Katerina Zhittsova

Energy analytics with the checks built in

I work on forecasting, reporting, and geospatial analysis where the useful result depends on clean tables, data QA, tested transformations, and a clear explanation of the caveats.

SQL · Power BI · Python ETL · Data QA · Forecasting · Geospatial analytics

I'm a Berlin-based data analyst working around energy, renewables, operations, and maps. Most of the job happens before the chart looks interesting: finding the right grain, checking the joins, and making sure the result is still explainable a month later.

My usual toolkit is SQL, Power BI, Python ETL, geospatial data, and plain documentation that says what actually happened. Forecasting and reporting matter, but so do the quieter parts: definitions, source notes, data QA, testing the joins and transformations, and the awkward assumptions that should not vanish after the first demo.

What I do

I take analytical questions from "there is data somewhere" to something concrete: a model-ready table, a dashboard, a map, a notebook, or a short explanation of what the evidence can and cannot say.

Focus areas

Energy & renewables analytics

KPI reporting, operational data checks, and infrastructure questions where the numbers need context before anyone should act on them.

Forecasting-oriented analysis

Weather-linked, trend-based, and operational analysis with uncertainty kept in view instead of tidied away.

Geospatial analytics

Districts, stations, polygons, land cover, and the small spatial mismatches that quietly break otherwise sensible analysis.

Data engineering for analytics

ETL/ELT, DuckDB and SQL-first work, QA checks, lightweight tests, and small systems that make a result repeatable after the first successful run.

AI-assisted analytics automation

I use AI tools where they help with review, documentation, and boring glue work, while keeping the actual analytical claims tied to data I can inspect.

Explore my work Portfolio GitHub CV LinkedIn

Highlights

Featured case study

Agri-Weather-Yield Drivers

6 Apr 2026

A weather, yield, soil, and geospatial analysis project for risk-aware siting and environmental review.

Pinned projects

  • Crude Oil Benchmark Analytics

    Built the first public crude benchmark visual bundle, including interactive API/sulfur and regional context views.

  • agri-weather-yield-drivers

    Built a rerunnable analytics pipeline for risk-aware siting conversations, with transparent assumptions and map-ready layers.

Browse the full project list on /portfolio .

How I work

I like taking analytical problems end-to-end, especially the parts that decide whether the final number is trustworthy.

  • Start with the actual business, operational, or research question.
  • Write down the metric definitions before they drift.
  • Build the dataset and keep the awkward assumptions visible.
  • Check quality, joins, coverage, and the places where the data gets thin.
  • Ship dashboards, reports, notebooks, or reusable outputs that someone else can maintain.