Simulation-based decision support system for data analytics deployment
Data has been recognized as one of the most valuable assets of modern business. The capacity to gather, store, analyze and interpret data in great quantities can determine to a large degree the ability of a company to achieve goals and adapt to largely volatile environments. This is especially true for financial institutions where data is directly connected to profitability. In the presence of a large number of relevant solutions to support automatic data analytics, implementation of analytics tasks and their deployment on computation infrastructure, as in cloud, involve complex decisions that can often lead to suboptimal results. Besides accuracy of analytics, this lack of optimality may lead to misused or wasted computation resources and loss of productivity for data scientists. In this project, our objective is to model this variety of alternative options by capturing their performance, such as latency and throughput, as well as their business aspects, including ROI and productivity. Based on this model, we will build a simulation engine capable of replaying what-if scenarios and guide data scientists towards more optimal solutions.