Download PDFOpen PDF in browser

Leveraging Generative Adversarial Networks (GANs) for Supply Chain Optimization: a Comprehensive Overview

EasyChair Preprint no. 12929

13 pagesDate: April 6, 2024


Generative Adversarial Networks (GANs) represent a groundbreaking advancement in the realm of generative artificial intelligence, offering immense potential across diverse applications, including supply chain optimization. This abstract aims to provide a comprehensive exploration of GANs, elucidating their fundamental principles, applications, and implications in the context of supply chain management.

At its core, a GAN comprises two neural networks, the generator and the discriminator, engaged in a dynamic adversarial process. The generator generates synthetic data samples, while the discriminator evaluates their authenticity relative to real data. Through iterative training, GANs learn to generate increasingly realistic data distributions, making them invaluable tools for data augmentation, anomaly detection, and scenario simulation.

In the realm of supply chain management, GANs serve multifaceted roles, ranging from generating synthetic datasets for demand forecasting and inventory optimization to simulating complex supply chain scenarios and optimizing logistical processes. By leveraging GANs, organizations can overcome data scarcity or privacy constraints by generating synthetic datasets that closely mimic real-world data distributions. These synthetic datasets enable robust model training, facilitating more accurate demand forecasting, inventory planning, and supply chain optimization.

Keyphrases: anomaly detection, data augmentation, Generative Adversarial Networks, Generative Artificial Intelligence, Supply Chain Optimization, synthetic data

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
  author = {Dylan Stilinski and Lucas Doris and Louis Frank},
  title = {Leveraging Generative Adversarial Networks (GANs) for Supply Chain Optimization: a Comprehensive Overview},
  howpublished = {EasyChair Preprint no. 12929},

  year = {EasyChair, 2024}}
Download PDFOpen PDF in browser