Проекты

Volta Neobank — Product Analytics

End-to-end neobank analytics narrative — funnel, A/B test, retention, segmentation. Four sequential projects on synthetic fintech data with reproducible seeded pipelines and ship-gated statistical methodology.

Эффект: +6.24pp KYC conversion (Z=6.35, p<0.0001), €716K/yr (48× ROI), +9.2pp M3 retention, +€227K/yr incremental LTV, 4 data-driven user segments with per-segment monetization strategy, CUPED variance reduction + AA-test (type-I = 0.050) + Bonferroni correction

A/B Testing Methodology Toolkit

Calibration-driven A/B testing methods, validated by simulation — SRM, CUPED, delta-method ratio metrics, alpha-spending boundaries, always-valid p-values (mSPRT), bootstrap CI, HTE, multiple-comparison correction, novelty/primacy and switchback designs. Every module ships with an A/A null check and a power/coverage calibration.

Эффект: 15 модулей, каждый откалиброван симуляцией: Type I error ≈ α, power-кривые, CUPED: SE сжимается в ~corr(X,Y)² раз, Наивный peeking раздувает Type I error — Pocock/OBF и mSPRT держат его под контролем, Delta-method даёт корректный SE для ratio-метрик (CTR, RPC) — наивный per-unit t-test смещён, End-to-end pipeline: SRM → CUPED → delta-method CTR → сегментные ATE + BH → novelty check

Sales Calls Analytics Dashboard

Streamlit-дашборд аналитики ИИ-обзвона: воронка из 4 шагов (приветствие → оффер → встреча → квалификация), разбор главной утечки по типам, взвешенные потери контактов, реакции клиентов, вовлечённость по часам и дням, качество бота и drill-down в транскрипты обрывов.

Эффект: 16 891 синтетический звонок, разметка детерминированная (маркеры скрипта), 4-шаговая воронка: приветствие → оффер → встреча → квалификация, Главная утечка разбирается по типам (молчание / сброс / отказ) + взвешенная потеря контактов, Вовлечённость по часам и дням недели — когда звонить, Хук под LLM-разметку реакций (llm_labels.csv) — пайплайн воспроизводим и без него

SQL Analytics Case Study

Ten end-to-end SQL case studies on a synthetic product dataset (~183k events), runnable on DuckDB with one command. Funnel, N-day retention, DAU/MAU stickiness, LTV, gaps-and-islands streaks, A/B conversion, and revenue attribution.

Эффект: 10 self-contained SQL cases (funnel → attribution), DuckDB — no server, no credentials, one command, Regression tests with deterministic invariants per case, Synthetic deterministic data (seed=42, ~183k events)

RFM Analysis of Bank Clients

RFM analysis of bank clients to segment users by Recency, Frequency, and Monetary metrics. Surfaced key customer groups, optimized marketing campaigns, and improved retention efficiency.

Эффект: Identified high-value customer segments, Optimized marketing campaigns, Improved retention efficiency

Cohort Analysis Dashboard

Cohort retention and LTV analysis on synthetic data — retention curves, churn patterns, and revenue/LTV by acquisition cohort. Python pipeline (pandas + matplotlib/seaborn) plus a Tableau-ready export with CSV and Hyper extract.

Эффект: Cohort retention matrix with triangular decay, ARPU / LTV by cohort with proper observation-age caveat, Tableau-ready export (CSV + .hyper extract), Reproducible seeded pipeline (seed=42)

Product Analytics + A/B on Supabase

Full-stack product analytics platform — a Streamlit dashboard reading live Supabase Postgres through Row Level Security, plus an Edge Function ingest API and a concluded A/B experiment with SQL-computed conversion and a chi-square significance test.

Эффект: Full-stack: Streamlit UI + Supabase Postgres + Edge Function ingest (API-key auth), Row Level Security on every table — a user sees only their org's rows, SQL views compute funnel, cohort, MRR, DAU, channel conversion — the dashboard reshapes, it does not aggregate, A/B result in the DB: control 32.1% vs treatment 37.2%, p = 0.0034 (chi-square)

Репозиторий приватный — доступ по запросу

TaskFlow — PostHog Product Analytics Pipeline

End-to-end portfolio project — instrument a SaaS product with PostHog, generate realistic traffic, and analyze the events into a funnel, cohort retention, an A/B test, revenue/LTV, and time-to-convert, all in Python.

Эффект: Typed event catalog (single source of truth) + PostHog capture/identify/group with PII scrubbing, Feature flag → onboarding A/B variant; A/B analysis with chi-square, uplift, Wilson CI + SRM check, Day-N cohort retention, time-to-convert, revenue/LTV, first-feature → upgrade conversion, The same metrics as SQL (BI / interview reference) + interactive Streamlit dashboard, CI (pytest + ruff) + Docker + render.yaml for one-click deploy

Репозиторий приватный — доступ по запросу

Product Analytics Dashboard (Streamlit)

A self-contained product analytics dashboard on a synthetic SaaS dataset (8,000 users). Covers the AARRR funnel, cohort retention, revenue, and user segmentation.

Эффект: 8,000 synthetic users, Jan 2024 – Jun 2025, deterministic seed = 42, AARRR funnel: app_open → signup → activate → start_trial → subscribe with step drop-off, Cohort retention heatmap (signup month × months since signup), Revenue: MRR growth, MRR by plan, ARPU, logo churn, Segments: distributions + conversion + ARPU by segment / channel / country / device

Репозиторий приватный — доступ по запросу

Reporting Automation Telegram Bot

A Telegram bot that automates weekly reporting and integrates with external APIs. Cuts time on routine tasks, ensures timely delivery of key metrics, and improves team communication.

Эффект: Cut weekly report prep from 1–2h to automated cron, KPI table + sparklines delivered on schedule, Fallback notifications on source failures, Single consolidated pipeline replacing fragmented sources

Scrolly English Speaking

Scrollytelling-гайд по улучшению spoken English для рабочих разговоров (A2–B1) — построен на Astro 6 с MDX-нарративом и D3-визуализациями. Контент и визуализации разделены: MDX хранит текст, data-модули — структуру секций и props визуализаций.

Эффект: Scrollytelling-нарратив на Astro 6 + MDX, D3-визуализации (workflow, bars, calendar, checklist), Контент и визуализации разделены — доверенный data-модуль, frontmatter безопасно мёржится, Интерактивные viz-панели через IntersectionObserver + dark/light тема + reduced-motion, Деплой на GitHub Pages по subpath, Node 22, `astro check` в CI

Digital Garden

A personal digital garden and Zettelkasten published as a website with Quartz v4 — linked notes, backlinks, graph view, and atomic evergreen notes instead of chronological blog posts.

Эффект: Linked-notes Zettelkasten with backlinks + graph view, Atomic evergreen notes over chronological posts, Quartz v4 — TypeScript-extensible, static output, Obsidian-flavored Markdown → public site

This Portfolio Site

The portfolio you are looking at — built with Astro v5, TypeScript, and Markdown content collections. Static output, dark/light theme, RSS, sitemap, JSON-LD, and a base-path-aware URL helper for GitHub Pages.

Эффект: Astro v5 + TypeScript + Markdown content collections, Dark/light theme with no-flash inline script, RSS, sitemap, robots, JSON-LD, OG/Twitter meta, Base-path-aware URLs for GitHub Pages subpath hosting