Professional Documents
Culture Documents
Lifi
Lifi
SUBMITTED BY
Gana Devraj
0
Proprietary content. ©Great Learning. All Rights Reserved. Unauthorized use or distribution prohibited
1) Introduction of the business problem 2
2) Data Report 2
k) Is the data unbalanced? If so, what can be done? Please explain in the
context of the business
l) Any business insights using clustering (if applicable)
m) Any other business insights
1
Proprietary content. ©Great Learning. All Rights Reserved. Unauthorized use or distribution prohibited
PROBLEM STATEMENT:
Life insurance companies are faced by several problems such as low penetration rate, consumer
behaviour, harsh economic environment and financial illiteracy among others. The company agents,
whose efforts contributes to a larger of the companies' income also face difficulties such as instances of
rejection during their constant hustling, and networking. The excellence of agent performance has
remained a major problem which needs to be addressed.
This project will help the company to design appropriate engagement activity for their agents basing on
their performance.
Life insurance companies offers various opportunities to individuals, institutions and the economy. They
protect societies' wealth, maintain standards of living, provide a sense of security and peace of mind,
encourage loss mitigation, increase prosperity, and provide awareness of the reality of risks and their
consequences through civic education.
DATA REPORT:
Import Libraries
Load data
Inspect Rows
Data Information
Dataset has 20 variables
There are 5 integer data types, 7 float and 8 object types.
Missing values
'isnull()' method detects missing values. It returns a Boolean same-sized object indicating if the values
are NA. NA values, gets mapped to True values. Everything else gets mapped to False values.
'sum()' method followed by 'isnull()' adds up all the True instances per column to give a summary of
missing values per column.
We find no missing values in our new data frame
Outliers
Some columns contain outliers. However, we will not drop them since they may be correctly observed
values
Univariate analysis
Continuous variables
- Summary statistics
- The maximum agent bonus is 9608.00000 and the minimum is 1605.00000 and median bonus is
3911.50000
- The average gross monthly income of customer is 22890.309991
- Minimum age of customer is 2 and maximum is 8
- Minimum existing policies of a customer is 3.565363 and maximum is 6.000000
Categorical variables
2. Occupation
3. Education Field
5. Designation
- Most people who subscribe life insurance policy are managers and the least are exe.
Bivariate analysis
Most bonus come from people located North, West and East of India
4. Agent bonus, designation and payment method
Most bonus income are from Vp who pay monthly and yearly, and AVP who pay quarterly
Business insights from EDA
1. Is the data unbalanced? If so, what can be done? Please explain in the context of the business
- The distribution of class variables in our dataset is comparable hence balanced
There is a fair distribution of bonus basing on the occupation and customer care score
- Life insurance company should train their agents to target the following persons: