A machine learning based approach for predicting blockchain adoption in supply Chain

Sachin S. Kamble, Angappa Gunasekaran, Vikas Kumar, Amine Belhadi, Cyril Foropon

Research output: Contribution to journalArticlepeer-review

150 Scopus citations


The purpose of this paper is to provide a decision support system for managers to predict an organization's probability of successful blockchain adoption using a machine learning technique. The study conceptualizes blockchain technology as a dynamic capability that should be possessed by the organization to remain competitive. The factors influencing the blockchain adoption behavior were modeled using the theoretical lens of the Technology Acceptance Model and Technology-organisation-Environment framework. The findings identify competitor pressure, partner readiness, perceived usefulness, and perceived ease of use as the most influencing factors for blockchain adoption. A predictive decision support system was developed using a Bayesian network analysis featuring the significant factors that can be used by the decision-makers for predicting the probability of blockchain adoption in their organization. The prior probability values reported in the study may be used as indicators by the practitioners to predict their blockchain adoption probability. The practitioner will be required to substitute these probability values (high or low), as applicable to their organization to estimate the adoption probability. The use of the decision support system is likely to help the decision-makers to assess their adoption probability and develop future adoption strategies.

Original languageEnglish (US)
Article number120465
JournalTechnological Forecasting and Social Change
StatePublished - Feb 2021

All Science Journal Classification (ASJC) codes

  • Business and International Management
  • Applied Psychology
  • Management of Technology and Innovation


Dive into the research topics of 'A machine learning based approach for predicting blockchain adoption in supply Chain'. Together they form a unique fingerprint.

Cite this