Data Scientist – Dynamic Pricing & Offer Optimization
Summary
Build ML models for dynamic pricing, offer optimization, and churn prediction using Python and MLOps, then deploy them into business decision engines.
At TechBiz Global, we are providing recruitment service to our TOP clients from our portfolio. We are currently seeking a Data Scientist to join one of our clients' teams. If you're looking for an exciting opportunity to grow in a innovative environment, this could be the perfect fit for you.
Key Responsibilities:
-
Build and deploy models for:
Price Elasticity / Conversion Prediction
Churn Propensity / Retention Uplift
Segment Discovery & Similarity (Clustering, KNN)
Offer Recommendation / Ranking (Scoring Models)
Design A/B testing and uplift modeling to evaluate campaign performance.
Develop simulation engines for pricing what-if analysis and scenario testing.
Create automated pipelines for model training, scoring, and retraining.
Work closely with Data Engineers to ensure feature store alignment.
Collaborate with the Business Decisioning team to translate insights into rules and thresholds.
Implement feedback loops using real-time events (purchase, rejection, expiry) to improve models.
Requirements
Required Skills:
Experience Level: 5–8 years in Applied Machine Learning, Statistical Modeling, and Data Science for large-scale systems
Strong foundation in Machine Learning, Statistics, and Econometrics.
Proficient in Python (pandas, scikit-learn, numpy, statsmodels, xgboost, lightGBM).
Experience with model lifecycle management (MLOps).
Solid understanding of telecom KPIs: ARPU, recharge frequency, wallet size, churn rate, etc.
Ability to design feature engineering pipelines and perform A/B testing.
Expertise in data visualization and storytelling for non-technical stakeholders
Preferred (Nice-to-Have):
Experience with Telecom Offer & Recharge Modeling or Dynamic Pricing Systems.
Knowledge of Pricefx PriceAI, Adobe Target Recommendations, or Reinforcement Learning frameworks.
Understanding of Elasticity Curves, Customer Lifetime Value (CLV), and Offer Fatigue Modeling.
Experience integrating ML outputs into business decision engines or rule systems.