GURU GOBIND SINGH INDRAPRASTHA

UNIVERSITY DWARKA,
DELHI-110064

UNIVERSITY SCHOOL OF MANAGEMENT STUDIES

Business Analytics (MS 211)
End Term Paper

Submitted To: Submitted by:

Prof. Udita Taneja Name – Shagun Mittal (00516603923)
Astha Dhyani (03116603923)
Devashi Garg (03716603923)
Taniya Negi (07016603923)
Kanak Maroo (09916603923)
 BA TERM PAPER

INTRODUCTION

There are various sectors in India in which business analytics can be applied. Therefore, we have chosen E-
commerce sector, with Flipkart being a suitable company example. Flipkart has extensively used analytics to
optimize its operations, enhance customer experience, and drive business growth.

The e-commerce sector refers to the buying and selling of goods and services through digital platforms over the
internet. This industry has revolutionized traditional retail by providing convenience, accessibility, and a wide
range of options to consumers. It encompasses various models, including business-to-consumer (B2C),
business-to-business (B2B), consumer-to-consumer (C2C), and direct-to-consumer (D2C) transactions.

E-commerce in India has experienced rapid growth due to increased internet penetration, widespread
smartphone usage, and digital payment adoption. Government initiatives like "Digital India" and the rise of
logistics and delivery networks have further fueled its expansion. Major players such as Flipkart, Amazon India,
and Myntra dominate the market, offering products across categories like electronics, fashion, groceries, and
more. The sector continues to evolve with the integration of technologies like AI, machine learning, and data
analytics, which enhance customer experience, streamline operations, and drive business efficiency.

About Flipkart

Flipkart is a leading Indian e-commerce platform founded in 2007, offering a wide range of products including
electronics, fashion, and groceries. Known for its customer-centric approach, Flipkart leverages technology and
analytics to enhance user experience, streamline operations, and provide competitive pricing, making it a
pioneer in India’s online retail market.

How a Business analytics project will be beneficial for Flipkart?

A business analytics project can significantly benefit Flipkart by providing data-driven insights to enhance
decision-making. It can optimize supply chain management, predict customer preferences, and improve
inventory planning, reducing costs and delivery times. Analytics can refine personalized recommendations,
boosting customer engagement and sales. Additionally, it aids in identifying market trends, enabling Flipkart to
adapt strategies proactively. By leveraging analytics for fraud detection and dynamic pricing, Flipkart can
ensure platform security and competitiveness, driving overall efficiency and sustained business growth.

Project Phases

Phase 1- Defining objective and strategy

Objective: The objective of the Flipkart Sales Dashboard is to provide a comprehensive view of sales
performance across various metrics including:
Category-wise Sales: Understand the sales contribution of different product categories.
Region-wise Sales: Analyze the sales performance in different geographical regions.
Top 10 Products: Identify the best-performing products.
Payment Method: Track the usage of different payment methods.
Order Date: Monitor sales trends over time.

Strategy: The strategy focuses on using data visualization and analysis to:
Identify key areas of success and weakness: This helps prioritize efforts and resources effectively.
Track performance trends: This enables proactive adjustments to marketing strategies and product offerings.
Make informed decisions: The insights provided by the dashboard support data-driven decision making.

Phase 2 – Determining type of analytics to use

1. Descriptive Analytics: The dashboards use descriptive analytics to summarize and illustrate sales data for
different categories, regions, products, and payment methods. This is achieved through bar charts, line
charts, and pie charts.
2. Diagnostic Analytics: The dashboards likely incorporate some diagnostic analytics to understand the
factors influencing sales patterns. For example, the region-wise sales chart can be analyzed to see which
regions have higher sales and potentially identify reasons for this.
3. Predictive Analytics: While not explicitly shown, the dashboards could leverage predictive analytics to
forecast future sales trends based on historical data. The order date filter and "All Periods" option suggest
the possibility of analyzing sales data over time to predict future performance.
Phase 3 – Data Collection and Preparation

1. Data Gathering

The data for this analysis was sourced from a combination of internal and external repositories.

● Internal Sources: Sales records, customer region details, and payment method data
were extracted from Flipkart's CRM and transaction systems.
● External Sources: Insights into product trends and market comparisons were derived
from competitor analysis and market research databases.

2. Data Management Tools

The tools used to create this dashboard include:

1. Microsoft Excel:
○ Pivot Tables and Charts: For creating visualizations like bar, line, and pie
charts.
○ Slicers: For interactive filters (e.g., category or region).
○ Data Models: To manage large datasets for analysis.
2. Excel Functions:
○ Data Filtering: To categorize and organize data.
○ Formatting Tools: For improving the dashboard design (e.g., headers, logos).

This dashboard was created entirely using Excel.

3. Data Preprocessing

The collected data underwent a series of preprocessing steps to ensure accuracy and
consistency:

● Handling Missing Values: Any gaps in data (e.g., missing product categories or
payment methods) were identified and filled using relevant business rules.
● Data Normalization: To ensure uniformity, sales figures and percentages were
standardized for better comparison.
● Transformations: Data was formatted into a dashboard-friendly structure to create
visual elements like bar charts, line graphs, and pie charts.
 This structured approach allowed for the development of an insightful sales dashboard,
highlighting critical business metrics like category-wise performance, regional sales
distribution, and payment preferences.

Phase 4 – Analytical Techniques

1. Choosing Analytical Methods (Using Excel)

For the Flipkart sales data, Excel was used to apply statistical methods and generate insights
that address business problems like sales forecasting, customer segmentation, and product
performance evaluation.

1. Trend Analysis
○ Purpose: To analyze sales trends over time.
○ Technique: Excel's line chart feature was used to identify monthly sales
patterns using the "Order Date" data. This helps predict future sales and identify
peak sales months.
2. Descriptive Statistics
○ Purpose: To summarize sales data across categories, regions, and products.
○ Technique: Functions like AVERAGE, MAX, and MIN were applied to
determine top-performing products (e.g., Apple iPhone 13) and regions (e.g.,
North with ₹4,00,000 sales).
3. Pivot Tables for Segmentation
○ Purpose: To segment data based on regions, categories, and payment methods.
○ Technique: Pivot tables were used to classify data, allowing Flipkart to focus
on high-demand categories (Electronics) or popular payment methods (Cash on
Delivery at 21%).
4. Forecasting (Basic Regression in Excel)
○ Purpose: To predict future sales of products or regions.
○ Technique: Excel's trendline feature in charts was used to project sales for
categories like Electronics, which dominate with ₹14,00,000.
 5. Visualization Techniques
○ Purpose: To communicate insights effectively.
○ Technique: Bar charts, pie charts, and line graphs were created to visualize:
■ Region-wise sales distribution.
■ Category-wise contribution.
■ Payment preferences.

These analytical techniques in Excel provided actionable insights into sales trends, regional
performance, and customer preferences, enabling strategic decision-making.

Phase 5 – Reporting

Challenges and how they will be overcome:

Challenge 1: Data Accessibility and Quality

Issue: Integrating data from multiple sources (e.g., CRM, third-party logistics) while ensuring its accuracy.

Solution: Implement ETL (Extract, Transform, and Load) pipelines to streamline data integration and apply
data quality checks.
Challenge 2: Skills Gap

Issue: Limited availability of data science talent with expertise in advanced analytics.

Solution: Invest in employee training and collaborate with external experts for knowledge transfer.

Challenge 3: Integration with Existing Systems

Issue: Difficulty in embedding business analytics tools into legacy systems.

Solution: Use middleware solutions to bridge gaps and migrate critical systems to cloud-based platforms.

Challenge 4: Decision-Making Challenges

Issue: Resistance to data-driven changes from stakeholders.

Solution: Foster a data-driven culture by showcasing pilot project successes and offering stakeholder training.

Challenge 5: Ethical and Security Concerns

Issue: Risks related to data privacy and breaches.

Solution: Ensure compliance with data protection laws and invest in cyber security measures.

Challenge 6: Regulatory Environment

Issue: Adhering to consumer protection regulations and data localization laws.

Solution: Work closely with legal teams to ensure compliance and adopt secure data storage practices.
Conclusion:

Business Analytics has the understood to change operations at Flipkart by utilizing data-driven insightfully
for vital decision-timber. By upholding progressed analytics ways, Flipkart can improve client fulfillment,
optimize constrain chain adequacy, and drive benefit development. Tending to challenge comparative as
information quality and integration will be basic, nearby cultivating a culture of development and compliance.
With a centered approach, business analytics can set Flipkart's position as a pioneer in thee-commerce
assiduity, empowering it to remain ahead in a competitive asks.

Expected outcomes

1. Improved client fulfillment through substantiated showcasing and decreased conveyance times.

2. Bettered utilitarian viability by streamlining constrains chain forms.

3. Expanded benefit through superior bargains soothsaying and focused on heights.

Recommendations

1. Persistently contribute in progressed analytics apparatuses and ways.

2. Create a solid data-driven culture inside the affiliation.

3. Routinely upgrade analytics models to reflect changing ask conditions.

Summary of the project

The proposed business analytics plan for Flipkart illustrates how analytics can transfigure operations, upgrade
client fulfillment, and drive development. By tending to challenges and utilizing data-driven insightfully,
Flipkart can cement its position as an ask pioneer in Indian e-commerce.