Artificial intelligence algorithms for supply chain resilience and performance: Bibliometric and thematic analysis (2015 – April 2026)

Abstract

Artificial intelligence is increasingly seen as a catalyst for designing resilient and sustainable supply chains in the context of shocks (pandemics, geopolitical crises, price spikes). The main types of algorithms and systems used are: machine learning, supervised learning algorithms, unsupervised learning algorithms, deep learning, reinforcement learning, and natural language processing algorithms.

The main objective of this paper is to map artificial intelligence algorithms, following a methodology in the form of a systematic review covering the period 2015 – April 2026. It is based on a quantitative approach using the R bibliometrix package, in a corpus of 288 documents referenced in Scopus.

The results show through bibliometric analyses: keyword co-occurrence analysis the emergence of four clusters: machine learning and prediction techniques, artificial intelligence and supply chain resilience, risk management, decision-making, sustainable logistics, and the circular economy. The thematic analysis presents five main themes: decision-making behavioral research, decision support systems, machine learning systems, logistic regression, decision support systems, deep learning risk assessment, artificial intelligence, and supply chain management.

Keywords: Bibliometric Analysis, Artificial Intelligence, Supply Chain Resilience, Supply Chain Performance.

Received Date: June 19, 2026

Accepted Date: July 10, 2026

Published Date: August 01, 2026

Available Online at: https://www.ijsrisjournal.com/index.php/ojsfiles/article/view/837