This article walks through a complete data‑driven study of Taobao app user actions, using SQL and Python to ingest 2 million records, applying the AARRR funnel and RFM segmentation to quantify churn, retention, conversion rates, and to propose data‑backed marketing tactics.
This article analyzes a JD e‑commerce dataset using Python and MySQL to calculate key metrics such as PV, UV, conversion rates, attrition, daily activity, hourly trends, user‑behavior funnels, purchase intervals, retention rates, product sales, and RFM segmentation, and then offers data‑driven recommendations to improve traffic, conversion, and user loyalty.
This study analyzes JD e‑commerce operational data from February to April 2018, employing Python and SQL to compute key metrics such as PV, UV, conversion rates, attrition, purchase frequency, time‑based behavior, funnel analysis, retention, product sales, and RFM segmentation, and provides actionable recommendations for improving user engagement and sales performance.
This article explains how DataFun’s automated feature engineering and modeling platform dramatically reduces credit‑risk model development time from weeks to days by standardizing feature creation, integrating popular algorithms such as LR, XGBoost and LightGBM, and providing comprehensive evaluation, deployment and monitoring capabilities.
This article analyzes 2 million Taobao app user‑behavior records using AARRR funnel metrics and RFM segmentation, revealing daily and hourly usage patterns, conversion bottlenecks, product‑search mismatches, and offering data‑driven marketing recommendations to boost retention and sales.
This tutorial walks you through a real‑world example of constructing e‑commerce user profiles using Python, pandas, and matplotlib, covering data loading, preprocessing, feature engineering, behavior tagging, activity analysis, and RFM segmentation with clear code snippets and visualizations.
This article explains the background of shrinking traffic dividends, defines consumer equity and user segmentation, introduces common models such as AIPL and RFM, outlines step‑by‑step methods for behavioral, value, flow and attribution models, and provides real‑world case studies to illustrate how marketers can evaluate asset changes and optimize channel contributions.
This article demonstrates how to use Python's time, NumPy, and Pandas libraries to build an RFM (Recency, Frequency, Monetary) model for customer value segmentation, covering data preparation, score calculation, weighting strategies, and exporting the results for marketing insights.
This article walks through a comprehensive analysis of a 3.43 GB sales dataset from a Brazilian automotive service chain, covering data loading, cleaning, exploratory visualizations, time‑series forecasting with ARIMA, RFM customer segmentation, product clustering, and key business insights using Python and Tableau.
This article presents a complete data‑analysis workflow that scrapes Bilibili video metrics from January 2019 to March 2020, cleans and preprocesses 50,130 records, and extends the classic RFM model into an IFL framework—calculating interaction, frequency and like rates—to score and rank up‑creators across multiple categories, with code and datasets provided for replication.
This tutorial walks through a complete Python workflow for analyzing a month of Taobao mobile app data, covering data import, cleaning, feature engineering, traffic and behavior metrics, funnel conversion, RFM segmentation, and visualizations to reveal user patterns and business performance.
This article explains why many static data reports are ineffective, identifies the lack of judgment standards as the core issue, and offers three practical ways—problem‑based, goal‑based, and business‑based—to establish meaningful standards that make data analysis reports valuable.
This article explains why user segmentation is essential for modern product operations, introduces common models such as RFM, AIPL, and AARRR, explores demographic and targeted layering approaches, and offers practical design strategies for traffic allocation and personalized content delivery.
This article details how telecom operators can identify fraudulent ModemPOOL (cat‑pool) terminals and predict churn using data‑driven clustering and day‑interval warning models, covering metric selection, data exploration, k‑means clustering, model deployment, and performance evaluation.
