Doktorand Predictive Analytics als Analyst / Consultant (w|m|d) | findic
zeb consulting · BE, DE
5 days agoImpress employers and recruiters.
Choose from hundreds of resume examples.
Impress employers and recruiters.
Choose from hundreds of resume examples.
Tailor your resume to this Doktorand Predictive Analytics als Analyst / Consultant (w|m|d) | findic role.
Rezi rewrites your resume against zeb consulting's job description. Free.
Tailor your resume to this Doktorand Predictive Analytics als Analyst / Consultant (w|m|d) | findic role.
Rezi rewrites your resume against zeb consulting's job description. Free.
Don't guess if your resume is good enough.
See how it scores against the Doktorand Predictive Analytics als Analyst / Consultant (w|m|d) | findic posting at zeb consulting — free, in seconds.
Don't guess if your resume is good enough.
See how it scores against the Doktorand Predictive Analytics als Analyst / Consultant (w|m|d) | findic posting at zeb consulting — free, in seconds.
Responsibilities
- Develop innovative predictive analytics methods to derive reliable probabilities and sound data-based decisions from statistical forecasts.
- Investigate methods of model calibration, uncertainty quantification, and conformal prediction, evaluating their suitability for robust forecasts and sound decisions under real data conditions.
- Develop machine learning models and ensemble architectures for tabular data, analyzing when more complex models offer measurable added value over established methods.
- Develop evaluation methods that consider discrimination power, probability calibration, statistical uncertainty, temporal changes, and economically relevant decision thresholds.
- Translate current research into innovative AI solutions for banks and insurance companies, for example, for risk assessment, pricing, and customer management.
Requirements
- Possess a very good Master's degree in Statistics, Mathematics, Computer Science, Economics with a quantitative focus, or a related field, and are currently pursuing or about to begin a doctorate.
- Have sound knowledge of Python and the classic ML stack (e.g., NumPy, pandas, scikit-learn), ideally complemented by XGBoost, LightGBM, or CatBoost.
- Have a solid understanding of statistical modeling, model validation, and predictive evaluation, recognizing that high predictive accuracy does not automatically equate to well-calibrated probabilities.
- Can methodically distinguish between discrimination power and probability calibration and evaluate them with appropriate metrics (e.g., ROC-AUC and Average Precision for ranking quality, Log Loss and Brier Score for probabilistic forecasts).
- Are familiar with ECE and Reliability Diagrams as supplementary tools for calibration analysis and can contextualize the limitations of each metric.
- Have experience with time-based model validation and data leakage prevention, and are familiar with suitable methods like Purging and Embargo for overlapping label or observation periods.
- Possess very good German language skills (at least C1 level, business fluent) and good English language skills (at least B2 level, fluent) in speaking and writing.
Skills
- Platt Scaling
- Isotonic Regression
- Conformal Prediction
- Probabilistic Forecasting
- Ensemble Learning
- Stacking
- Time Series Forecasting
- Uplift Modeling
- Distribution Shift
- Concept Drift
- Bootstrap Confidence Intervals
- Time-based Model Validation
- Docker
- Model Versioning
- Monitoring
- Production Deployment of Machine Learning Models
Work Type
- Full-time
- Part-time
- Hybrid
Education Level
- Master's degree
- Doctorate