A Unified Analytical Framework for Trustable Machine Learning and\n Automation Running with Blockchain

Abstract

Traditional machine learning algorithms use data from databases that are\nmutable, and therefore the data cannot be fully trusted. Also, the machine\nlearning process is difficult to automate. This paper proposes building a\ntrustable machine learning system by using blockchain technology, which can\nstore data in a permanent and immutable way. In addition, smart contracts are\nused to automate the machine learning process. This paper makes three\ncontributions. First, it establishes a link between machine learning technology\nand blockchain technology. Previously, machine learning and blockchain have\nbeen considered two independent technologies without an obvious link. Second,\nit proposes a unified analytical framework for trustable machine learning by\nusing blockchain technology. This unified framework solves both the\ntrustability and automation issues in machine learning. Third, it enables a\ncomputer to translate core machine learning implementation from a single thread\non a single machine to multiple threads on multiple machines running with\nblockchain by using a unified approach. The paper uses association rule mining\nas an example to demonstrate how trustable machine learning can be implemented\nwith blockchain, and it shows how this approach can be used to analyze opioid\nprescriptions to help combat the opioid crisis.\n

Ähnliche Arbeiten