A Blockchain-enabled and Transparent Evaluation of ML Models in the Decentralised Marketplace
Year: 2024
Type: conference-paper
Abstract: In the current digital era, supply chain companies possess vast amounts of data that can drive smarter products and services. Machine Learning (ML) and Artificial Intelligence (AI) can extract valuable insights from this data. Model buyers often encounter high costs or uncertainty about the quality of models developed by large corporations, while many small ML developers have developed suitable models. These small owners are often reluctant to share or compete due to concerns about transparency and fairness in the evaluation process. Decentralised model marketplaces aim to bridge this gap, addressing issues related to cost, privacy, and fairness, but significant barriers still hinder participation. This paper introduces a decentralised evaluation platform of the ML model marketplace that tackles these marketplace challenges. The transparent, fair, and immutable ranking system enables buyers to find models that meet their budget and quality expectations and encourages model owners to share their best models. The proposed workflow is implemented and analysed for efficiency, throughput, and costs.
Institutions: University of London, City, University of London
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
SDG: Reduced inequalities
Open Access status: green
OpenAlex ID: W4402595332