📈 Amazon Sales Prediction using Machine Learning

A complete end-to-end Machine Learning project focused on predicting Amazon sales using historical transaction data, feature engineering, and multiple regression models.

🚀 Project Overview

Accurately forecasting sales is critical for inventory planning, marketing strategy, and revenue optimization. This project applies data analytics and machine learning regression techniques to predict Amazon sales and uncover key business drivers behind revenue performance.

🎯 Problem Statement

To predict future sales/revenue using historical Amazon transaction data and identify the most influential factors affecting sales performance.

🧠 Machine Learning Approach

1️⃣ Data Collection

• Dataset loaded from CSV: Amazon Sale Report
• Contains transaction-level sales information

2️⃣ Data Cleaning & Preprocessing

• Handling missing values
• Removing irrelevant columns
• Encoding categorical features
• Feature selection
• Train-test split

3️⃣ Exploratory Data Analysis (EDA)

• Sales distribution analysis
• Trend and category-level insights
• Visualizations using Matplotlib & Seaborn

4️⃣ Model Building

The following regression models were trained and evaluated:

• Linear Regression
• Random Forest Regressor
• Gradient Boosting Regressor

5️⃣ Model Evaluation Metrics

• R² Score
• Mean Squared Error (MSE)

🛠️ Tech Stack

• Programming Language: Python
• Libraries:
  • NumPy
  • Pandas
  • Matplotlib
  • Seaborn
  • Scikit-learn

📈 Business Impact

• Helps forecast demand and revenue trends
• Supports data-driven inventory and marketing decisions
• Demonstrates real-world ML application for sales analytics

▶️ How to Run the Project

1. Clone the repository

   git clone https://github.com/your-username/amazon-sales-prediction.git
   

2. Install dependencies

   pip install -r requirements.txt
   

3. Open the notebook

   jupyter notebook "Amazon Sales Prediction.ipynb"
   

👤 Author

Soundharya Sundaram Iyer

📧 Email: soundharyaiyer99@gmail.com

🔗 LinkedIn: https://www.linkedin.com/in/soundharyaiyer09

💻 GitHub: https://github.com/Soundharya09

⭐ If you found this project useful, please consider giving it a star!