Thanks to visit codestin.com
Credit goes to www.scribd.com

Scribd
Upload
3K views16 pages

Business Analytics Project

The document discusses a business analytics project aimed at improving store operations and sales. The objectives are to determine optimal stock levels to prevent outages, predict frequently purchased products, and increase sales through bundling and store design. The dataset contains over 14,000 customer transactions over 2 years for stores in California, Orlando, and Washington. Neural networks and market basket analysis were used to analyze purchase patterns and identify out-of-stock items. Recommendations include co-locating commonly purchased items and adjusting product placement based on regional preferences.

Uploaded by

KASI
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
3K views16 pages

Business Analytics Project

The document discusses a business analytics project aimed at improving store operations and sales. The objectives are to determine optimal stock levels to prevent outages, predict frequently purchased products, and increase sales through bundling and store design. The dataset contains over 14,000 customer transactions over 2 years for stores in California, Orlando, and Washington. Neural networks and market basket analysis were used to analyze purchase patterns and identify out-of-stock items. Recommendations include co-locating commonly purchased items and adjusting product placement based on regional preferences.

Uploaded by

KASI
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 16

BUSINESS ANALYTICS

Aniket Kulkarni
Mohsin Ahmed

Dinesh Reddy Vakiti


Mohd.Khalid Saifullah
Sarvesh Kumar Gantala

PROJECT OBJECTIVES
To decide on the type of stock to keep in each store and to have a steady
supply of these SKUs to prevent stock outs,
To predict the most frequently bought products by customers for:
1.

To prevent stock out of items

2.

Increase in sales and walk-ins based on customer taste and need in


respective regions.
By bundling products
Efficient Store Design

Microsoft Excel
Worksheet

DATASET

Number of instances -14060 for Supermarket. Excel


December 2012 to December 2014

Purchase Customer Gende Marital


Date
ID
r
Status

Homeowner

Childr Annual
en
Income

City

State or
Province

Country

Product
Family

Product
Department

Product Category

Units Revenu
Sold
e

12/18/2012

7223

$30K $50K

Los
Angeles

CA

USA

Food

Snack Foods

Snack Foods

$27.38

12/20/2012

7841

$70K $90K

Los
Angeles

CA

USA

Food

Produce

Vegetables

$14.90

12/21/2012

8374

$50K $70K

Bremerton

WA

USA

Food

Snack Foods

Snack Foods

$5.52

12/21/2012

9619

$30K $50K

Portland

OR

USA

Food

Snacks

Candy

$4.44

12/22/2012

1900

$130K $150K

Beverly
Hills

CA

USA

Drink

Beverages

Carbonated
Beverages

$14.00

12/22/2012

6696

$10K $30K

Beverly
Hills

CA

USA

Food

Deli

Side Dishes

$4.37

12/23/2012

9673

$30K $50K

Salem

OR

USA

Food

Frozen Foods

Breakfast Foods

$13.78

12/25/2012

354

$150K +

Yakima

WA

USA

Food

Canned Foods

Canned Soup

$7.34

12/25/2012

1293

WA

USA

NonConsumable

Household

Cleaning Supplies

$2.41

$10K Bellingham
$30K

Description of Variables
Purchase Date Date of purchase

Numeric for 2012,2013,2014

Customer ID Customer Transaction Card

Numeric

Gender

String M, F

Marital Status

String- M, S

Homeowner

String Y,N

Children

Numeric

Annual Income

Numeric

City

String

State or Province State or Province

String CA,WA, OR

Country

String - US

Product Family

String

Product Department

String

Product Category

String

Units Sold

Numeric

Revenue

Numeric

DATA
Data collected was over a period of 2 years
We have divided the data basis of states; California, Orlando , Washington

Methodology

Neural Network
Market Basket Analysis

RESULTS & DISCUSSION

Neural Networks
WASHINGTON
Model predicted that, there is high percent of stock outs in Tacoma City

Neural Networks
Orlando
Model predicted that, there is high percent of stock outs in Salem City

Neural Networks
WASHINGTON
Model predicted that, there is high percent of stock outs in Tacoma City

Market Basket Analysis


ORLANDO

Description
Checkout

Items
Frozen Foods
Beverages
Periodicals

Market Basket Analysis


WASHINGTON
85% probability that customer can pickup meat, eggs, Deli Soups, Carousel
and starchy products

Description
Checkout

Items
Meat
Deli Soups
Carousel
Starchy Products
Eggs

Market Basket Analysis


California

Description
Checkout

Items
Diary
Canned Foods
Carousel
Alcoholic Beverages
Periodicals

Recommendations
California:
Design the stores in such a way that Diary products, canned foods, Carousel are kept near to
each other.
Alcoholic Beverages are least preferred, so they should be kept far from Counter.

Orlando
Seafood is heavily consumed
Sea food and meat should kept beside each other.
Beverages & Frozen food can be bundled. This will result in increase of the sale.

Washington
Maintain eggs, starchy foods near the checkout points in the store
Deli soups in the middle aisle
Meat is also highly preferred by the customers. So they can be kept at the corner of the store

!
!
!
u
o
Y
k
n
a
h
T

You might also like