About Me
Designed and implemented customer segmentation frameworks (VAP, RFM, K-Means clustering) to identify high-value cohorts, improving campaign targeting precision and audience relevance. Built and deployed ML models (Logist…
Designed and implemented customer segmentation frameworks (VAP, RFM, K-Means clustering) to identify high-value cohorts, improving campaign targeting precision and audience relevance. Built and deployed ML models (Logistic Regression, Random Forest) for conversion and engagement prediction, driving measurable improvements in campaign ROI across marketing use cases. Led A/B testing and experimentation pipelines, applying statistical significance testing to evaluate campaign effectiveness and support data-driven optimization decisions. Developed scalable data pipelines using SQL, SAS, and Databricks to process and transform large-scale customer datasets for downstream analytics and model consumption. Engineered end-to-end ML workflows covering feature engineering, model validation, hyperparameter tuning, and performance evaluation using standard ML metrics. Collaborated with cross-functional stakeholders (marketing, product, strategy) to translate ambiguous business problems into structured, data-driven analytical solutions. Applied predictive modelling and campaign optimization techniques to support lifecycle marketing, retention, and acquisition strategies at scale.
Experience
Associate Data Scientist
Developed and operationalized customer segmentation frameworks using VAP and RFM, enhanced with K-Means clustering, improving targeting effectiveness by 15–20% across multiple campaign cohorts. Built and deployed predictive models (Logistic Regression, Random Forest) for customer conversion and engagement, delivering 10–15% uplift in campaign ROI compared to baseline targeting approaches. Designed and executed A/B experiments with statistical validation and causal analysis, increasing engagement rates by 8–12% across targeted segments. Engineered and optimized data pipelines using SQL, SAS, and Databricks to process large-scale datasets (millions of records), improving processing efficiency by 25%+. Led end-to-end ML workflows, including feature engineering, model training, cross-validation, and performance evaluation (AUC, precision-recall). Worked closely with cross-functional stakeholders to translate complex business requirements into scalable data science solutions, enabling informed decision-making and measurable business impact.