Your Name
Data Scientist
City, Country · email@example.com · linkedin.com/in/yourname · yourportfolio.com
Professional summary
Data Scientist with 5 years applying machine learning, forecasting, and experimentation to pricing and retention problems in e-commerce and telecom. Built a churn model that retained 9% of at-risk subscribers, designed A/B tests for product teams, and partners with engineers to put models into production. Skilled in Python, SQL, scikit-learn, XGBoost, and causal inference.
Skills
Python · Machine learning · SQL · Statistics · scikit-learn · Pandas · Feature engineering · Model evaluation · Experimentation · Data visualization · Git · ML pipelines
Experience
Senior Data Scientist — Company Name
2021 – Present
- Built an XGBoost churn model (AUC 0.86) to target retention offers, keeping 9% of at-risk subscribers in the first quarter.
- Developed weekly demand forecasts for 4,000 SKUs with LightGBM, reducing MAPE from 24% to 15% and cutting stockouts.
- Designed and analyzed 30+ A/B tests using CUPED variance reduction, shortening average test duration by 35%.
- Segmented 2M customers with k-means on RFM features, informing a campaign that raised email conversion by 14%.
- Productionized models with MLflow and scheduled batch scoring in Airflow, replacing notebooks that were run manually each month.
Projects
Credit Card Fraud Detection | Python, Pandas, scikit-learn, XGBoost, SHAP, Streamlit
- Handled a 0.17% fraud rate with class weighting and SMOTE, comparing logistic regression, random forest, and XGBoost.
- Reached 0.84 precision-recall AUC and tuned the decision threshold to balance missed fraud against false alarms.
- Explained predictions with SHAP values and presented the results in an interactive Streamlit app.