Rashmi Erandika Ratnayake

The fast adoption of blockchain technology across various sectors has been driven by its numerous benefits, including decentralization, immutability, and transparency. However, a persistent challenge remains: while blockchains ensure the integrity of data once it's added, they do not inherently ensure the accuracy or truthfulness of the data itself, leading to what is known as the 'blockchain bad data problem.' This issue has significant implications, especially in areas where decision-making relies heavily on accurate data. One potential solution is the integration of machine learning (ML), which can complement traditional validation methods like oracles or trusted third parties by providing an additional layer of verification. ML models excel at analyzing complex patterns, detecting anomalies, and making data-driven predictions. By leveraging ML algorithms, blockchain systems can enhance their ability to verify and validate data accuracy, thus bolstering trust in the information stored on the blockchain. My research highlights the potential synergy between ML and blockchain technologies, with a focus on integrating ML algorithms into blockchain-enabled Internet of Things (IoT) systems. This integration aims to address challenges related to data accuracy, introducing innovative approaches to mitigate the blockchain bad data problem.