Python tool that monitors Meta Ads campaigns, calculates 7-day performance deltas and sends automated daily email alerts.
Маркетинговая аналитика: оптимизация рекламного бюджета по каналам Flow и Stock
Python CLI tool that analyzes your Google Ads search term reports to suggest, deduplicate, and export campaign-level negative keywords — saving hours of manual work.
Cohort retention and revenue-retention analysis on 1M+ Online Retail II transactions (2009–2011) — measuring repeat-purchase quality by acquisition month across 25 monthly cohorts.
Python script that detects conflicts between positive and negative keywords in Google Ads campaigns, preventing wasted spend and lost impressions from self-blocking negatives.
Customer segmentation using RFM analysis on 779K transactions — identifying 11 lifecycle segments from 5,878 UK wholesale customers with interactive Looker Studio dashboard
Multi-account Google Ads automation — tracking audits, GA4 setup, feed optimisation, weekly reporting, and AI recommendations. Integrates Google Ads, GTM, GA4, Merchant Center, Shopify, Monday.com, and Claude AI.
Google Ads campaign audit analyzing ₹31.4 lakh ad spend across 10 campaigns — identifying wasted budget, high CPA campaigns, and reallocation opportunities using Python and statistical analysis
End-to-end funnel analysis on an India-focused marketing dataset — segmenting acquisition drop-off by channel and tier-2 city to surface where budget is leaking across the top-of-funnel.
A/B test analysis with statistical significance testing plus a Random Forest conversion-prediction model on 588k marketing records — combining classical experimentation with interpretable machine learning and feature importance.
India-market Marketing Mix Modeling on 104 weeks of synthetic weekly spend data across 6 channels — recovering channel ROAS with adstock + saturation and recommending a quarterly budget reallocation plan.
Cross-channel ROAS benchmarking across 6 marketing channels — comparing efficiency of Google Ads, Meta, Amazon, Offline, LinkedIn, and Influencer spend using Python statistical analysis
Multi-touch attribution modeling comparing Last-Click, First-Click, Linear, Time-Decay, and Position-Based models on a digital marketing dataset — quantifying how channel credit shifts across attribution rules.
Add a description, image, and links to the performance-marketing topic page so that developers can more easily learn about it.
To associate your repository with the performance-marketing topic, visit your repo's landing page and select "manage topics."