Improvement of the Internal Audit Planning System in an IT Company through Predictive Analytics.

Internal auditing is a fundamental process for quality assurance and compliance of processes within a company. For this reason, it is very important that companies can adequately plan its execution. One of the most important aspects to consider for effective planning is the calculation of the estimated time it takes to execute the audits. This project proposes the use of machine learning to develop a model that can predict the effort time (referred to as Actual Effort) that is required to carry out a certain number of audits in a period of two weeks (referred to as Sprint) in an information technology services company. In the early stages of the project, it was intended to develop an algorithm that predicts the Actual Effort for a single audit, but due to inefficient results, the approach of predicting the Actual Effort per Sprint was preferred. Many types of models were implemented along the project and various evaluation metrics, such as coefficient of determination (R²), symmetric mean absolute percentage error (SMAPE), and others, were evaluated. The best results were obtained by an ETR model where an R² of 96% and a SMAPE of 8.47% were obtained. [ABSTRACT FROM AUTHOR]