Problem-solving based, as much as possible, on real data, expert knowledge, and on-field observation are quite desired objectives. However, it creates several difficulties on deployment in real situations. In this work, a data-driven version of the well-known PDCA cycle is proposed for continuous improvement within a general class of problems represented by key performance indicators (KPI). Such class is wide enough to accommodate several real problems but still has a controlled level of complexity that allows defining a general data-driven protocol that covers all the (sub)steps of the cycle. New approaches and alternatives in the literature are discussed. A brief example of one of the steps of the protocol is given with real data from a company that adopts many of the new Industry 4.0 technologies.