연결

E-Commerce Analytics

rnavarychbyrnavarych
•
9
•
전자상거래 솔루션

Optimizes e-commerce performance through advanced conversion funnel tracking, customer segmentation, and data-driven revenue analysis.

This skill empowers developers and data analysts to implement sophisticated e-commerce tracking and analysis directly within Claude. It provides domain-specific guidance on building robust conversion funnels, calculating critical metrics like Customer Lifetime Value (CLV) and Average Order Value (AOV), and performing RFM customer segmentation. Whether you are debugging attribution models or designing statistically significant A/B tests, this skill ensures your e-commerce platform leverages data-driven insights to maximize revenue and acquisition efficiency.

주요 기능

019 GitHub stars
02RFM (Recency, Frequency, Monetary) customer segmentation logic
03Statistical design and analysis for high-rigor A/B testing
04Multi-model revenue attribution (last-click, first-click, linear)
05Cohort retention analysis for long-term customer value tracking
06End-to-end conversion funnel tracking and bottleneck diagnosis

사용 사례

01Implementing tracking for the browse-to-purchase customer journey
02Setting up dashboards for cart abandonment and repeat purchase rates
03Calculating CLV to CAC ratios to optimize marketing spend
name domain-ecommerce:ecommerce-analytics
description E-commerce analytics: conversion funnel tracking (browse to purchase), revenue attribution, cohort analysis, customer lifetime value (CLV), RFM segmentation, A/B test analysis (statistical significance), and key metrics (AOV, conversion rate, cart abandonment rate, repeat purchase rate).
allowed-tools Read, Grep, Glob, Bash

E-Commerce Analytics

When to use

  • Building or debugging conversion funnel tracking (browse → product view → cart → checkout → purchase)
  • Implementing revenue attribution models (last click, first click, linear, data-driven)
  • Running cohort retention analysis to compare acquisition cohorts over time
  • Calculating or predicting customer lifetime value (CLV) for CAC decisions
  • Segmenting customers with RFM (Recency, Frequency, Monetary) scoring
  • Designing or analyzing A/B tests with proper statistical rigor
  • Setting up a core e-commerce metrics dashboard with anomaly alerting

Core principles

  1. Segment every funnel — aggregate conversion rates hide the signal; break by device, source, and customer type
  2. CLV must outpace CAC 3:1 — anything lower and the acquisition engine is destroying value, not creating it
  3. Sample size before peeking — underpowered A/B tests produce false winners; calculate required n before starting
  4. RFM actions must differ per segment — Champions and Lost customers cost the same to email but have opposite expected ROI
  5. Alert on rate drops, not absolute counts — seasonal volume swings mask conversion rate problems in absolute metrics

Reference Files

  • references/funnel-attribution-cohorts.md — funnel stage definitions, tracking implementation, bottleneck diagnosis, attribution models, cohort analysis, CLV calculation
  • references/rfm-abtesting-metrics.md — RFM dimension scoring, segment actions, A/B test statistical design and reporting, core and operational KPI dashboard