Braskem needed a view of expected maintenance-shutdown costs before committing the budget. Paulo Cardoso’s team at Manifesttto built a regression model around the historical spreadsheets used by its planning team.
A planned industrial maintenance shutdown brings a substantial set of costs into one event. Braskem’s planners needed to use the cost history from earlier shutdowns to inform the next budget.
The useful intervention was a projection based on information the planning team already held. It did not require replacing their familiar data source with a new operational platform.
The Manifesttto team built a linear regression model from historical cost spreadsheets supplied by Braskem. Those records became the model input, and a projection chart made the expected cost of the next shutdown visible to planners.
Paulo’s role at Manifesttto spanned client scope and software delivery. This project connected a specific planning question to a bounded analytical tool.
The model gave the planning team an expected-cost projection before the shutdown budget was committed. It turned the historical records into a forward-looking input for a business decision.
A forecasting tool is useful only when its owner understands the source data, assumptions and limits. The model and the process for updating it should travel together in a handover. A small analytical intervention can be the right first change when it addresses a well-defined decision.
Project contribution: Paulo Cardoso through Manifesttto. The scope described above identifies the work behind this case.
Editorial review: Ego Eimi · Updated September 6, 2026 · About the team
Your technology
Start with the business
Tell us which system matters, what has changed and who controls it. We will define a reviewable next step. Read Foundation and the commitments and evidence.
