Junior Data Analyst

Researched customer needs and developed comprehensive functional specifications. Created test cases
and executed assessments. Collaborated with project key stakeholders and oversaw the specifications
life span. Formulated delivery paperwork for the assignments, comprising acceptance criteria.
Utilized BPMN notation to design activity diagrams as well as flow diagrams (draw.io). Engaged in
user acceptability training and user acceptance testing.

Performed product metrics (DAU, MAU, WAU, CTR, Retention) analysis with visualization in dashboards
using Superset. Analyzed users' behaviors and trends, and analyzed the effectiveness of the
marketing campaign in attaining and retaining the users. Performed A/B tests and made
recommendations on whether the specific features should be deployed to production. Created ETL
pipeline (Airflow, ClickHouse). Performed report automatization by sending the key metrics report
once a day to Telegram chat. Created anomaly detection system that is monitoring the product metrics
every 15 minutes and in case of any anomalies the alert is sent to Telegram chat automatically.
A/B tests: https://github.com/KateBaburina/Product-Analytics---AB-testing
ETL pipeline: https://github.com/KateBaburina/Product-Analytics---ETL
Report automation: https://github.com/KateBaburina/Product-Analytics---Report-Automation
Anomaly detection system: https://github.com/KateBaburina/Product-Analytics---Alerts

Involved in gathering data, interpreting statistics, writing reports, and designing charts and
graphs. Executed analysis by utilizing data science platforms as well as creating predictive models
for classification, regression, and clustering by implementing the following algorithms, including
logistic regression, decision tree, decision forest, decision jungle, gradient boosted trees, and
random forest. Performed ABC, XYZ, and RFM marketing analysis, and created dashboards with KPIs and
other business metrics.
Projects completed:
Python - solving Churn task - XGBoost, CatBoost, Random Forest, Light Gradient Boosting Machine,
Gradient Boosting, Extremely Randomized Trees, H2O AutoML: https://github.com/KateBaburina/Predictive-Modeling---Employee-Attrition
Google BigQuery - predictive models - solving Churn task - Linear Regression, XGB: https://github.com/KateBaburina/Predictive-Modeling---BigQuery
Data Science Platforms - predictive models - solving Churn task - Logistic Regression, Decision
Tree, Decision Forest, Decision Jungle, Gradient Boosted Trees, Random Forest: https://github.com/KateBaburina/Predictive-Modeling---Data-Science-Platforms
Final report with Predictive Modeling for Sales Predicting using Time Series (BigQuery, Python,
Tableau): https://github.com/KateBaburina/Predictive-Modeling---Time-Series-Tableau-Visualizations

~~Tableau visualizations and dashboards, clustering, and Time Series:
Customers with the Highest Profit
Customers with the Lowest Profit
Sales Forecast using Tableau TS
Dashboard with KPI and Clustering for Customers
~~QlikSense dashboards:
Retail KPIs
Sales/Sub-Category Insights