Lookalike model using the Locality Sensitive Hashing algorithm to find similar users and increase the click rate compared to the default rate.
-
Updated
Dec 9, 2023 - Python
Lookalike model using the Locality Sensitive Hashing algorithm to find similar users and increase the click rate compared to the default rate.
This repository contains the solutions for the exploratory data analysis (EDA), building a lookalike model, and performing customer segmentation using clustering techniques.
Performed exploratory data analysis (EDA), built predictive models, and derived actionable insights.
This repository contains a comprehensive data science project analyzing eCommerce transaction data, implementing customer segmentation, and developing a lookalike model. The project showcases EDA, clustering techniques, and recommendation systems using Python.
ecommerce-Transactions-Dataset using Python, Pandas, NumPy,Scikit-learn,Power BI, Matplotlib, Seaborn,Machine Learning algorithms like K-Means clustering,Classification models like Logistic Regression, Random Forest
Includes EDA, Predictive models and some actionable insights of E-Commerce Transactions.
Customer analytics and segmentation project using K-Means clustering, EDA, and lookalike modeling. Assignment for Zeotap Data Scientist position. Analyzes 200 customers and 1,000 transactions with 5-cluster segmentation (DB Index: 1.05).
Add a description, image, and links to the lookalike-model topic page so that developers can more easily learn about it.
To associate your repository with the lookalike-model topic, visit your repo's landing page and select "manage topics."