Enhancing Supply Chain Resilience: A Machine Learning Approach for Predicting Product Availability Dates Under Disruption (2304.14902v1)

Abstract: The COVID 19 pandemic and ongoing political and regional conflicts have a highly detrimental impact on the global supply chain, causing significant delays in logistics operations and international shipments. One of the most pressing concerns is the uncertainty surrounding the availability dates of products, which is critical information for companies to generate effective logistics and shipment plans. Therefore, accurately predicting availability dates plays a pivotal role in executing successful logistics operations, ultimately minimizing total transportation and inventory costs. We investigate the prediction of product availability dates for General Electric (GE) Gas Power's inbound shipments for gas and steam turbine service and manufacturing operations, utilizing both numerical and categorical features. We evaluate several regression models, including Simple Regression, Lasso Regression, Ridge Regression, Elastic Net, Random Forest (RF), Gradient Boosting Machine (GBM), and Neural Network models. Based on real world data, our experiments demonstrate that the tree based algorithms (i.e., RF and GBM) provide the best generalization error and outperforms all other regression models tested. We anticipate that our prediction models will assist companies in managing supply chain disruptions and reducing supply chain risks on a broader scale.

• The paper proposes advanced machine learning models, especially tree-based algorithms, which significantly improve product availability predictions.
• Utilizing real-world data from GE Gas Power, the study shows that Random Forest and Gradient Boosting outperform traditional regression methods.
• Accurate predictions help optimize logistics, reduce costs, and strengthen supply chain resilience during periods of disruption.

The paper "Enhancing Supply Chain Resilience: A Machine Learning Approach for Predicting Product Availability Dates Under Disruption" addresses the critical issue of predicting product availability in the context of supply chain disruptions, specifically for General Electric (GE) Gas Power. These disruptions are exacerbated by events such as the COVID-19 pandemic and geopolitical conflicts, which have caused significant delays in logistics operations.

Key Objectives and Methods

The central goal of the paper is to develop predictive models for the accurate estimation of product availability dates, which are crucial for planning logistics and shipment schedules and minimizing costs. The researchers focus on GE Gas Power's inbound shipments related to gas and steam turbine services and manufacturing.

The paper utilizes both numerical and categorical features to train and evaluate several regression models, including:

• Simple Regression
• Lasso Regression
• Ridge Regression
• Elastic Net
• Random Forest (RF)
• Gradient Boosting Machine (GBM)
• Neural Network Models

Experimental Findings

Based on the real-world data from GE operations, the experimental results highlight that tree-based algorithms, specifically the Random Forest (RF) and Gradient Boosting Machine (GBM), showcase the best performance in terms of generalization error. These models outperformed the other regression techniques tested in the paper, making them the most effective approach for predicting availability dates accurately.

Implications

The successful implementation of these predictive models is anticipated to significantly aid companies in handling supply chain disruptions more effectively. By accurately predicting product availability, companies can optimize their logistics operations, reduce transportation and inventory costs, and mitigate broader supply chain risks.

In conclusion, the research provides valuable insights and tools for enhancing supply chain resilience through advanced machine learning techniques, offering practical solutions to challenges faced in turbulent times.