One of the most significant challenges we have in the context of today's big data world is the fact that we are unable to process enormous amounts of data in a timely manner. In this piece, the authors will use drive HQ cloud to analyse and evaluate two different supervised multiplication systems that are built on service cluster applications. Spark, on the other hand, provides a framework for managing data that is more dependable, and also has the ability to address concerns such as the loss of nodes and the duplication of data. Although it comes at the expense of insufficient failure organization, this study issue has the ability to considerably increase pace effectiveness, which is something many research/industry companies are interested in. A soon-to-be-released study will examine the methods on bigger datasets, especially in cases where the data cannot be totally stored in memory.