Cryptocurrency and Associated Bourse Analysis using Machine Learning and Knowledge Graphs

Abstract

Data science has a goal to discover hidden patterns in raw data. This is exceptionally useful when discussing the stock market. The way crypto currency has taken over the world is something that wasn't predicted 20 years ago. It seems that regular market indicators aren't being implemented in the case of crypto currencies such as bit coin. Crypto currency seems to evade inflation as well. For analysts to perform analyses on these entities there are umpteen tools. One instance is the knowledge graph, which is a collection of interlinked descriptions of objects, events, or concepts. It puts data in context through linking and semantic metadata. Historical data present across many trading and finance websites enable analysts and enthusiasts to try machine learning and deep learning algorithms to predict the subsequent nature of that market. The paper has summarized and analyzed all the possible algorithms to prepare the data available regarding the lifetime and volatility of a currency state. A knowledge graph linking all the related information was also materialized along with a UML-style ontological graph is done to aid and support proper inference from the knowledge representation model.