- Design and build standalone quantitative models for forecasting, optimization, scoring, pattern detection, and relationship analysis.
- Develop model components with defined inputs, outputs, assumptions, performance expectations, and testing criteria.
- Build and maintain data pipelines combining historical data, vendor inputs, market signals, trend data, and other enterprise sources.
- Prepare model-ready features from incomplete, inconsistent, or unreliable data.
- Develop backtesting and evaluation frameworks to compare model outputs with historical outcomes.
- Validate model performance, accuracy, reliability, confidence ranges, and limitations.
- Monitor model drift, input quality, accuracy changes, and data-source reliability; define retraining, reweighting, or escalation triggers.
- Register models with versioning, explainability, and audit support, and document model interfaces and behavior.
- Collaborate with business analysts, AI platform teams, and governance teams to integrate models with downstream systems.
- Support user acceptance testing by explaining model outputs and tradeoffs to stakeholders.
PythonMachine LearningPandas+1 more