Deep neural network; Hidden Markov model; Integrated estimation and optimization; Inventory; Partially observed data; Data-driven approach; Estimation and optimization; Hidden-Markov models; Newsvendor problem; Observed data; Optimization problems; Unobservable; Computer Science (all); Modeling and Simulation; Management Science and Operations Research; Information Systems and Management
Résumé :
[en] We consider a single-period inventory problem with random demand with both directly observable and unobservable features that impact the demand distribution. With the recent advances in data collection and analysis technologies, data-driven approaches to classical inventory management problems have gained traction. Specially, machine learning methods are increasingly being integrated into optimization problems. Although data-driven approaches have been developed for the newsvendor problem, they often consider learning from the available data and optimizing the system separate tasks to be performed in sequence. One of the setbacks of this approach is that in the learning phase, costly and cheap mistakes receive equal attention and, in the optimization phase, the optimizer is blind to the confidence of the learner in its estimates for different regions of the problem. To remedy this, we consider an integrated learning and optimization problem for optimizing a newsvendor's strategy facing a complex correlated demand with additional information about the unobservable state of the system. We give an algorithm based on integrating optimization, neural networks and hidden Markov models and use numerical experiments to show the efficiency of our method. In an empirical experiment, the method outperforms the best competitor benchmark by more than 27%, on average, in terms of the system cost. We give further analyses of the performance of the method using a set of numerical experiments.
Disciplines :
Production, distribution & gestion de la chaîne logistique
Auteur, co-auteur :
Pirayesh Neghab, Davood; Department of Mechanical and Industrial Engineering, Ryerson University, Toronto, Canada
Khayyati, Siamak ; Université de Liège - ULiège > HEC Liège Research > HEC Liège Research: Business Analytics & Supply Chain Mgmt ; College of Engineering, Koç University, Istanbul, Turkey
Karaesmen, Fikri ; College of Engineering, Koç University, Istanbul, Turkey
Langue du document :
Anglais
Titre :
An integrated data-driven method using deep learning for a newsvendor problem with unobservable features
Research leading to these results has received funding from the EU ECSEL Joint Undertaking under grant agreement no. 737459 (project Productive4.0) and from TUBITAK (217M145).Research leading to these results has received funding from the EU ECSEL Joint Undertaking under grant agreement no. 737459 (project Productive4.0) and from TUBITAK (217M145).
Arifoğlu, K., Özekici, S., Optimal policies for inventory systems with finite capacity and partially observed Markov-modulated demand and supply processes. European Journal of Operational Research 204:3 (2010), 421–438.
Arifoğlu, K., Özekici, S., Inventory management with random supply and imperfect information: A hidden Markov model. International Journal of Production Economics 134:1 (2011), 123–137.
Avci, H., Gokbayrak, K., Nadar, E., Structural results for average-cost inventory models with Markov-modulated demand and partial information. Production and Operations Management 29:1 (2020), 156–173.
Ban, G.-Y., Rudin, C., The big data newsvendor: Practical insights from machine learning. Operations Research 67:1 (2019), 90–108.
Bensoussan, A., Cakanyıldırım, M., Sethi, S.P., On the optimal control of partially observed inventory systems. Comptes Rendus Mathematique 341:7 (2005), 419–426.
Bensoussan, A., Çakanyıldırım, M., Sethi, S.P., A multiperiod newsvendor problem with partially observed demand. Mathematics of Operations Research 32:2 (2007), 322–344.
Bertsimas, D., Kallus, N., From predictive to prescriptive analytics. Management Science 66:3 (2020), 1025–1044.
Bertsimas, D., Thiele, A., A data-driven approach to newsvendor problems. Technical report, 2005, Massachusetts Institute of Technology, Cambridge, MA.
Besbes, O., Muharremoglu, A., On implications of demand censoring in the newsvendor problem. Management Science 59:6 (2013), 1407–1424.
Beyer, D., Sethi, S.P., Average cost optimality in inventory models with Markovian demands. Journal of Optimization Theory and Applications 92:3 (1997), 497–526.
Bhar, R., Hamori, S., Hidden Markov models: Applications to financial economics. vol. 40, 2004, Springer Science & Business Media.
Blinder, A.S., Maccini, L.J., The resurgence of inventory research: What have we learned?. Journal of Economic Surveys 5:4 (1991), 291–328.
Du, X., Cindy, L.Y., Hayes, D.J., Speculation and volatility spillover in the crude oil and agricultural commodity markets: A Bayesian analysis. Energy Economics 33:3 (2011), 497–503.
Efendigil, T., Önüt, S., Kahraman, C., A decision support system for demand forecasting with artificial neural networks and neuro-fuzzy models: A comparative analysis. Expert Systems with Applications 36:3 (2009), 6697–6707.
Feldman, R.M., A continuous review (s, s) inventory system in a random environment. Journal of Applied Probability 15:3 (1978), 654–659.
Gallego, G., Hu, H., Optimal policies for production/inventory systems with finite capacity and Markov-modulated demand and supply processes. Annals of Operations Research 126:1 (2004), 21–41.
Gallego, G., Moon, I., The distribution free newsboy problem: Review and extensions. Journal of the Operational Research Society 44:8 (1993), 825–834.
Goel, S., Hofman, J.M., Lahaie, S., Pennock, D.M., Watts, D.J., Predicting consumer behavior with web search. Proceedings of the National Academy of Sciences, 2010.
Gruhl, D., Chavet, L., Gibson, D., Meyer, J., Pattanayak, P., Tomkins, A., Zien, J., How to build a WebFountain: An architecture for very large-scale text analytics. IBM Systems Journal 43:1 (2004), 64–77.
Gruhl, D., Guha, R., Kumar, R., Novak, J., Tomkins, A., The predictive power of online chatter. Proceedings of the Eleventh ACM SIGKDD International Conference on Knowledge Discovery in Data Mining, 2005, ACM, 78–87.
Gurney, K., An introduction to neural networks. 2018, CRC press.
Hamilton, J., Analysis of time series subject to changes in regime. Journal of Econometrics 45 (1990), 39–70.
He, B., Dexter, F., Macario, A., Zenios, S., The timing of staffing decisions in hospital operating rooms: Incorporating workload heterogeneity into the newsvendor problem. Manufacturing & Service Operations Management 14:1 (2012), 99–114.
Huang, G.-B., Learning capability and storage capacity of two-hidden-layer feedforward networks. IEEE Transactions on Neural Networks 14:2 (2003), 274–281.
Huh, W.T., Levi, R., Rusmevichientong, P., Orlin, J.B., Adaptive data-driven inventory control with censored demand based on Kaplan-Meier estimator. Operations Research 59:4 (2011), 929–941.
Ke, J., Liu, X., Empirical analysis of optimal hidden neurons in neural network modeling for stock prediction. Computational intelligence and industrial application, 2008. PACIIA’08. Pacific-Asia workshop on, vol. 2, 2008, IEEE, 828–832.
Kesavan, S., Kushwaha, T., Differences in retail inventory investment behavior during macroeconomic shocks: Role of service level. Production and Operations Management 23:12 (2014), 2118–2136.
Khayyati, S., Tan, B., Data-driven control of a production system by using marking-dependent threshold policy. International Journal of Production Economics, 226, 2020, 107607.
Van der Laan, N., Teunter, R.H., Romeijnders, W., Kilic, O., The data-driven newsvendor problem: Achieving on-target service levels. Technical Report, 2019, Working paper, University of Groningen, SOM research school.
Levi, R., Roundy, R.O., Shmoys, D.B., Provably near-optimal sampling-based policies for stochastic inventory control models. Mathematics of Operations Research 32:4 (2007), 821–839.
Levinson, S.E., Rabiner, L.R., Sondhi, M.M., An introduction to the application of the theory of probabilistic functions of a Markov process to automatic speech recognition. Bell System Technical Journal 62:4 (1983), 1035–1074.
Liyanage, L.H., Shanthikumar, J.G., A practical inventory control policy using operational statistics. Operations Research Letters 33:4 (2005), 341–348.
Lovejoy, W.S., Stopped myopic policies in some inventory models with generalized demand processes. Management Science 38:5 (1992), 688–707.
Mokni, K., Youssef, M., Empirical analysis of the cross-interdependence between crude oil and agricultural commodity markets. Review of Financial Economics 38:4 (2020), 635–654.
Monahan, G.E., State of the art-a survey of partially observable Markov decision processes: Theory, models, and algorithms. Management Science 28:1 (1982), 1–16.
Oroojlooyjadid, A., Snyder, L.V., Takáč, M., Applying deep learning to the newsvendor problem. IISE Transactions 52:4 (2020), 444–463.
Perakis, G., Roels, G., Regret in the newsvendor model with partial information. Operations Research 56:1 (2008), 188–203.
Qi, M., Shi, Y., Qi, Y., Ma, C., Yuan, R., Wu, D., Shen, Z.-J.M., A practical end-to-end inventory management model with deep learning. Available at SSRN 3737780, 2020.
Qin, F., Auerbach, A., Sachs, F., A direct optimization approach to hidden Markov modeling for single channel kinetics. Biophysical Journal 79:4 (2000), 1915–1927.
Rabiner, L.R., A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE 77:2 (1989), 257–286.
Sachs, A.-L., The data-driven newsvendor with censored demand observations. Retail analytics, 2015, Springer, 35–56.
Scarf, H., A min-max solution of an inventory problem. Studies in the Mathematical Theory of Inventory and Production, 1958.
Scarf, H., Bayes solutions of the statistical inventory problem. The Annals of Mathematical Statistics 30:2 (1959), 490–508.
Sethi, S.P., Cheng, F., Optimality of (s, s) policies in inventory models with Markovian demand. Operations Research 45:6 (1997), 931–939.
Seubert, F., Stein, N., Taigel, F., Winkelmann, A., Making the newsvendor smart–order quantity optimization with ANNs for a bakery chain. Working Paper, 2020.
Shang, K.H., Single-stage approximations for optimal policies in serial inventory systems with nonstationary demand. Manufacturing & Service Operations Management 14:3 (2012), 414–422.
Song, J.-S., Zipkin, P., Inventory control in a fluctuating demand environment. Operations Research 41:2 (1993), 351–370.
Treharne, J.T., Sox, C.R., Adaptive inventory control for nonstationary demand and partial information. Management Science 48:5 (2002), 607–624.
Van Parys, B.P., Esfahani, P.M., Kuhn, D., From data to decisions: Distributionally robust optimization is optimal. Management Science, 2020.
Zhang, Y., Gao, J., Assessing the performance of deep learning algorithms for newsvendor problem. International conference on neural information processing, 2017, Springer, 912–921.
