Bayesian marketing toolbox in PyMC. Media Mix (MMM), customer lifetime value (CLV), buy-till-you-die (BTYD) models and more.

A Practitioner’s Guide to Causal Inference, Marketing Mix Modeling, Pricing, Forecasting, and Customer Analytics

FLO wants to determine roadmap for sales and marketing activities. In order for the company to make a medium long -term plan, it is necessary to estimate the potential value that existing customers will provide to the company in the future.

TRACE: a transformer model and the Trajectory-Signal Validity (TSV) test for auditing trajectory signal in early high-value customer (CLV) prediction. Reference implementation accompanying the paper.

🚀 EcomOpti: 6-phase ML pipeline for telco churn prediction, CLV estimation & retention campaign optimization. Features survival analysis, causal uplift modeling, budget optimization, FastAPI microservice & interactive Power BI-style Dash dashboard.

WorthSignal — an open, local-first customer value toolkit for marketers: RFM, CLV, customer equity, retention, BG/NBD and BG/BB

End-to-end customer analytics project — segmenting 5,878 customers using RFM scoring, cohort analysis & CLV modelling to uncover £41M in revenue at risk. Built with Python, MySQL & Power BI.

This repository contains a collection of marketing calculators implemented in Python. These tools are designed to assist marketers, business analysts, and students in performing essential calculations related to customer lifetime value, economic value to the customer, linear interpolation, and relative importance of attributes.

Production-grade analytics platform for a vehicle e-commerce marketplace. Airbyte → Snowflake (medallion) → dbt → Dagster → Elementary + Great Expectations → Power BI.

Data-driven customer retention strategy using churn risk, customer value, and ROI-based intervention simulation on the Online Retail II dataset.

A Power BI and SQL-based dashboard offering insights into customer behavior, sales trends, and predictive models like churn and Customer Lifetime Value (CLV). This project utilizes a Kaggle dataset, Python for data preprocessing, SQL for data management, and Power BI for dynamic, interactive visualizations.

End-to-end Customer Lifetime Value (CLV) prediction pipeline using RFM analysis and CatBoost

This project aims to perform customer segmentation and revenue prediction for a gaming company based on customer attributes. The company wants to create persona-based customer definitions and segment customers based on these personas to estimate how much potential customers can generate in revenue.

This project involves performing customer segmentation and RFM (Recency, Frequency, Monetary) analysis on customer data from a retail company. The primary goal is to categorize customers into segments based on their buying behavior and identify potential target groups for marketing campaigns.

RFM + K-means segmentation with a customer-lifetime-value model and a per-segment action playbook.

Customer churn prediction, RFM segmentation, CLV estimation with XGBoost + SHAP explainability

Retail ML platform: CLV, customer segmentation, fraud detection and price optimization

Brazilian e-commerce customer analytics: CLV, churn, RFM segmentation, and sales forecasting on 96K+ Olist orders

End-to-end customer intelligence platform for CLV prediction, churn modeling, segmentation, and retention recommendations using retail transaction data.

Four customer models on 776k real UK retail transactions: KMeans segmentation, CLV, XGBoost repurchase prediction with SHAP, and a two-stage item2vec recommender. Temporal split, baselines for every model, served behind a FastAPI.