Download PDFOpen PDF in browser

Harnessing Predictive Analytics and Generative AI for Proactive Supply Chain Management: a Comprehensive Overview

EasyChair Preprint no. 12928

17 pagesDate: April 6, 2024


Predictive analytics, in tandem with generative AI techniques, stands as a transformative force in modern supply chain management, empowering organizations to anticipate demand, pinpoint potential bottlenecks, and proactively optimize their operations. This abstract aims to elucidate the synergistic potential of predictive analytics and generative AI in the context of supply chain optimization, offering insights into their applications, benefits, and implications.

Predictive analytics leverages advanced statistical algorithms and machine learning models to analyze historical data, identify patterns, and forecast future trends. By harnessing vast datasets encompassing sales records, market trends, and external factors, predictive analytics enables organizations to generate accurate demand forecasts, anticipate seasonal fluctuations, and optimize inventory levels. However, the inherent complexity and uncertainty of supply chain dynamics necessitate advanced techniques, such as generative AI, to augment predictive capabilities further.

Generative AI techniques, including Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), complement predictive analytics by generating synthetic data samples that closely resemble real-world distributions. By synthesizing diverse scenarios and augmenting limited datasets, generative AI enhances the robustness and accuracy of predictive models, enabling organizations to make informed decisions in dynamic environments. Moreover, generative AI facilitates scenario simulation, enabling organizations to assess the impact of potential disruptions, identify critical bottlenecks, and devise proactive mitigation strategies.

Keyphrases: Bottlenecks, Data Quality, data synthesis, Demand Forecasting, Generative AI, interpretability, Optimization, organizational readiness, Predictive Analytics, Proactive Decisions, Risk Mitigation, Scenario simulation, Supply Chain Management

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 = {Harnessing Predictive Analytics and Generative AI for Proactive Supply Chain Management: a Comprehensive Overview},
  howpublished = {EasyChair Preprint no. 12928},

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