Inventory Control with Unobservable Lost Sales and Bayesian Updates

We study a nite-horizon lost-sales inventory model. The demand distribution is unknown and is dynamically updated based on the previous sales data in a Bayesian fashion. We derive a samplepath representation of the rst order optimality condition, which characterizes the key tradeo of the problem. The expression allows us to see why the computation of the optimal policy is dicult and why the myopic solution is not a bound on the optimal solution. It enables us to develop simpler solution bounds and approximations. It also helps us to develop cost bounds as well as cost error bounds of the approximations. Numerical examples indicate that our approximations are most eective for products with short life-cycle. Otherwise, the myopic policy may be a reasonable choice.

[1]  Jing-Sheng Song,et al.  Inventory Planning with Forecast Updates: Approximate Solutions and Cost Error Bounds , 2006, Oper. Res..

[2]  H. Scarf.  Bayes Solutions of the Statistical Inventory Problem , 1959 .

[3]  S. Nahmias.  Demand estimation in lost sales inventory systems , 1994 .

[4]  S. Karlin.  Dynamic Inventory Policy with Varying Stochastic Demands , 1960 .

[5]  Woonghee Tim Huh,et al.  A Nonparametric Asymptotic Analysis of Inventory Planning with Censored Demand , 2009, Math. Oper. Res..

[6]  Suresh P. Sethi,et al.  A Multiperiod Newsvendor Problem with Partially Observed Demand , 2007, Math. Oper. Res..

[7]  Jing-Sheng Song,et al.  Analysis of Perishable-Inventory Systems with Censored Demand Data , 2008, Oper. Res..

[8]  Li Chen,et al.  Dynamic Inventory Management with Learning About the Demand Distribution and Substitution Probability , 2008, Manuf. Serv. Oper. Manag..

[9]  David J. Braden,et al.  Informational dynamics of censored observations , 1991 .

[10]  Martin L. Puterman,et al.  The Censored Newsvendor and the Optimal Acquisition of Information , 2002, Oper. Res..

[11]  Ananth V. Iyer,et al.  Improved Fashion Buying with Bayesian Updates , 1997, Oper. Res..

[12]  R. L. Winkler,et al.  Learning, Experimentation, and the Optimal Output Decisions of a Competitive Firm , 1982 .

[13]  Stephen A. Smith,et al.  Estimating negative binomial demand for retail inventory management with unobservable lost sales , 1996 .

[14]  W. Lovejoy.  Stopped Myopic Policies in Some Inventory Models with Generalized Demand Processes , 1992 .

[15]  H. Scarf.  Some remarks on bayes solutions to the inventory problem , 1960 .

[16]  Evan L. Porteus,et al.  Stalking Information: Bayesian Inventory Management with Unobserved Lost Sales , 1999 .

[17]  W. Lovejoy.  Myopic policies for some inventory models with uncertain demand distributions , 1990 .

[18]  M. Dada,et al.  Dynamic learning, pricing, and ordering by a censored newsvendor , 2007 .

[19]  Jing-Sheng Song,et al.  Newsvendor Bounds and Heuristic for Optimal Policies in Serial Supply Chains , 2001, Manag. Sci..

[20]  Katy S. Azoury.  Bayes Solution to Dynamic Inventory Models Under Unknown Demand Distribution , 1985 .

[21]  T. Morton.  The Nonstationary Infinite Horizon Inventory Problem , 1978 .

[22]  T. Morton,et al.  The finite horizon nonstationary stochastic inventory problem: near-myopic bounds, heuristics, testing , 1995 .

[23]  Suresh P. Sethi,et al.  Censored Newsvendor Model Revisited with Unnormalized Probabilities , 2009 .