Predictive analytic models to support the internal auditcapacity planning system of an IT company

The internal audits of a company are fundamental for quality assurance and proper compliance with variousprocesses. Planning these audits adequately is crucial, yet companies often lack the necessary tools foreffective planning. This planning involves factors like internal auditors' effort in work hours and audit capacity.These aspects are critical for organizing times and audits over time, as inadequate calculations cansignificantly affect planning and trigger various consequences for the company and its processes.
Given this, it was proposed to develop and implement predictive analytic models to facilitate the planning andoptimization of internal audits in terms of hours and number of audits, thereby improving an existing digitalplanning tool. Historical audit information was obtained, worked, and processed within an IT company.Different Machine Learning Python libraries were applied in the modeling process, including PyCaret, H2O,FLAML, TPOT, LazyRegressor, among others.