A/B-Testing-without-sampling

Welcome to my A/B Testing project! This project focuses on conducting an A/B test to evaluate the impact of 2 different variations of a website a conversion rates. The goal of this experiment was to test hypotheses and derive actionable insights that can improve decision-making.

📊 Objective

The primary objective of this A/B test was to:

• Test: different webpage layouts.
• Measure Impact: conversion rate.
• Determine: Whether one version (control or treatment) performs significantly better than the other in terms of the key metric.

🧪 Results

• Conclusion: There is no significant difference between two groups when performed Mann-Whitney U Test as the data is not Normally distributed.

🔧 Tools & Technologies Used

• Programming Languages: Python
• Libraries: Pandas, NumPy, SciPy, Matplotlib, Seaborn
• Data: From Kaggle
• Statistical Tests: K-Stest, Anderson-Darling test to check normality; Mann-Whitney U Test.

📂 Files in This Repository

• A/B_testing_without_sampling-Web_page_conversion.ipynb: Jupyter notebook used for cleaning and preparing the dataset and conducting the A/B test.

🔗 References

• Reference-1

---

"Experimentation is the key to data-driven decisions." 🚀