Load Balancing of Financial Data Using Machine Learning and Cloud Analytics

Abstract

With the rising use of technology, e-application systems for financial investments are highly used and are of major concern with the growing demand. As a result, a large number of users access web applications very often to analyze the trends in the market. This needs a proper managing system for balancing user requests. The process of balancing simultaneous requests is highly complicated, non-trivial and critical at times, which forces to add an external service—to handle requests and maximize the resource utilization. In this paper, we will discuss a Machine Learning Approach to design a load balancing system with a comparative case study of applying different approaches for scheduling requests. A supervised approach will be used to design the model, which will decide on the basis of predictions made by analyzing the log data. This will maximize resource utilization at different conditons like- low, medium and peak loads and will also bring flexibility to scale the system. Thus, producing a dynamic environment in the system.