Reporting and BI
Recurring KPI reporting, dashboard delivery, and ETL-backed reporting are strongest in my current professional data work.
Review 4 matching itemsThis index reuses reviewed portfolio facts and links each item back to the professional role or project section that supports it. It adds no new employment, project-result, or model-performance claim.
Every card keeps the supporting context visible and provides a direct route to deeper detail.
Recurring KPI reporting, dashboard delivery, and ETL-backed reporting are strongest in my current professional data work.
Review 4 matching itemsSchema standardization, validation, guarded ingestion, and repeatable pipelines show how I make recurring data work easier to trust.
Review 8 matching itemsCase studies show baseline comparison, out-of-sample validation, and explicit model limitations across classification, volatility, and forecasting.
Review 4 matching itemsMarket-facing projects emphasize provenance, risk context, model state, and decision boundaries instead of unqualified signals.
Review 2 matching itemsCombine an evidence type with a hiring focus to review the most relevant proof quickly.
Showing all 12 evidence items.
Change one filter or reset the explorer to return to the full evidence set.
Automated from a pricing workbook through a Python ETL workflow at Avomind.
Avomind, Junior Data Controller
Supported through two KPI views alongside reporting for 38 to 39 researchers.
Avomind, Junior Data Controller
Validated after standardizing a 134-column schema across three annual workbooks.
Avomind, Junior Data Controller
9,072 successful archived walk-forward forecast rows with 0 failed archived rows.
Portfolio evidence reviewed 2026-09-07
Recorded product scope covers 12 analytical areas with daily research and weekly model-governance design.
Portfolio evidence reviewed 2026-08-29
Validation F1 0.9291 with average precision 0.9788 on the fixed stratified rebuild holdout.
Portfolio evidence reviewed 2026-08-29
The public production route is live, while live acquisition, warehouse coverage, and current data behavior remain separate verification gates.
Portfolio evidence reviewed 2026-09-07
Historical MAPE 4.08%, retained as a historical result until a leakage-safe rebuild proves comparable validity.
Portfolio evidence reviewed 2026-08-29
Python · pandas · NumPy · SQL · R · statistical analysis · KPI reporting
Evidence links point to current CV or case-study sections.
Looker Studio · Google Sheets API · Google Apps Script · ETL scripting · HubSpot CRM · Power BI · Tableau
Evidence links point to current CV or case-study sections.
scikit-learn · LightGBM · Prophet · GARCH · forecast evaluation · baseline comparison
Evidence links point to current CV or case-study sections.
Streamlit · FastAPI · Docker · GitHub Actions · data quality · LLM evaluation
Evidence links point to current CV or case-study sections.
Credibility depends on keeping unavailable evidence visible as a limitation instead of filling the gap.
No verified real project screenshot pixels are currently integrated. Existing project visuals remain generated snapshot graphics and are labeled as such.
Recruiter-facing live links are published only when the current portfolio verification state allows them. Recorded but unverified product URLs remain withheld.
Build-size budgets are measured locally. Field Core Web Vitals remain unmeasured and are not presented as verified results.