We need a resource—ideally a data scientist—who can help prototype and validate this in the client’s environment. Key capabilities:

• Statistical / econometric modeling (logistic & log-log regressions, hierarchical shrinkage)
  

• Price-optimization or revenue-management experience
  

• Python data stack (pandas, numpy, statsmodels, scikit-learn or PyMC)
  

• Decision-tree segmentation and clustering
  

• Simulation / scenario analysis for guard-rail testing
  

• Solid SQL & data-engineering fundamentals
  

Desired Skills and Experience

Develop, implement, and optimize time series forecasting models.
Build and maintain end-to-end ML pipelines for data ingestion, preprocessing, model training, and deployment.
Apply machine learning algorithms (regression, classification, ensemble methods, boosting, etc.) to business use cases.
Design and train deep learning architectures (LSTM, GRU, CNNs, Transformers) for sequential and structured data.
Perform feature engineering, hyperparameter tuning, and model evaluation.
Collaborate with data engineers to ensure data quality, scalability, and efficient model deployment.
Deploy models to production environments.
Familiarity with MLOps best practices (versioning, monitoring, CI/CD for ML).
Monitor, retrain, and maintain models for continuous improvement and drift detection.
Document processes, models, and findings to ensure knowledge sharing and reproducibility