Nowadays, the computational cloud shows itself as an alternative to the traditional clusters, delivering high-performance virtual machines on demand and working on a pay-as-yougo basis, in which the user only needs to pay by the time of use. Nonetheless, inappropriate virtual machines selections can lead to unexpected billings and unacceptable performance. Therefore, this work has the objective to simplify the instance selection process, empowering the user to select how much they are willing to spend to process a data set in the Amazon Web Services (AWS) computational cloud and minimizing the execution time for that budget. To accomplish this task, we present a heuristic that auto-adjusts a cluster on the computational cloud to fit the user requested budget. By making smart choices, we assume that the heuristic will be able to execute the program in the shortest time without spending more than the desired. Our experiments have two steps for analysis: Firstly, we use a simulator to test our heuristic. Secondly, we use AWS cloud infrastructure to process a real dataset. The obtained results by our experiments are promising; they show the heuristic worked well both in simulated and real-world scenarios, delivering expected execution times for the input budgets and near optimum-minimal cost. Presentation Date: Wednesday, September 18, 2019 Session Start Time: 8:30 AM Presentation Start Time: 11:00 AM Location: 214D Presentation Type: Oral