0% found this document useful (0 votes)
14 views14 pages

Data Analytics CASE

ElectroMart, an e-commerce firm in Canada, is seeking to optimize its marketing budget for the upcoming year due to concerns about the effectiveness of past spending. The data analyst is tasked with analyzing various marketing variables to recommend budget allocations that enhance revenue performance. The analysis will include performance driver analysis, impact analysis on marketing ROI, and optimizing marketing spending using available data files and statistical methods.

Uploaded by

snehaltengse496
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
14 views14 pages

Data Analytics CASE

ElectroMart, an e-commerce firm in Canada, is seeking to optimize its marketing budget for the upcoming year due to concerns about the effectiveness of past spending. The data analyst is tasked with analyzing various marketing variables to recommend budget allocations that enhance revenue performance. The analysis will include performance driver analysis, impact analysis on marketing ROI, and optimizing marketing spending using available data files and statistical methods.

Uploaded by

snehaltengse496
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 14

DATA

ANALYTICS
CASE

Technology Students' Gymkhana

IIT Kharagpur

www.analytixlabs.co.in
1
Transforming Careers Since 2011

Leadership

2
Judge and Mentor

3
Business Context
ElectroMart is an e-commerce firm based out of Ontario, Canada
specializing in electronic products. Over the last year, they have spent a
significant amount of money on marketing. Occasionally, they also offered
big-ticket promotions (similar to the Big Billion Day offering by Flipkart in
India). They are about to create a marketing budget for the next year, which
includes spending on commercials, online campaigns, and pricing &
promotion strategies.

Stake Holders:
Rajesh – Director of ElectroMart
Sanya – Chief Marketing Officer
Pandey – Marketing Operations Team Lead

4
Business Problem
The CFO feels that the money spent over the last 12 months on marketing
was not sufficiently impactful, and, that they can either cut on the budget or
reallocate it optimally across marketing levers to improve the revenue
response

Imagine that you are a data analyst and supporting a marketing team and
the marketing team is working on budget optimization for the next year. As
part of this exercise, you are required to support the team by observing the
actual impact of different marketing variables over the last year. Using your
understanding of the data, you have to recommend the optimal budget
allocation for different marketing levers for the next year. (Note: This
required to be done using data analytics)

The objective is classified into the following sub-goals:


Performance driver analysis: Which KPIs drive the top-line (revenue)
performance?
Impact analysis on marketing ROI: What is the quantitative impact of
each commercial lever on revenue?
Optimizing marketing spending: How to best allocate the marketing
budget to gain the highest outcome?

5
Data Availability
The following data files were available to us for analysis:

Main Consumer file with customer order details on a daily basis


Media Investment file with the amount invested in each advertising
medium for the past year
Sale Calendar file showing dates from the past year when there was a
promotional offer
NPS file showing net promotion score and company stock value for last
year
Weather file having detailed weather reports from last year in the state
of Ontario, Canada
SKU Mapping with product hierarchy details to understand the product
hierarchy
Holidays list in Canada for the period of available data.

6
Data Description
Column Description for Customers_Orders.csv:

This table contains all the information about customer orders. You have to
use the data from July 2023 to June 2024. The data consists of the
following types of information:

FSN ID: The unique identification of each SKU (SKU => Stock Keeping
Unit)
Order Date: The date on which the order was placed
Order ID: The unique identification number of each order
Order item ID: Suppose you order 2 different products under the same
order, It generates 2 different order Item IDs under the same order ID;
orders are tracked by the Order Item ID.
Deliverybdays: days to get item or order from warehouse for shipping
Deliverycdays: days to deliver item to customer
GMV: Gross Merchandise Value or Revenue
Units: Number of units of the specific product sold
Order payment type: How the order was paid – prepaid or cash on
delivery
SLA: Number of days it typically takes to deliver the product
Cust id: Unique identification of a customer
Product MRP: Maximum retail price of the product
Product procurement SLA: Time is typically taken to procure the product

Note: You can assume "\N" value in deliverybdays & deliverycdays is equal to 0

7
Data Description

Description for “Media data-Sale Calendar-NPS Scores_Data.xlsx“

Media Spend: Monthly spending on various advertising channels


Sale Calendar: Days when there was any special sale
Monthly NPS score – this may work as a proxy to the ‘voice of the
customer’
Stock Index of the company on a monthly basis
Canada_holiday.xlsx: This helps to understand the holiday list for the
time period of data available

Description for “Product Hierarchy Details.docx”

FSN ID: The unique identification of each SKU


Super_Category: Product Super Category Information
Category: Product Category Information
Sub_Category: Product Sub-Category Information
Vertical: Product that belongs to which vertical

As the E-commerce company is situated in the Ontario region. Here, we will


include its climate data (Weather Data ONTARIO-2023.csv, Weather Data
ONTARIO-2024.csv) to analyze if it has any effect on the revenue.

8
Business Objective

Detailed Exploratory Data Analysis

Insights Generation & Detailed Presentation

Dashboards or Visualisation Creation

9
Expectations From Team
The team should Understand the below and document:
Business Context
Technology Stack
Available data
Problem Statement
List of Outputs to Generate
Assumptions Etc.
What technology stack do you want to use and why?
Detailed list of data checks to perform or can perform on this data.
Detailed list of data processing tasks to perform or can perform on this
data.
Detailed list of exploratory data analysis to perform or can perform on
this data.
Perform Univariate Analysis, Bivariate Analysis, Correlation, Cross-
tabs, and visualizations on the datasets. Obtain insights to solve the
business problem.
Detailed dashboards
KPI’s/KRA’s/KRI’s (Key Performance Indicators, Key Resultant Areas,
Key Risk Indicators)
Number of Dashboards
Reports in Each Dashboard
Filters/Slicers to use Etc
You should leverage statistical concepts (Hypothesis Testing) to solve
the problems
You should also leverage AI to solve these business problems

10
Expectations From Team

Identify what additional information that can help to solve the problem.
Also, additional analysis can be done with the help of new data.

Any alternative approaches can be leveraged to solve these problems (in


addition to what you worked)

11
Deliverables
Detailed Presentation that includes solutions for the below business
objectives
Performance driver analysis: Which KPIs drive the top-line (revenue)
performance?
Impact analysis on marketing ROI: What is the quantitative impact of
each commercial lever on revenue?
Optimizing marketing spending: How to best allocate the marketing
budget to gain the highest outcome for the next year?
Which of the products/product categories to target for the upcoming
campaigns? What is the rationality?
Which marketing channels to be leveraged for each of the product
categories? What is the rationality?
Code Files with Detailed comments
Github Repository (you should not upload the data)

12
Glossary

List Price: List Price = GMV * Units

Payday Week: If Payday falls within the week, then payday week = 1, else
0

Holiday Week: If Holiday falls within the week, then payday week = 1,
else 0

Product Type - Luxury /Mass-market: If GMV value is greater than 80


percentile, then luxury, else mass-market

Discount%: Discount% = 100*(product_mrp – list price) / product_mrp

13
Sample Exploratory Data Analysis

Relationship between revenue & advertisement spends


How are the discounts driving revenue?
How the customer satisfaction scores driving future revenues?
Is there any relationship between revenue & payment types?
Are holidays or paydays impacting sales?
Is there any relationship between product categories and revenue
Is there any trend & seasonality exists?
Are there any trends that exists in Advertisement Investments on
marketing channels?
Etc…

Note: This is not an exhaustive list of analyses. For your understanding, they
provided a few samples of analysis. As part of this exercise, you are required
to work on as many analyses that help to understand the data & problems
and provide insights & recommendations to solve the business problem.

14

You might also like