Backorder Prediction in Inventory Management: Classification Techniques and Cost Considerations

TL;DR

This paper evaluates various classification techniques for backorder prediction in inventory management, incorporating cost considerations and proposing combined modeling approaches to improve accuracy and decision-making.

Contribution

It introduces a comprehensive assessment of advanced classification methods with cost analysis for backorder prediction, highlighting ensemble and VAE techniques for imbalanced data.

Findings

Ensemble methods and VAE improve prediction accuracy.

Cost-aware models reduce false positives and negatives.

Enhanced interpretability aids inventory decision-making.

Abstract

This article introduces an advanced analytical approach for predicting backorders in inventory management. Backorder refers to an order that cannot be immediately fulfilled due to stock depletion. Multiple classification techniques, including Balanced Bagging Classifiers, Fuzzy Logic, Variational Autoencoder - Generative Adversarial Networks, and Multi-layer Perceptron classifiers, are assessed in this work using performance evaluation metrics such as ROC-AUC and PR-AUC. Moreover, this work incorporates a profit function and misclassification costs, considering the financial implications and costs associated with inventory management and backorder handling. The study suggests that a combination of modeling approaches, including ensemble techniques and VAE, can effectively address imbalanced datasets in inventory management, emphasizing interpretability and reducing false positives and false negatives. This research contributes to the advancement of predictive analytics and offers valuable insights for future investigations in backorder forecasting and inventory control optimization for decision-making.