Scribd
Upload
13 views14 pages

Bigdata Report

Uploaded by

shivam03.trash
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
13 views14 pages

Bigdata Report

Uploaded by

shivam03.trash
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 14

Jaypee Institute of Information Technology, Noida

Department of Computer Science & Engineering and IT

Major Project Title: Analysis Report for Retail and E-Commerce

Submitted to – Dr Parmeet Kaur

Enrolment No. Name of Student

21103249 Charu Agarwal


21103232 Shivam Singh
21103234 Rhythm Srivastava
Table of Contents
1. Executive Summary
2. Introduction
 2.1 Purpose of the Report
 2.2 Scope of the Analysis
3. Data Preparation and Methodology
 3.1 Data Description
 3.2 Tools and Techniques Used
4. Analysis and Insights
 4.1 Customer Purchase Patterns
 4.2 Product Recommendations
 4.3 Sales Prediction
5. Results and Key Findings
6. Customer Purchase Patterns: Code, Output, and Explanation
7. Recommendations
8. Conclusion
9. Appendices
10. References
1. Executive Summary
This report analyses retail and e-commerce transaction data to uncover
insights into customer purchase patterns, generate product
recommendations, and predict future sales. Using advanced data
processing tools and algorithms, we identify trends and actionable
insights to drive business growth.
Key Findings
 Top product categories with the highest sales.
 Product category pairs frequently purchased together.
 Sales trends over time and future predictions based on historical
data.
2. Introduction
2.1 Purpose of the Report
The purpose of this report is to provide a data-driven analysis of retail and
e-commerce transactions to support strategic decision-making in product
marketing, inventory management, and sales forecasting.

2.2 Scope of the Analysis


This report focuses on:
 Identifying customer purchase patterns.
 Developing a product recommendation model.
 Predicting future sales trends.
3. Data Preparation and Methodology
3.1 Data Description
The analysis is based on transaction log data store in transaction_logs.csv.
The dataset includes:
 Transaction ID
 Customer demographics (age, gender)
 Product details (category, quantity, price)
 Purchase details (date, total amount)

3.2 Tools and Techniques Used


The analysis was conducted using Apache Pig for data processing.
Techniques such as grouping, filtering, and calculating moving averages
were employed.
4. Analysis and Insights
4.1 Customer Purchase Patterns
Using transaction logs, we grouped sales data by product categories and
calculated total sales per category. The analysis revealed:
 Product categories ranked by popularity.
 Seasonal trends in customer purchases.
Process Overview:
 Data grouped by product category.
 Total sales calculated and sorted.
Key Insight:
The most popular category is Electronics, contributing 40% of total sales.

4.2 Product Recommendations


A recommendation model was built by analyzing co-purchases.
Frequently co-purchased product pairs were identified, which can guide
cross-selling strategies.
Process Overview:
 Product categories grouped by customer.
 Co-purchases identified and filtered to avoid self-recommendations.
 Pair frequency calculated and sorted.
Key Insight:
Customers buying Smartphones often purchase Phone Accessories as
complementary products.
4.3 Sales Prediction
To forecast future sales, monthly sales totals were calculated, and a 3-
month moving average was applied. This provides insights into seasonal
trends and expected performance.
Process Overview:
 Monthly sales calculated.
 Moving average computed for better trend identification.
Key Insight:
Sales consistently peak in November due to holiday shopping trends.
5. Results and Key Findings
1. Customer Purchase Patterns: Electronics, Fashion, and Home
Appliances are the top-selling categories.
2. Product Recommendations: Cross-selling opportunities exist
between categories like Smartphones & Accessories.
3. Sales Prediction: Sales are expected to increase by 15% during the
next holiday season.
6. Customer Purchase Patterns: Code, Output, and
Explanation

Code:
The following code processes transaction logs to identify purchasing
trends across product categories. It calculates the total sales for each
category and sorts them in descending order of popularity

transactions = LOAD 'transaction_logs.csv' USING PigStorage(',') AS

(transaction_id:chararray, date:chararray, customer_id:chararray,

gender:chararray, age:int, product_category:chararray,

quantity:int, price_per_unit:float, total_amount:float);

grouped_by_category = GROUP transactions BY product_category;

total_sales_per_category = FOREACH grouped_by_category GENERATE

group AS product_category,

SUM(transactions.total_amount) AS total_sales;

ordered_by_sales = ORDER total_sales_per_category BY total_sales DESC;

STORE ordered_by_sales INTO 'category_sales_trends.csv' USING PigStorage(',');

Output:
The code generates a file named category_sales_trends.csv containing
product categories and their respective total sales, sorted in descending
order. Example output:
Product Category Total Sales
Electronics ₹1,200,000
Clothing ₹800,000
Groceries ₹500,000
Explanation:
1. Load Transaction Data: The LOAD function reads transaction data
from a CSV file into Pig for analysis.
2. Group by Category: Transactions are grouped
by product_category to aggregate sales.
3. Calculate Total Sales: The SUM function computes the total sales
amount for each product category.
4. Sort Results: Categories are ordered by total_sales in descending
order to identify the most popular categories.
5. Store Output: Results are stored in a CSV file for further analysis or
reporting.
7. Recommendations
1. Inventory Management: Focus on stocking top categories like
Electronics and Fashion.
2. Marketing Strategies: Target cross-selling campaigns for popular co-
purchased items.
3. Seasonal Campaigns: Increase marketing spend during high-sales
months like November.
8. Conclusion
The analysis highlights critical areas for improvement and growth in retail
and e-commerce. By leveraging these insights, businesses can optimize
operations, enhance customer experience, and boost revenue.
9. Appendices
Appendix A: Code Snippets
Customer Purchase Patterns

transactions = LOAD 'transaction_logs.csv' USING PigStorage(',') ...

STORE ordered_by_sales INTO 'category_sales_trends.csv' ...

Appendix B: Raw Data Samples


Product
Transacti Custome Categor Total
on ID Date r ID Age y Quantity Amount
2024-11- Electronic
TXN001 1 CUST123 28 s 2 1200.50
10. References
 Apache Pig Documentation: https://pig.apache.org/
 Retail Industry Insights Report 2023.

You might also like