ProData Consult
Machine Learning (advanced)
Catboost (advanced)
XGBoost (advanced)
Python (advanced)
Catboost (advanced)
XGBoost (advanced)
Python (advanced)
PROJECT INFORMATION:
- Industry: e-commerce
- Location: 100% remote or from client’s office in Warsaw
- Project language: Polish, English
- Assignment type: B2B
- Remuneration: Up to 200 PLN/H +VAT
- Start: Flexible
PROJECT ROLE:
E2E delivery of credit risk models including:
- New features creation based on current models’ errors
- Tuning models after auto-ml phase
- Extending internal ml library
- Calibrating scores to observed probability of default
- Optimizing treshold of optimal automated decisions
REQUIREMENTS:
- Min. 4 years of professional experience
- Very good knowledge of Python (Sklearn, Hyperopt, Pandas, NumPy, LGBM)
- Machine Learning (at least one model deployed to the production environment that made automated decisions)
- Excellent knowledge of gradient boosting algorithm (LGBM, xgBoost, Catboost)
- Feature Engineering (experience with features (predictors) creation from multiple sources, ability to write easily extendable and maintainable SQL code)
- Optimization (experience with the calculation of optimal thresholds for automated decisions)
- Good knowledge of linear models (logistic regression with regularization)
- Knowledge of the influence of the train sample definition on model outputs
- Knowledge of model validation techniques
WE OFFER:
- Work in the international environment within the Scandinavian business culture
- Co-financing of private medical care (Medicover) and the Multisport card
- Recommendation program
- ProData Consult mobile application – easy reporting of working time, quick access to new offers
Source ⇲
feeds.talent.com