This visual analytics venture comprises of "INSIGHT TOY COMPANY 2017" Dataset

visual analysis utilizing SAS Visual Analytics software. SAS Visual Analytics is a superior,

in-memory solution for investigating huge measures of information rapidly. It enables us to

spot designs, perceive opportunities for additional investigation and express visual outcomes

through Web reports. This presentation is a concise overview of the numerous highlights and

abilities of SAS Visual Analytics. We have investigated SAS visual analytics features

utilizing "INSIGHT TOY COMPANY 2017" dataset. Further we have performed

representation for having insight of Geo-Hierarchy, Gross margin, and sales in different main

lands and so on.

Overview of Data

Insight Toy Company is a fictitious company that launches and sells high-tech toys. The data

is made up of 14 years of Financial, Manufacturing and Sales & Marketing information, with

127 facilities across the world:

 Financial: product sales cost of sales, gross margin;

 Manufacturing: unit capacity, reliability, lifespan, etc;

 Sales & Marketing: sales representative, sales rep rating, customer satisfaction,

customer distance, etc.

The data is made up of 252.1 thousand rows and 57 columns.

Task 1 involves calculating the gross margin of products, and creating a new data item for the

average gross margin. Secondly, task 2 involves creating visualisations to summarise the

gross margin in 2017, whilst task 3 involves creating ‘interactive’ visualisations to explore

product sales and customer satisfaction. Lastly, task 4 is mainly concerned about building one
report page to help the global production manager to identify the correlations between facility

attributes and customer satisfaction.

Task 1: Create data items

Task 1.1

A factor “Gross Margin” is created using the “add new data item” in data column on SAS

visual analytics. Gross margin is calculated utilizing the formula: Gross Margin = Product

sales – Product Cost of sales. A new data item is calculated and created by taking the mean of

the above calculated Gross Margin and named it as “Average Gross Margin”

Task 1.2

Hierarchy factor, a new data item is generated using Hierarchy option in new data item

creation drop down menu and then added the factors Brand, Line, Make and style in the same

series as mentioned. An example of which is given below by hierarchy across the Gross

Margin factor generated:

Product Brand in the hierarchy

On selecting “Toy” it further drills into as given below:
Task 1.3

“Facility Geo-Hierarchy”, a new factor is created using the same method as created in task

1.2 while in this the hierarchy consists of continents, country, region and city in the series. It

is added and named as ‘Facility Geo-Hierarchy’ and then plotted a bar chart of facility Geo-

Hierarchy across Gross Margin factor.

Task 2: Create visualisations to summarise the gross margin in 2017

Task 2.1

A cross tab is generated for displaying the data across continents and countries for Product Sales and

Gross margin factors.

The entire table not displayed.

Task 2.2

The highest and lowest Gross Margin across countries is shown in a bar chart generated below.
Using the evidence from the bar chart we could argue that the country with highest Gross margin is

United states with a value of 533066.85 and the country with lowest gross margin is India with a

value of 2086.85.

Task 2.3

In this task the Product sales variable is compared across the continents over time in 2017. A Bar

chart is generated for analysis.

In the above Bar Chart North America shows the highest product sales over time in 2017.
The table is not fully displayed.

The above shown is a table for displaying the product sales across continents in 2017.

TASK 3: Create ‘interactive’ visualisations to explore product sales and customer

satisfaction.

This task involves an interactive visualization, which is created for viewing the varying Product sales

and Customer satisfaction across the continents, countries, regions and cities using a drillable Geo-

map. A drillable geo-map is generated with “Facility Geo-Hierarchy” factor and product sales then

added on Average customer satisfaction (a new data item created using calculated item in data column

with customer satisfaction factor) and then a drillable filter of transaction dates in 2017 for product

sales and customer satisfaction.

In this task, we will be able to drill the map into continents, showing their product sales and their

average customer satisfaction level along with the time period, and the same process will be done for

the particular selected country, then for the selected region and further into the cities in the data for a

specific region.

The output sample for a specific continent, country, city and region is as shown below:
Basically geo-map is a geographical presentation of a country, continent, or region map, with colours

and values assigned to specific regions on a map. The values are displayed as a colour scale, and we

can specify optional hover-text for regions.

Through this visualization, we were able to show their product sales and average customer satisfaction

level along with the time period for different continent. After that, a particular country was selected,

same applies for the cities and specific regions for showing the product sales and their average level

of customer satisfaction.
TASK 4: Build one report page to help the global production manager to identify the

correlations between facility attributes and customer satisfaction

Task 4.1

In this task a Button bar is created with Continents and the facility, both are filtered as on selecting a

continent, it shows the facilities in that specific continent as shown below one example:
The above shows the facilities of African continent.

Below is a bar chart which is created with Average customer satisfaction factor across countries and

also the products of that specific selected country is shown along with the bar chart with a list of table

objects.

Task 4.2

A list bar and a time series plot is created as Correlation matrix shown below which is utilized to

show the correlation between Customer satisfaction factor and Customer Distance factor. Further a

list bar is utilized for displaying the Average customer distance across various countries in the dataset

and then a time series plot for displaying the distribution of Customer distance over time in 2017.
Task 4.3

In this task an interactive link is generated between tasks 4.1 and 4.2 that are page link is used. Using

task 4.1 on selecting a particular bar of country in the bar chart, the list of products of that specific

country is displayed further it takes to task 4.2 page that is correlation page where it displays the

correlation between Customer Satisfaction factor and customer distance factor for that selected

country bar and also this page displays the Average customer distance value for that specific country

and also the distribution of Customer distance over time in that country.

Data dictionary

Field Description
Product Brand 2 product brands: “Novelty” and “Toy”

Product Line 8 product lines. A line belongs to one product brand

Product Make 71 products make. A make belongs to one product line

Product Style 335 product styles. A style belongs to one product make

Sales Rep ID of the sales representative that made the sale.

Transaction Year Year of the sale, from 1998 to 2012

Field Description
Manufacturing unit that was used to assemble that product. There are
Unit
166 units in total.
Status of the manufacturing unit (eg. “Active”, Failure”, etc). There are
Unit Status
5 possible statuses.
A percentage of gross margins, calculated by dividing Gross Margin by
% Gross Margin
Product Sale for each transaction.
Distance from the customer address to the nearest sales facility.
Customer Distance
Anywhere from 100 meters to 50 kilometers.
An evaluation of the customer satisfaction, at the time of the sale. Scores

Customer Satisfaction vary from about 20% (very low

satisfaction) all the way to 100%.

Facility Age Age of the facility, from 0 (brand new) to about 32 years old.
An evaluation of the efficiency of the facility’s operations based on

Facility Efficiency multiple management factors. Scores vary

from 30% to 100%.

Product Cost of Sale. The purchase and production cost of the product
Product Cost of Sale
sold.
Product Material Cost The raw material component of the Cost of Sale.

Field Description
The standard ideal product price – if the product was deemed 100%

Product Price (target) quality and the market conditions were

ideal, this is what the Product Sale price would be set at.
An evaluation of the manufacturing quality of the product. Scores vary
Product Quality
from 60% to 100%.
Product Sale The actual revenue of the sale of that product.
Sales Rep Customer Amount of potential revenue for all possible customers in a given sales

Base representative’s region.

Number of customers a sales representative is responsible for at a given
Sales Rep Customers
date.
Sales Rep ID ID of the sales representative who made that sale.
The internal organization’s evaluation of the performance of a sales
Sales Rep Rating
representative.
Unit Actual Products produced from a given manufacturing unit at that point in time.
Unit Age Age of a manufacturing unit
References

1. “Predictions 2014: The Year of Digital Business,” Forrester Research, Inc., December

2013.

2. Adobe. Sept. 23, 2013. “Digital Distress: What Keeps Marketers Up at Night?”

Adobe Systems Inc.

3. “Digital Intelligence Replaces Web Analytics,” Forrester Research, Inc., November

2013.

4. Gordon, Ruth and Hulls, Katharine. January 2014. “Digital Marketing Insights Report

2014.” Teradata/Celebrus Technologies.