Abstract

With the advent of technology, modern human activities produce a huge amount of data. This vast amount of data facilitates a better model training, thus creating accurate predictions. But most of the business entities lack the facilities and resources to develop an AI system. There is a need for a platform, to which the business can outsource the process of data collection, model development, and its deployment. These models should be tailored for each use case. The work presented here attempts to address these issues using blockchain and incremental learning. The transactions and user identification in the platform are implemented using blockchain, thus maintaining the ownership of the model and dataset in a transparent, immutable and decentralized manner. Incremental learning algorithms are employed to facilitate the real-time updation of the model. All the models and the datasets collected in the platform are considered resources. The platform opens up an avenue for developing a marketplace for data and trained models.