I help finance and operations teams turn document queues, forecasts, and fragmented reports into workflows they can check and use.
Seven objects. Seven ways into the work.
Choose an object to look closer, or browse the work below.
01 / Work
02 / Work
Four services, two research projects, and one synthetic demonstration. Open any volume to examine its scope, evidence, and limitations.
The document nobody has time to read — and one person is the bottleneck.
A single figure, presented as certainty and planned against as fact.
Two departments, two revenue figures, and a meeting that has already moved on.
Two regulatory systems at once. The expensive mistake is not knowing which question to ask.
A claim that outruns the commitment. Evaluated on 29 claims — and it misses most of them.
When an outcome passes through a threshold, it is the threshold that must be modelled.
An allocation you cannot interrogate. Invented assumptions, shown in full.
03 / Evidence record
A result is useful when you can inspect how it was produced—and what it does not prove.
29 claims
0.40 recall at 1.00 precision
04 / Approach
We look at the actual decision and the actual data, and agree what a good outcome would be before anything is built. Often this is where a project gets smaller.
A written problem statement, and an honest view of whether it is worth doing.
One workflow, one document type, one forecast. Small enough that finding out it does not work is a cheap answer rather than a sunk cost.
A working prototype and an evaluation on your own data.
The thing that survived the pilot gets built where the work actually happens, with the review step in place from the first day rather than added later.
The deployed workflow, its documentation, and the checks that show when it drifts.
Your team runs it without me. That includes knowing how to re-evaluate it when the inputs change, because they will.
Documentation, the evaluation harness, and a walkthrough with whoever owns it next.
05 / About
A background spanning economics, risk and control, industrial data science, and applied research. Based in Milan, working across Italy and Türkiye.
About / CV06 / Bumin Kağan Çetin