Inspiration
The inspiration behind our projects lies behind our shared interest in blockchain technologies, and the nuances behind creating an efficient and scalable network. The first question as a result was something that aligned perfectly with our interests, and we wanted to provide a solution that could help further improve such networks
What it does
Our algorithm can convert a training set to a blockchain and can train itself to identify the risk levels of a transaction by reading the key identifiers within a block. Our algorithm is then able to take in a set of data provided by the user, convert it into a blockchain and assign appropriate risk levels depending on the date within the block
How we built it
We employed the use of Python to write our algorithm and employed libraries such as pandas and scikit-learn to read the data file stored as a csv file and make our model
Challenges we ran into
One big challenge we faced was visualising how to create our blockchain in code as we only had a theoretical understanding of it but did not have any experience with creating it
Accomplishments that we're proud of
One thing we are proud of is having been able to create our very own blockchains without having to reference an external source and using our theoretical understanding of it
What we learned
One important lesson we learnt was how to better make use of machine learning algorithms to read different data in the block to make accurate assessments
What's next for Machine Learning BlockChain Risk Classifier
We hope to further expand our blockchain from a simple class to a full-scale network and further improve on our model to not only make use of internal data stored within the block but also make use of external data such as external country regulations to better make accurate predicitons
Log in or sign up for Devpost to join the conversation.