Industry 4.0 technologies and environmental sustainability performance in supply chains: an exploratory statistical and machine learning analysis

Purpose This study examines how key Industry 4.0 technologies relate to environmental sustainability performance in supply chains. Specifically, it examines Internet of Things, Artificial Intelligence, Big Data Analytics, Blockchain, Digital Twin and Cloud Computing, and explores their relative associations with sustainability outcomes using both statistical and machine learning techniques. Design/methodology/approach A quantitative cross-sectional survey design was adopted. Data were collected from 268 supply chain and logistics professionals across multiple industries. Descriptive and inferential statistical analyses were conducted using SPSS software version 31.0.2. Machine learning analysis was carried out using Orange Data Mining to perform feature importance ranking and decision tree modeling, with model performance evaluated using 10-fold cross-validation. Findings Correlation and hierarchical regression analyses reveal no statistically significant association between any individual Industry 4.0 technology and environmental sustainability performance and tested pairwise interaction effects are likewise non-significant. Exploratory machine learning feature rankings order the technologies differently across three methods, and cross-validated models do not outperform a mean-only baseline, indicating no detectable predictive signal in these data. Research limitations/implications The study is based on cross-sectional survey data, which limits causal interpretation and does not capture changes in technology adoption and sustainability performance over time. The sample, although adequate for the applied analyses, is restricted to 268 respondents and may not fully represent all industries and geographical contexts. Future research should use longitudinal designs, larger international samples and additional Industry 4.0 technologies to extend the understanding of digital transformation and sustainability relationships in supply chains. Practical implications The findings caution against expecting sustainability improvements from technology adoption alone. No individual technology, and no tested combination, showed a statistically significant association with environmental sustainability performance, and cross-validated models showed no predictive signal. The results redirect managerial attention from technology acquisition toward the mediating organizational practices through which digital technologies may generate sustainability value. Originality/value This study measures six Industry 4.0 technologies as separate constructs within a single sample, combines conventional statistical testing with exploratory, cross-validated machine learning, and transparently reports a null result for direct technology–performance associations a finding that complements prior mediation-based evidence by suggesting that direct effects of individual technologies may be weak in the absence of mediating capabilities.

Authors

Institutions

Publication Details

Journal
Modern Supply Chain Research and Applications
Published
2026-10-13
DOI
https://doi.org/10.1108/mscra-03-2026-0027
Primary Topic
Sustainable Supply Chain Management
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Industry 4.0 technologies and environmental sustainability performance in supply chains: an exploratory statistical and machine learning analysis

Arish Ibrahim
Modern Supply Chain Research and Applications
Sustainable Supply Chain Management
article

Industry 4.0 technologies and environmental sustainability performance in supply chains: an exploratory statistical and machine learning analysis

Arish Ibrahim
article en

Abstract

Purpose This study examines how key Industry 4.0 technologies relate to environmental sustainability performance in supply chains. Specifically, it examines Internet of Things, Artificial Intelligence, Big Data Analytics, Blockchain, Digital Twin and Cloud Computing, and explores their relative associations with sustainability outcomes using both statistical and machine learning techniques. Design/methodology/approach A quantitative cross-sectional survey design was adopted. Data were collected from 268 supply chain and logistics professionals across multiple industries. Descriptive and inferential statistical analyses were conducted using SPSS software version 31.0.2. Machine learning analysis was carried out using Orange Data Mining to perform feature importance ranking and decision tree modeling, with model performance evaluated using 10-fold cross-validation. Findings Correlation and hierarchical regression analyses reveal no statistically significant association between any individual Industry 4.0 technology and environmental sustainability performance and tested pairwise interaction effects are likewise non-significant. Exploratory machine learning feature rankings order the technologies differently across three methods, and cross-validated models do not outperform a mean-only baseline, indicating no detectable predictive signal in these data. Research limitations/implications The study is based on cross-sectional survey data, which limits causal interpretation and does not capture changes in technology adoption and sustainability performance over time. The sample, although adequate for the applied analyses, is restricted to 268 respondents and may not fully represent all industries and geographical contexts. Future research should use longitudinal designs, larger international samples and additional Industry 4.0 technologies to extend the understanding of digital transformation and sustainability relationships in supply chains. Practical implications The findings caution against expecting sustainability improvements from technology adoption alone. No individual technology, and no tested combination, showed a statistically significant association with environmental sustainability performance, and cross-validated models showed no predictive signal. The results redirect managerial attention from technology acquisition toward the mediating organizational practices through which digital technologies may generate sustainability value. Originality/value This study measures six Industry 4.0 technologies as separate constructs within a single sample, combines conventional statistical testing with exploratory, cross-validated machine learning, and transparently reports a null result for direct technology–performance associations a finding that complements prior mediation-based evidence by suggesting that direct effects of individual technologies may be weak in the absence of mediating capabilities.

Modern Supply Chain Research and Applications
Vocational Training Council (HK)
Openalex Percentile: Top 9%
Sustainable Supply Chain Management
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.