Adaptive Risk-Aware Decision-Focused Learning for Dynamic Inventory Optimization with Lead Times and Censored Demand
DOI:
https://doi.org/10.66238/smsrj.v4i2.86Keywords:
decision-focused learning, inventory control, lost sales, lead time, conditional value-at-risk, censored demand, online calibrationAbstract
Decision-focused learning trains a demand forecaster on the cost of the decisions it induces, but in retail it has mostly been applied to single-period decisions, whereas replenishment is dynamic: stock carries over, orders arrive after a lead time and sales are censored when shelves empty. This paper proposes DynRA-DFL, an adaptive risk-aware decision-focused learning framework for periodic-review lost-sales systems. A global network emits monotone multi-horizon demand quantiles and a state-conditional risk weight; an order-up-to layer mixes the critical-fractile level with a closed-form CVaR-optimal level; and the network is trained through a differentiable simulator with deterministic or stochastic lead times, promotion-scaled penalties and a censoring-corrected mean–CVaR cost. An online risk calibration (ORC) rule updates a per-series safety margin from stock-out indicators and provably bounds the long-run stock-out frequency. On 909 M5 and 281 Stallion series, evaluated on observed sales and on reconstructed demand, risk-neutral dynamic training attains mean costs 11.2% lower than static single-period decision-focused learning and 5.9% lower than the same network used for predict-then-optimise, while adding CVaR only at the decision stage raises cost. DynRA-DFL trades off average inventory cost against selected tail-risk reductions: relative to the risk-neutral dynamic baseline it lowers the per-item tail cost by 10.4% at a 2.9% higher mean cost. Under a simulated demand surge, ORC raises the fill rate of the affected series for every policy, with cost changes ranging from −2.5% to +1.4%. We also quantify the bias of evaluating on censored sales.
References
D. Teng, “TRIAD: Deadline- and reliability-aware scheduling for post-earthquake structural assessment workflows,” World Journal of Engineering Research, vol. 3, no. 6, pp. 55–66, 2025.
A. N. Elmachtoub and P. Grigas, “Smart ‘predict, then optimize’,” Manage. Sci., vol. 68, no. 1, pp. 9–26, 2022, doi: 10.1287/mnsc.2020.3922.
P. Donti, B. Amos, and J. Z. Kolter, “Task-based end-to-end model learning in stochastic optimization,” in Proc. Adv. Neural Inf. Process. Syst. (NIPS), vol. 30, 2017, pp. 5484–5494.
J. Mandi, J. Kotary, S. Berden, M. Mulamba, V. Bucarey, T. Guns, and F. Fioretto, “Decision-focused learning: Foundations, state of the art, benchmark and future opportunities,” J. Artif. Intell. Res., vol. 80, pp. 1623–1701, 2024, doi: 10.1613/jair.1.15320.
U. Sadana, A. Chenreddy, E. Delage, A. Forel, E. Frejinger, and T. Vidal, “A survey of contextual optimization methods for decision-making under uncertainty,” Eur. J. Oper. Res., vol. 320, no. 2, pp. 271–289, 2025, doi: 10.1016/j.ejor.2024.03.020.
G.-Y. Ban and C. Rudin, “The big data newsvendor: Practical insights from machine learning,” Oper. Res., vol. 67, no. 1, pp. 90–108, 2019, doi: 10.1287/opre.2018.1757.
A. Oroojlooyjadid, L. V. Snyder, and M. Takáč, “Applying deep learning to the newsvendor problem,” IISE Trans., vol. 52, no. 4, pp. 444–463, 2020, doi: 10.1080/24725854.2019.1632502.
X. Zhang, Y. Yang, and Y. Wang, “Risk-aware decision-focused demand forecasting for multi-channel inventory optimization under promotion and stock-out constraints,” Highlights Bus. Econ. Manag., vol. 69 (MSIED 2026), pp. 263–279, 2026.
M. Qi, Y. Shi, Y. Qi, C. Ma, R. Yuan, D. Wu, and Z.-J. Shen, “A practical end-to-end inventory management model with deep learning,” Manage. Sci., vol. 69, no. 2, pp. 759–773, 2023, doi: 10.1287/mnsc.2022.4564.
J. Gijsbrechts, R. N. Boute, J. A. Van Mieghem, and D. J. Zhang, “Can deep reinforcement learning improve inventory management? Performance on lost sales, dual-sourcing, and multi-echelon problems,” Manuf. Serv. Oper. Manag., vol. 24, no. 3, pp. 1349–1368, 2022, doi: 10.1287/msom.2021.1064.
J. Chen, X. Han, X. Zhang, and Y. Yang, “Exact concept-level explanations for early detection of financial misstatements,” Eurasia Journal of Science and Technology, vol. 5, no. 2, pp. 34–48, 2023.
D. Madeka, K. Torkkola, C. Eisenach, A. Luo, D. P. Foster, and S. M. Kakade, “Deep inventory management,” arXiv:2210.03137, 2022.
M. Alvo, D. Russo, and Y. Kanoria, “Neural inventory control in networks via hindsight differentiable policy optimization,” arXiv:2306.11246, 2023, doi: 10.48550/arXiv.2306.11246.
P. Zipkin, “Old and new methods for lost-sales inventory systems,” Oper. Res., vol. 56, no. 5, pp. 1256–1263, 2008, doi: 10.1287/opre.1070.0471.
J. Wang, Y. Ge, J. Liu, and B. Jiang, “Early warning of liquidity stress in U.S. banks with seasonally aligned frailty hazards and delayed-feedback conformal alarms,” Journal of Trends in Finance and Economics, vol. 1, no. 1, pp. 85–100, 2024.
O. Besbes and A. Muharremoglu, “On implications of demand censoring in the newsvendor problem,” Manage. Sci., vol. 59, no. 6, pp. 1407–1424, 2013, doi: 10.1287/mnsc.1120.1654.
R. T. Rockafellar and S. Uryasev, “Optimization of conditional value-at-risk,” J. Risk, vol. 2, no. 3, pp. 21–41, 2000, doi: 10.21314/JOR.2000.038.
J. Gotoh and Y. Takano, “Newsvendor solutions via conditional value-at-risk minimization,” Eur. J. Oper. Res., vol. 179, no. 1, pp. 80–96, 2007.
X. Chen, M. Sim, D. Simchi-Levi, and P. Sun, “Risk aversion in inventory management,” Oper. Res., vol. 55, no. 5, pp. 828–842, 2007, doi: 10.1287/opre.1070.0429.
S. Ahmed, U. Çakmak, and A. Shapiro, “Coherent risk measures in inventory problems,” Eur. J. Oper. Res., vol. 182, no. 1, pp. 226–238, 2007.
A. Ruszczyński, “Risk-averse dynamic programming for Markov decision processes,” Math. Program., vol. 125, no. 2, pp. 235–261, 2010, doi: 10.1007/s10107-010-0393-3.
J. Chen, X. Zhang, and X. Han, “Explainable identification of tax-related financial reporting anomalies in U.S. public companies: Cross-fitted tax-consistency residuals and Owen-value Shapley propagation,” World Journal of Economics and Business Research, vol. 1, no. 1, pp. 33–45, 2023.
W. T. Huh and P. Rusmevichientong, “A nonparametric asymptotic analysis of inventory planning with censored demand,” Math. Oper. Res., vol. 34, no. 1, pp. 103–123, 2009, doi: 10.1287/moor.1080.0355.
W. T. Huh, R. Levi, P. Rusmevichientong, and J. B. Orlin, “Adaptive data-driven inventory control with censored demand based on Kaplan–Meier estimator,” Oper. Res., vol. 59, no. 4, pp. 929–941, 2011, doi: 10.1287/opre.1100.0906.
I. Gibbs and E. Candès, “Adaptive conformal inference under distribution shift,” in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), vol. 34, 2021, pp. 1660–1672.
R. Koenker and G. Bassett, “Regression quantiles,” Econometrica, vol. 46, no. 1, pp. 33–50, 1978, doi: 10.2307/1913643.
D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” in Proc. Int. Conf. Learn. Represent. (ICLR), 2015, arXiv:1412.6980.
J. Wang, J. Liu, Y. Ge, and B. Jiang, “Risk-aware ensemble learning for credit default prediction under economic uncertainty,” World Journal of Economics and Business Research, vol. 1, no. 1, pp. 18–32, 2023.
G. Ke, Q. Meng, T. Finley, T. Wang, W. Chen, W. Ma, Q. Ye, and T.-Y. Liu, “LightGBM: A highly efficient gradient boosting decision tree,” in Proc. Adv. Neural Inf. Process. Syst. (NIPS), vol. 30, 2017, pp. 3146–3154.
F. X. Diebold and R. S. Mariano, “Comparing predictive accuracy,” J. Bus. Econ. Statist., vol. 13, no. 3, pp. 253–263, 1995, doi: 10.1080/07350015.1995.10524599.
J. Liu, J. Wang, and H. Lin, “Coordinated Physics-Informed Multi-Agent Reinforcement Learning for Risk-Aware Supply Chain Optimization,” IEEE Access, 2025, doi: 10.1109/ACCESS.2025.3629716.
P. Li et al., “Think4SCND: Reinforcement Learning With Thinking Model for Dynamic Supply Chain Network Design,” IEEE Access, 2024, doi: 10.1109/ACCESS.2024.3521439.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Jasper Moore, Mia Edwards, Katherine Kang
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles in the Social and Management Sciences Research Journal are published under the Creative Commons Attribution 4.0 (CC BY 4.0) license. Users can share, copy, distribute, and adapt the work, including for commercial purposes, provided proper attribution is given to the authors and the journal.
