lOMoARcPSD|46636157

Assignment- Python Introduction- Austo Motor Company

data science and business (Great Lakes Institute of Management)

Scan to open on Studocu

Studocu is not sponsored or endorsed by any college or university

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])
 lOMoARcPSD|46636157

BUSINESS REPORT
PGP – [Link].24.A

MUSKAN SETIYA

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])

 lOMoARcPSD|46636157

Contents
List of Figures ..................................................................................................... 3
List of Tables ...................................................................................................... 4
1) Understanding the data and its Structure: ..................................................... 5
2) Data checks and treating irregularities: .......................................................... 5
Checking missing data fields ........................................................................... 5
Checking data consistency .............................................................................. 6
Checking statistical summary of the data ........................................................ 7
3) Univariate Analysis ......................................................................................... 8
4) Bivariate Analysis ......................................................................................... 15
5) Key Questions .............................................................................................. 18
6) Recommendations ....................................................................................... 24

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])

 lOMoARcPSD|46636157

List of Figures
Fig 1.1 – Missing data fields
Fig 1.2 – Unique column values
g 1.3 – Statistical Summary
Fig 1.4 – Bar Chart - Gender
Fig 1.5 – Bar Chart - Profession
Fig 1.6 – Bar Chart – Marital Status
Fig 1.7 – Bar Chart – Education
Fig 1.8 – Bar Chart – Personal Loan
Fig 1.9 – Bar Chart – House Loan
Fig 1.10 – Bar Chart – Partner Working
Fig 1.11 – Bar Chart – Vehicle Type
Fig 1.12 – Histogram – Age
Fig 1.13 – Histogram – Salary
Fig 1.14 – Histogram – Partner Salary
Fig 1.15 – Histogram –Total Salary
Fig 1.16 – Histogram –Price
Fig 1.17 – Pairplot
Fig 1.18 – Correlation Table
Fig 1.19 – Correlation Matrix
Fig 1.20 - Car Preference within males and females
Fig 1.21 – Car preference within professions
Fig 1.22 – Vehicle distribution – By profession and gender
Fig 1.23- Total amount spent on vehicles- By gender
Fig 1.24 – Total amount spent on vehicles- By personal loan
Fig 1.25 – Influence of partner working on purchase of high-priced cars

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])

 lOMoARcPSD|46636157

List of Tables

Table 1.1- Data structure

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])

 lOMoARcPSD|46636157

Austo Motor Company is a leading car manufacturer specializing in SUV, Sedan,

and Hatchback models. In its recent board meeting, concerns were raised by
the members on the efÏciency of the marketing campaign currently being
used. The board decides to rope in analytics professional to improve the
existing campaign

1) Understanding the data and its Structure:

• Data contains 1581 rows and 14 columns

• Data Type-
Column Name Data Type
Age int64
Gender object
Profession object
Marital_status object
Education object
No_of_Dependents int64
Personal_loan object
House_loan object
Partner_working object
Salary int64
Partner_salary float64
Total_salary int64
Price int64
Make object
Table 1.1- Data structure

2) Data checks and treating irregularities:

• There are no duplicates in the data

Checking missing data fields

• We checked for missing data values and found Gender and
Partner_salary has some null values

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])

 lOMoARcPSD|46636157

Fig1.1 – Missing data fields

• Gender contains 53 null values. It is suggested to keep these records to

avoid losing out on the values for other variables in these records.
Creating a new category is also not suggested as it is only 3% of the
data
• Partner_salary contains 106 missing values. This variable is dependent
upon other two variables which are Marital_status and
Partner_working. Wherever we have Partner_working = ‘Yes’, we
ensured that all the records must mention ‘married’ under
Marital_status column
• Rows where Partner_salary is null, data is obtained from subtracting
Salary from Total_salary
i.e., Partner_salary = Total_salary – Salary
Here we checked that wherever Partner_working = no, the value in
the Partner_salary column would be ‘0’

Checking data consistency

• We checked the unique values of all the categorical data within the dat
a set and found that data under column gender is inconsistent. It cont
ains records that mentions - 'Male' 'Femal' 'Female' nan 'Femle']
• ‘Femal’ and ‘Femle’ were replaced with ‘Female’

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])

 lOMoARcPSD|46636157

Fig 1.2 – Unique column values

Checking statistical summary of the data

Fig 1.3 – Statistical Summary

o Observations
▪ Mean age is 31.9 years and max is 54 years
▪ Average number of dependents 2.45 ~ 2-3 dependents
▪ Average salary is ~60,000
▪ Average partner salary is ~ 19000
▪ Average total salary is ~80000 with maximum as 171000
▪ Average price at which the vehicle is bought is ~36000 and
highest price is 70000

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])

 lOMoARcPSD|46636157

3) Univariate Analysis

a) There are more males (n=1199) in the data than females (n=329)

Fig 1.4 – Bar Chart – Gender

b) There are more salaried people in the data set

Fig 1.5 – Bar Chart - Profession

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])

 lOMoARcPSD|46636157

c) Marital status of most of the people is ‘Married’

Fig 1.6 – Bar Chart – Marital Status

d) In the data set, more people are postgraduate degree holders

Fig 1.7 – Bar Chart – Education

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])

 lOMoARcPSD|46636157

e) 50% of the people have a personal loan

Fig 1.8 – Bar Chart – Personal Loan

f) 33% of the people have taken a house loan

Fig 1.9 – Bar Chart – House Loan

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])

 lOMoARcPSD|46636157

g) More than 800 people have a working partner

Fig 1.10 – Bar Chart – Partner Working

h) Most of the people have Sedan followed by Hatchback

Fig 1.11 – Bar Chart – Vehicle Type

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])

 lOMoARcPSD|46636157

i) 60% of the sample has age less than 30

Fig 1.12 – Histogram – Age

j) Salary has a normal distribution curve

Fig 1.13 – Histogram – Salary

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])

 lOMoARcPSD|46636157

k) Partner salary is right skewed

Fig 1.14 – Histogram – Partner Salary

l) Total salary is right skewed

Fig 1.15 – Histogram –Total Salary

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])

 lOMoARcPSD|46636157

m) Price is also right skewed

Fig 1.16 – Histogram –Price

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])

 lOMoARcPSD|46636157

4) Bivariate Analysis

• Pairplot and correlation of continuous variables

• There is a linear relationship between –
o Age and Salary
o Age and Total Salary
o Age and Price
o Salary and Total Salary
o Price and Salary
o Partner Salary and Total Salary
o Total Salary and Price

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])

 lOMoARcPSD|46636157

Fig 1.17 – Pairplot

• Correlation Table –

Fig 1.18 – Correlation Table

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])

 lOMoARcPSD|46636157

• Correlation Matrix –

Fig 1.19 – Correlation Matrix

• Below variables are highly correlated-

o Age and Price
o Age and Salary
o Salary and Total Salary
o Partner Salary and Total Salary

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])

 lOMoARcPSD|46636157

5) Key Questions

Fig 1.20 - Car Preference within males and females

• Observation:

o Males prefer buying more cars than females

o Males prefer Sedan and Hatchback
o Females prefer SUV as compared to Sedan and Hatchback

• Recommendation

Marketing strategy could be focused depending upon the group

preference. Group focused discounts or promotional offers could be rolled
out to boost sales

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])

 lOMoARcPSD|46636157

Fig 1.21 – Car preference within professions

• Observation:

o Salaried people prefer Sedan and SUV more as compared to people

into business
o Within the salaried people, highest preference is for Sedan followed
by Hatchback

• Recommendation

o Allocate more promotional resources and marketing campaigns

towards highlighting the features, benefits, and appeal of Sedans
specifically to salaried professionals
o Highlight the versatility, affordability, and practicality of Hatchbacks
to attract salaried customers who may prioritize these factors

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])

 lOMoARcPSD|46636157

Fig 1.22 – Vehicle distribution – By profession and gender

• Observation:
The statement made by Sheldon Cooper is false as -
o Salaried Male prefer Sedan over SUVs
o Salaried female prefers SUVs the most followed by Sedan

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])

 lOMoARcPSD|46636157

Fig 1.23- Total amount spent on vehicles -By gender

• Observation:
o On an average, females spend more than males on cars

• Recommendation:
o Focusing marketing efforts on females could help boost the profits
of the business

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])

 lOMoARcPSD|46636157

Fig 1.24 – Total amount spent on vehicles- By personal loan

• Observation:
o People who do not have a personal loan spend slightly more on an
average as compared to people who do not

• Recommendation:
o Marketing efforts do not need to be segmented based on whether
individuals have a personal loan or not

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])

 lOMoARcPSD|46636157

Fig 1.25 – Influence of partner working on purchase of high-priced cars

• Observation:
o Having a working partner does not lead to purchase of high-priced
cars

• Recommendation:
o Marketing efforts do not need to be segmented based on whether
people have a working partner or not

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])

 lOMoARcPSD|46636157

6) Recommendations
• To increase sales:

o The company should customize promotional offers and tailor

marketing campaigns separately for males and females
o Prioritizing marketing efforts towards males is crucial to improve
overall sales figures
o Consistently applying current marketing strategies targeting males
for Hatchback and Sedan models has proven effective
o To increase sales of Sedans and Hatchbacks among females, it is
essential to direct marketing campaigns towards females and offer
promotional offers
o Increasing marketing efforts could be effective in boosting sales of
SUVs among female customers

Downloaded by Dhiviya Muralidharan (dhiviyamurali.54@[Link])