programming
90C59 Approximation methods and heuristics in mathematical programming
90C39 Dynamic programming
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, Devin M, et al. (2016) Tensorflow: A system for large-scale machine learning. Proc. 12th USENIX Conf. Oper. Systems Design Implementation (OSDI 16) (USENIX Association, Berkeley, CA), 265-283.Google Scholar
[2] Abiodun OI, Jantan A, Omolara AE, Dada KV, Mohamed NA, Arshad H (2018) State-of-the-art in artificial neural network applications: A survey. Heliyon 4(11): e00938.Crossref, Google Scholar · doi:10.1016/j.heliyon.2018.e00938
[3] Alp O, Erkut E, Drezner Z (2003) An efficient genetic algorithm for the p-median problem. Ann. Oper. Res. 122(1-4):21-42.Crossref, Google Scholar · Zbl 1038.90046 · doi:10.1023/A:1026130003508
[4] Bohlmeijer E, Ten Klooster PM, Fledderus M, Veehof M, Baer R (2011) Psychometric properties of the five facet mindfulness questionnaire in depressed adults and development of a short form. Assessment 18(3):308-320.Crossref, Google Scholar · doi:10.1177/1073191111408231
[5] Boysen N, de Koster R, Weidinger F (2019) Warehousing in the e-commerce era: A survey. Eur. J. Oper. Res. 277(2):396-411.Crossref, Google Scholar · Zbl 1430.90065 · doi:10.1016/j.ejor.2018.08.023
[6] Bucko J, Kakalejčík L, Ferencová M (2018) Online shopping: Factors that affect consumer purchasing behaviour. Cogent Bus. Management 5(1):1-15.Crossref, Google Scholar · doi:10.1080/23311975.2018.1535751
[7] Chen C, Liu J, Li Q, Wang Y, Xiong H, Wu S (2017) Warehouse site selection for online retailers in inter-connected warehouse networks. Proc. 2017 IEEE Internat. Conf. Data Mining (ICDM) (IEEE, Piscataway, NJ), 805-810.Google Scholar
[8] Cheney W, Kincaid D (2009) Linear Algebra: Theory and Applications (Jones & Bartlett Learning, Burlington, MA).Google Scholar
[9] Chong AYL, Ch’ng E, Liu MJ, Li B (2017) Predicting consumer product demands via big data: The roles of online promotional marketing and online reviews. Internat. J. Production Res. 55(17):5142-5156.Crossref, Google Scholar · doi:10.1080/00207543.2015.1066519
[10] Contreras I, Cordeau JF, Laporte G (2011) Benders decomposition for large-scale uncapacitated hub location. Oper. Res. 59(6):1477-1490.Link, Google Scholar · Zbl 1242.90094
[11] Cui R, Li M, Li Q (2020) Value of high-quality logistics: Evidence from a clash between sf express and Alibaba. Management Sci. 66(9):3879-3902.Link, Google Scholar
[12] Do CB, Batzoglou S (2008) What is the expectation maximization algorithm? Nature Biotechnology 26(8):897-899.Crossref, Google Scholar · doi:10.1038/nbt1406
[13] Drucker H, Burges CJ, Kaufman L, Smola AJ, Vapnik V (1997) Support vector regression machines. Jordan MI, Petsche T, eds. Proc. 9th Internat. Conf. Neural Inform. Processing Systems (MIT Press, Cambridge, MA), 155-161.Google Scholar
[14] Duan Q, Liao TW (2013) Optimization of replenishment policies for decentralized and centralized capacitated supply chains under various demands. Internat. J. Production Econom. 142(1):194-204.Crossref, Google Scholar · doi:10.1016/j.ijpe.2012.11.004
[15] Fernie J, Sparks L (2018) Logistics and Retail Management: Emerging Issues and New Challenges in the Retail Supply Chain (Kogan Page Publishers, London).Google Scholar
[16] Ferreira KJ, Lee BHA, Simchi-Levi D (2015) Analytics for an online retailer: Demand forecasting and price optimization. Manufacturing Service Oper. Management 18(1):69-88.Link, Google Scholar
[17] Fischetti M, Ljubić I, Sinnl M (2017) Redesigning benders decomposition for large-scale facility location. Management Sci. 63(7):2146-2162.Link, Google Scholar
[18] Fisher ML (2004) The Lagrangian relaxation method for solving integer programming problems. Management Sci. 50(12, supplement):1861-1871.Link, Google Scholar
[19] Friedman JH (2001) Greedy function approximation: A gradient boosting machine. Ann. Statist. 29(5):1189-1232.Crossref, Google Scholar · Zbl 1043.62034 · doi:10.1214/aos/1013203451
[20] Gendron B, Khuong PV, Semet F (2016) A Lagrangian-based branch-and-bound algorithm for the two-level uncapacitated facility location problem with single-assignment constraints. Transportation Sci. 50(4):1286-1299.Link, Google Scholar
[21] Goodfellow I, Bengio Y, Courville A (2016) Deep Learning (MIT Press, Cambridge, MA).Google Scholar · Zbl 1373.68009
[22] Hassoun MH (1995) Fundamentals of Artificial Neural Networks (MIT Press, Cambridge, MA).Google Scholar · Zbl 0850.68271
[23] Hastie T, Tibshirani R (1996) Discriminant adaptive nearest neighbor classification and regression. Touretzky D, Mozer M, Hasselmo M, eds. Advances in Neural Information Processing Systems 8 (MIT Press, Cambridge, MA), 409-415.Google Scholar
[24] Hübner A, Holzapfel A, Kuhn H (2015) Operations management in multi-channel retailing: An exploratory study. Oper. Management Res. 8(3):84-100.Crossref, Google Scholar · doi:10.1007/s12063-015-0101-9
[25] Hübner A, Kuhn H, Wollenburg J (2016) Last mile fulfilment and distribution in omni-channel grocery retailing: A strategic planning framework. Internat. J. Retail Distribution Management 44(3):228-247.Crossref, Google Scholar · doi:10.1108/IJRDM-11-2014-0154
[26] Karlik B, Olgac AV (2011) Performance analysis of various activation functions in generalized MLP architectures of neural networks. Internat. J. Artificial Intelligence Expert Systems 1(4):111-122.Google Scholar
[27] Liaw A, Wiener M (2002) Classification and regression by random forest. R News 2(3):18-22.Google Scholar
[28] Lim SFW, Jin X, Srai JS (2018) Consumer-driven e-commerce: A literature review, design framework, and research agenda on last-mile logistics models. Internat. J. Physical Distribution Logist. Management 48(3):308-332.Crossref, Google Scholar · doi:10.1108/IJPDLM-02-2017-0081
[29] Lin Y (2019) E-urbanism: E-commerce, migration, and the transformation of Taobao villages in urban China. Cities 91:202-212.Crossref, Google Scholar · doi:10.1016/j.cities.2018.11.020
[30] Liu J, Sun L, Chen W, Xiong H (2016) Rebalancing bike sharing systems: A multi-source data smart optimization. Proc. 22nd ACM SIGKDD Internat. Conf. Knowledge Discovery Data Mining (ACM, New York), 1005-1014.Google Scholar
[31] Liu J, Li Q, Qu M, Chen W, Yang J, Xiong H, Zhong H, Fu Y (2015) Station site optimization in bike sharing systems. 2015 IEEE Internat. Conf. Data Mining (IEEE, Piscataway, NJ), 883-888.Google Scholar
[32] Loh WY (2008) Classification and regression tree methods. Encyclopedia Statist. Quality Reliability 1:315-323.Google Scholar
[33] Lu Y, Liu Z, Ma L (2020) Competing through logistics management: Studies on e-retailing in China. Supply Chain and Logistics Management: Concepts, Methodologies, Tools, and Applications (IGI Global, Hershey, PA), 1075-1094.Crossref, Google Scholar · doi:10.4018/978-1-7998-0945-6.ch050
[34] Masood S, Sharif M, Masood A, Yasmin M, Raza M (2015) A survey on medical image segmentation. Current Medical Imaging 11(1):3-14.Crossref, Google Scholar · doi:10.2174/157340561101150423103441
[35] Matarazzo TJ, Pakzad SN (2016) Stride for structural identification using expectation maximization: Iterative output-only method for modal identification. J. Engrg. Mechanics 142(4):04015109.Crossref, Google Scholar · doi:10.1061/(ASCE)EM.1943-7889.0000951
[36] Melo MT, Nickel S, Saldanha-Da-Gama F (2009) Facility location and supply chain management-A review. Eur. J. Oper. Res. 196(2):401-412.Crossref, Google Scholar · Zbl 1163.90341 · doi:10.1016/j.ejor.2008.05.007
[37] Michalewicz Z (2013) Genetic Algorithms+ Data Structures= Evolution Programs (Springer Science & Business Media, Berlin).Google Scholar
[38] Mukherjee I, Routroy S (2012) Comparing the performance of neural networks developed by using Levenberg-Marquardt and quasi-newton with the gradient descent algorithm for modelling a multiple response grinding process. Expert Systems Appl. 39(3):2397-2407.Crossref, Google Scholar · doi:10.1016/j.eswa.2011.08.087
[39] Ortiz-Astorquiza C, Contreras I, Laporte G (2018) Multi-level facility location problems. Eur J. Oper. Res. 267(3):791-805.Crossref, Google Scholar · Zbl 1403.90484 · doi:10.1016/j.ejor.2017.10.019
[40] Ortiz-Astorquiza C, Contreras I, Laporte G (2019) An exact algorithm for multilevel uncapacitated facility location. Transportation Sci. 53(4):1085-1106.Link, Google Scholar
[41] Panagiotelis A, Smith MS, Danaher PJ (2014) From Amazon to Apple: Modeling online retail sales, purchase incidence, and visit behavior. J. Bus. Econom. Statist. 32(1):14-29.Crossref, Google Scholar · doi:10.1080/07350015.2013.835729
[42] Ponce D, Contreras I, Laporte G (2020) E-commerce shipping through a third-party supply chain. Transportation Res. Part E: Logist. Transportation Rev. 140:101970.Crossref, Google Scholar · doi:10.1016/j.tre.2020.101970
[43] Ranganathan A (2004) The Levenberg-Marquardt algorithm. Tutorial LM Algorithm 11(1):101-110.Google Scholar
[44] Rao S, Goldsby TJ, Griffis SE, Iyengar D (2011) Electronic logistics service quality (e-lsq): Its impact on the customer’s purchase satisfaction and retention. J. Bus. Logist. 32(2):167-179.Crossref, Google Scholar · doi:10.1111/j.2158-1592.2011.01014.x
[45] Rardin RL, Rardin RL (1998) Optimization in Operations Research, vol. 166 (Prentice Hall, Upper Saddle River, NJ).Google Scholar
[46] Rohmer S, Gendron B (2020) A Guide to Parcel Lockers in Last Mile Distribution-Highlighting Challenges and Opportunities from an OR Perspective (CIRRELT, Montreal).Google Scholar
[47] Singh S, Rana R (2018) Effect of demographic factors on consumers’ perception of online shopping. Global J. Management Bus. Res. 18(6):6-E.Google Scholar
[48] Solomatine DP, Shrestha DL (2004) Adaboost.RT: A boosting algorithm for regression problems. 2004 IEEE Internat. Joint Conf. Neural Networks, vol. 2 (IEEE, Piscataway, NJ), 1163-1168.Google Scholar
[49] Song G, Zhan Y, Guo Y (2016) The effectiveness of online shopping characteristics and logistics service on satisfaction. 13th Internat. Conf. Service Systems Service Management (ICSSSM) (IEEE, Piscataway, NJ), 1-6.Google Scholar
[50] Speranza MG (2018) Trends in transportation and logistics. Eur. J. Oper. Res. 264(3):830-836.Crossref, Google Scholar · Zbl 1375.90039 · doi:10.1016/j.ejor.2016.08.032
[51] Subramanian N, Gunasekaran A, Yu J, Cheng J, Ning K (2014) Customer satisfaction and competitiveness in the Chinese e-retailing: Structural equation modeling (SEM) approach to identify the role of quality factors. Expert Systems Appl. 41(1):69-80.Crossref, Google Scholar · doi:10.1016/j.eswa.2013.07.012
[52] Wang G, Gunasekaran A, Ngai EW, Papadopoulos T (2016) Big data analytics in logistics and supply chain management: Certain investigations for research and applications. Internat. J. Production Econom. 176:98-110.Crossref, Google Scholar · doi:10.1016/j.ijpe.2016.03.014
[53] Wu CJ (1983) On the convergence properties of the EM algorithm. Ann. Statist. 11(1):95-103.Crossref, Google Scholar · Zbl 0517.62035 · doi:10.1214/aos/1176346060
[54] Xu D, Tian Y (2015) A comprehensive survey of clustering algorithms. Ann. Data Sci. 2(2):165-193.Crossref, Google Scholar · doi:10.1007/s40745-015-0040-1
[55] Yu H, Wilamowski BM (2011) Levenberg-Marquardt training. Wilamowski BM, Irwin JD, eds. The Industrial Electronics Handbook (CRC Press, Boca Raton), 12-1-12-16.Crossref, Google Scholar · doi:10.1201/b10604-15
[56] Yu J, Subramanian N, Ning K, Edwards D (2015) Product delivery service provider selection and customer satisfaction in the era of internet of things: A Chinese e-retailers’ perspective. Internat. J. Production Econom. 159:104-116.Crossref, Google Scholar · doi:10.1016/j.ijpe.2014.09.031
[57] Yu Y, Wang X, Zhong RY, Huang G (2017) E-commerce logistics in supply chain management: Implementations and future perspective in furniture industry. Indust. Management Data Systems 117(10):2263-2286.Crossref, Google Scholar · doi:10.1108/IMDS-09-2016-0398
[58] Zetina CA, Contreras I, Cordeau JF (2019a) Exact algorithms based on benders decomposition for multicommodity uncapacitated fixed-charge network design. Comput. Oper. Res. 111:311-324.Crossref, Google Scholar · Zbl 1458.90180 · doi:10.1016/j.cor.2019.07.007
[59] Zetina CA, Contreras I, Cordeau JF (2019b) Profit-oriented fixed-charge network design with elastic demand. Transportation Res. Part B: Methodological 127:1-19.Crossref, Google Scholar · doi:10.1016/j.trb.2019.06.004
[60] Zhang L, Suganthan PN (2016) A survey of randomized algorithms for training neural networks. Inform. Sci. 364:146-155.Crossref, Google Scholar · Zbl 1426.68299 · doi:10.1016/j.ins.2016.01.039
[61] Zhang C, Tian YX, Fan ZP, Liu Y, Fan LW (2020) Product sales forecasting using macroeconomic indicators and online reviews: A method combining prospect theory and sentiment analysis. Soft Comput. 24:6213-6226.Crossref, Google Scholar · Zbl 1489.91137 · doi:10.1007/s00500-018-03742-1
[62] Zhu F, Liu Q (2018) Competing with complementors: An empirical look at Amazon. com. Strategic Management J. 39(10):2618-2642.Crossref, Google Scholar · doi:10.1002/smj.2932
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.