growth-model-analyzer

Uplift modeling uses machine learning with XGBoost to estimate incremental impact on individual users by comparing treatment and control groups. This Skill applies statistical testing and effect-size measures to quantify which users respond most to campaigns, enabling targeted ROI optimization across digital channels.

RFM segmentation clusters customers by Recency, Frequency, and Monetary value using KMeans and pandas preprocessing. This Skill automates segmentation, visualization, and targeting insights to guide resource allocation and identify high-value customer groups for retention and expansion.

Yes. This Skill evaluates funnel conversions and campaign impact using Chi-squared and t-tests to measure statistical significance, calculates effect sizes with Cramer's V and Cohen's d, and generates Qini curve analysis to quantify uplift across treatment segments.

This Skill provides scripts that load growth data, preprocess with pandas and numpy, run statistical and ML analyses including XGBoost uplift modeling, generate Plotly and Matplotlib visualizations, and produce automated reports linking funnel performance, segmentation, and ROI outcomes.

Uplift modeling requires sufficient treatment and control observations to avoid overfitting; small samples weaken statistical power and effect-size estimates. This Skill applies Chi-squared and t-tests to validate assumptions, but results lose reliability when group sizes are severely imbalanced or below minimum thresholds.