Retailer-Supplier Inventory System Simulation Data with Defective Returns

A 1.6 MB dataset on figshare by Hanieh Karami, last updated May 2026, presents simulation results for an inventory system. The study integrates an LSTM neural network for demand forecasting within a Continuous-Time Markov Chain framework to optimize reorder points and order quantities. It models nonlinear demand patterns influenced by price, discounts, seasonality, and incorporates defective returns.

Use Cases

• Optimizing reorder points and order quantities based on stochastic modelling of demand uncertainty and delivery time.
• Forecasting demand using machine learning techniques to capture patterns influenced by price, discounts, and seasonality.
• Analyzing the impact of defective product returns on inventory policy and profitability.
• Evaluating the effect of supplier delivery rate changes on optimal inventory levels and expected profit.

Strengths

• The model incorporates defective returns and price-dependent demand, enhancing practical relevance.
• Numerical results confirm the concavity of the profit function and support effective policy identification.
• Managerial insights quantify a 50% increase in supplier delivery rate reducing optimal reorder levels by ~20% and increasing expected profit by 2%.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The dataset is small at 1.6 MB, suggesting it contains summary results or a limited simulation scope.

Provenance

Source

figshare

Collection Method

Likely generated through simulation and numerical analysis as part of the described research.

Freshness

Last updated 2026-05-11 23:42:42; freshness should be verified.