Project Report on Introduction to Business Analytics for

Sales Data Analysis

Introduction
In the contemporary business landscape, data-driven decision-making has emerged as a
cornerstone for organizational success. With the advent of advanced analytics tools and
technologies, companies can harness the power of data to gain valuable insights into their
operations, customer behaviour, and market trends. In this context, the sales store dataset
provides a rich source of information that can be leveraged to understand various aspects of
sales performance and customer dynamics.
The sales store dataset comprises essential attributes such as Order ID, Customer details,
Product Category, Sub-Category, City, Order Date, Regions, Sales figures, Profit margins,
and State information. Each of these attributes offers valuable insights into different facets of
the sales process, ranging from customer demographics to product performance and
geographic trends
By analysing the sales store data, businesses can unlock actionable insights that drive
strategic decision-making across multiple functions. For instance, understanding customer
preferences and buying behaviour can inform product assortment strategies and targeted
marketing campaigns. Similarly, identifying high-performing regions or product categories
can guide resource allocation and sales prioritization efforts.
Moreover, the dataset allows businesses to evaluate the profitability of different sales
channels, identify opportunities for cost optimization, and mitigate potential risks. By delving
into the relationship between sales and profit margins, organizations can fine-tune their
pricing strategies and operational efficiencies to maximize profitability while ensuring
customer satisfaction.
Overall, the sales store dataset serves as a valuable asset for businesses seeking to optimize
their sales performance, enhance customer experiences, and achieve sustainable growth in
today's competitive marketplace. Through comprehensive analysis and strategic utilization of
data insights, organizations can gain a competitive edge and drive long-term success in the
dynamic world of sales and retail.
Team Composition
Aniruddha Gaikwad - 732391004
Shubham Jagtap - 732391012
Raj Jamnik - 732391014
Prachi Singh - 732391023
Pranav Patil - 732391024

Objective: Let's uncover hidden trends in the sales data! By analysing this dataset, we can
identify patterns in sales across cities, regions, product categories, and subcategories. These
insights will help us make informed decisions to boost sales and profits.
Problem Statement: "Analysing sales data to identify product performance trends and optimize
sales strategies for increased revenue and profitability."
Project Outcome: Analyse Sales Data for Revenue Growth: This project will leverage
data analysis to identify factors significantly influencing the company's revenue. We'll then
develop actionable solutions to address these factors and optimize revenue growth.
Dataset Introduction:
The sales dataset is a collection of data that includes information on the sales of
products. This type of dataset may include details such as the total sales profit, the
location of the sales, the type of product sold, and any other relevant information.

The dataset contains 9995 records and 10 fields that contain information about

1. Order ID
2. Customer
3. Category
4. Sub- Category
5. City
6. Order Date
7. Regions
8. Sales
9. Profit
10. State

All these records are from the time period from 2015 to 2018.

Source of the Dataset - Kaggle.

Excel Analysis:
The dataset was analysed in Excel with the help of rows and columns. It includes performing
various operations like data cleaning, data manipulation, and performing calculations. Excel
helps to transform the raw data into a tabular format for further analysis.
Tableau Implementation:
The data from the Excel dataset is visualized and analysed more effectively using Tableau.
Tableau makes creating dashboards, charts, graphs, and filters easier based on this data.
We imported the Excel dataset into Tableau which is further used for analysis.
We used functions like summation and average to calculate the sum of sales, profit, and
revenue of the grocery store and average profits per year as well.
For visualization, we have implemented bar graphs, line graphs, pie charts, and map points,
which help in better and more effective data understanding.
Analysis:
Business Understanding
The dashboard displays sales data for Super Store, which appears to be a retail company that sells
groceries and daily needs in different cities of Tamil Nadu.

The sales dashboard you provided shows various sales and profit metrics for a grocery store
chain. Here's a detailed breakdown of the information:

1. Total Sales:

 The total sales figure of grocery store is 1,49,56,982.

2. Average Sales in each City:

 The first chart titled "Sales by City" denotes the average number of sales for each city,
represented with the help of the map, shows the average number of sales occurred in
each city in the state of Tamil Nadu.
 The number of sales can be understood by the colour shown, i.e., light colour shade
represents less sales while darker shade represents a greater number of sales.

3. Average Profits per Year:

 The second graph titled "Average Profits per Year" shows the average quarterly
profits for the grocery store in the years 2015, 2016, 2017, 2018.
 In the year 2015 - 2016, a steady decline is seen in the profits, whereas a slow
quarterly increase can be seen in the year 2017 and 2018.

4. Average Sales per Region:

 The pie chart titled "Average Sales per Region" shows average of total sales of the
grocery store in Tamil Nadu state which is 7244.
 It also shows that the South region of Tamil Nadu has the highest average sales at
1508, followed by the West at 1498, the Central at 1493, and the East at 1491, and the
lowest average sales is seen in the North region at 1254.

5. Profits by Category of Products:

 The line graph titled "Yearly Profits by Product category" shows the total profit or
revenue generated by the grocery store with respect to the category of products in the
period of four years. Different categories are represented by different colours in the
Line Graph.
 As shown in the graph, we can conclude that the Eggs & Meat as well as the Snacks
category are at the top for profits throughout the 4 years. The highest profit generated
is 196,027 by Snacks, followed by Eggs & Meat at 191,195 in the year 2018.
 A rapid growth in the profits by all categories is seen in the year 2017 to 2018, this
may be a result of inflation or price hike.
 Change in profits generated by different category of products can be a result of
Customer demands, customer behaviour, Increasing competition, Store management,
price inflation, Taxation, etc.
 6. Sales by Category of Products:

 The chart titled "Sales by Category of Products" includes Sales of grocery store with
respect to their category of products sold as well as the sub-category. The different
categories are represented by different colours, which includes Bakery, Beverages,
Eggs & Meat, Food Grains, Fruits & Veggies, Oil & Masala, and Snacks.
 These 7 categories are further divided into sub-categories and their sales are plotted
using a bar graph as shown.
 The Beverages category has the highest sales at 10,51,439, followed by Snacks at
768,213, and Bakery products at 741,586.
 The lowest number of sales is seen in the Rice at 498,323, which is a sub-category in
Food Grains category.

Data understanding

The data in the dashboard appears to include the following attributes:

 Order ID
 Customer
 Category
 Sub- Category
 City
 Order Date
 Regions
 Sales
 Profit
 State
Data preparation
The data preparation stage would likely involve cleaning and transforming the data.
Some specific steps that might be needed include:

Fixing missing Values: Some data points might be missing, like customer names. We'll need
to decide how to handle these, either by filling them in with estimates or by removing those
rows altogether.

Formatting consistently: The dates in the order date category might be all jumbled up. We'll
want to make sure they're all formatted in the same way.

Creating new details: We can also make new data points based on the ones we already have.
For instance, we could calculate the profit margin by dividing the total profit by the total
sales.

Data modelling

A star schema is a suitable data model. It would have a central fact table containing shipping
data and dimension tables for descriptive attributes (customer names, destinations, etc.).

Evaluation
The evaluation stage would assess the data analysis model's effectiveness. This could involve
comparing the model's results to known sales and profit performance metrics or using
accuracy, and precision.

Deployment

Deployment involves making the analysis available to users. In this case, the dashboard itself
serves as the deployment, providing visualizations for users to understand sales performance.

Possible Insights

 The Central region seems to be the most profitable based on average sales.
 The Bakery category is the highest-grossing product category.
 The grocery store chain experienced a decline in profits over the years (2015-2018).

Limitations

 Data for some sections of the dashboard are cut off and inaccessible.
 It is unclear how many cities are included and what their individual sales figures are.
 There is no data on expenses or cost of goods sold, making it difficult to assess
profitability.

Conclusion

Based on the available data in the grocery store dashboard, we can draw the following
conclusions:

1. Regional Performance: The Central region appears to be the strongest performer,

boasting the highest average sales.
2. Product Category Sales: Bakery is the clear leader in terms of sales, followed by
Beverages and Food Grains.
3. Profit Decline: There's a concerning trend of declining average profits over the years
(2015-2018).

However, important limitations hinder a more comprehensive conclusion:

 Incomplete Data: Several sections of the dashboard lack crucial information,

including city-specific sales figures and yearly profit breakdowns by category.
 Missing Cost Data: Without data on expenses and cost of goods sold, it's impossible
to determine the true profitability of each region or product category.

Recommendations

 To get a clearer picture of the store's health, analyze complete data sets that include
missing information.
 Investigate the reasons behind the declining profits to identify areas for improvement.
By addressing these limitations and conducting further analysis, the grocery store can gain
valuable insights into its performance and make informed decisions to boost sales and
profitability.