Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 7

Introduction

Since it is in process of organizing problem and evaluating answers to the countless problems that
develop during the business process, data analysis is the most important component of the firm.
Acquiring the set of data, purifying it, modifying it, and finally analyzing it so that important info and
interpretations can be presented to the corporation's senior managers is the appropriate statistical
phase of the business operations. The numbers and statistics in this report originate from a monetary
data set that shows how much money a person has spent.

Overview of the data


Dividend stocks are amongst the most widely used terms in the financial system, and is one of the
important factors that contribute for banks. Contributions assist banks in making loans to financially
distressed customers. Financial assets are a type of money that enables a financial institution to offer
loans to individuals and businesses. The funds are held at the agreed-upon higher returns for the time
specified by the bank's customers. The banking industry has its own strategy for promoting savings to
consumers, and it sells it to them at a premium.

The financial data set contains 34 values, comprising 14 arithmetic operations, 12 text factors, and 8
Conditional factors.

The mean lifespan of the bank's customers is referred to as age.

Description of job: For each customer in the data set, this is a description of his or her job.

This field represents the marital status of each customer in the data set.

Specific learning goals level- This shows the consumer's educational level in relation to the data
collection.

Personal default value- Per the information, this really is the state of consumers whom have defaulted
on assets of the banking system.

The sum of funds in the customer's bank account is known as the private savings account.

Residential requirements - That's the home requirement in each of the information collection's users.

Personal bank loan status- The legal standing of a user's personal loan from a bank is shown here.

Individual contact- This is the consumer's connection category in the information gathering.

Data preprocessing
Filtering a collection of data so that it can be appropriately transformed together into data analysis data
set and afterwards decreasing the range of data so that the data and information can be correctly
evaluated in a number of ways is the method of data management. Considering inaccurate data
gathering would outcome in a flood of difficulties instead of solutions, information gathering is a critical
phase in the research process.
Data cleaning
The feature extraction phase encompasses eliminating incorrect information and data, fixing damaged
knowledge / analysis, discarding badly structured information and data, and, finally, replacing missing
data and information detected during the data gathering. The data set that are provided in this report
file has many empty data cells that are very harmful for the proper data analysis and data mining
process. In order to properly identify the knowledge, information and solution of the problem it is highly
necessary that the data and information needs to be cleaned thoroughly. The data and information of
the bank marketing are incorrect and it needs to be cleaned. If the data set is not cleaned properly then
the outcome of the data analysis, and the algorithms of the data analysis becomes unreliable, which to
normal eye seems correct in many ways, but are actually incorrect. In this report, the bank loan is taken
by the customer and similarly, the deposits are done by the same customer. This analysis shows that
there needs to be proper data cleaning process for the use of the data for proper data analysis.

Data transformation
Following information extraction, data processing is regarded among the most critical processes. The
term "big data" relates to the procedure of changing the structuring of different factors in a data set. In
the data gathering, a huge set of variables are inaccurately reported. Some of the data and information
have different format in the data set, which needs to be transformed to the proper required data set.
The data transformation method allows for the change of the data format that helps the data analysts to
properly manage the data analysis and find the proper solution of the problem that are seen from the
data analysis methods. There are two methods for the data transformation technique, which are
migration of the data and information, warehousing of the data and information, integration of the data
and information, and wrangling of the data and information. This report analysis provides the migration
of the data and information, and integration of the data and information of the data set that are used
for the techniques of the data analysis. The usage of the information and data transfer approach allows
comparable information and data to be transferred into a data collection, allowing data scientists to
deliver correct analysis of the data to the senior manager.

Data reduction
Data reduction process is known as the final step before the use of the data analysis conducted for the
organization. The data and information that are conducted in the process allows for the reducing of the
data and information so that there is the proper use of the data analysis to understand the solution of
the problem of the organization business process. There are terabytes of the data and information that
can be found for the banking sector. So, the data and information are reduced to useful information so
that there are proper data analysis performance done. Along a large number of data points, a
complicated examination of the data set is generated, and there is an excessive amount of information
analysis techniques available, which will lead to wrong data being delivered during the data collection
stage. Below is shown the proper formation of the data reduction.
Figure 1: Original data and information for the banking system

The figure shown above is the original data set that has not been set to reduction process. It can be seen
from the figure above that there are 4251 rows of the data and information in the banking marketing
data set. The figure shows there are 17 columns in the data set where all the data and information of
the banking marketing is provided. All of the data and information that are provided in the above figure
are the original data and information, which needs to be reduced using different techniques. This will
allow the use of the proper data analysis.
Figure 2: data reduction process used for the rows of the data set

The data reduction section of the row of the set of data is completed using the partitioning of the data
set. The process of the data reduction using the partitioning allows for the proper partitioning of the
data set using the different techniques. There are many methods that are used for the partitioning and
the 70% of the total data set is partitioned for the data analysis part.

Figure 3: data reduction method for the column of the data set
The figure above shows the reduction process used in the column. Previously the data set had 34
columns and now all the columns are reduced to only 9 columns. The 9 columns that are shown here
provide the similar analysis as to that of the original data set.

Dashboard design

Figure 4: Dashboard 1 design for the banking marketing

The figure shown above is the dashboard design for the banking marketing. It shows that most of the
people who are involved in the loan taking and deposit making in the banking sector have the job in
management sector. It also shows that most of the customer have completed their secondary level of
education. Very few people are only set to unknown level of the education. It shows that the most of
the customer that are in the banking sector who have deposited the amount have not taken any loan
from the bank. Also, those people who have not taken much loan have most of the deposit in the
banking sector.
Figure 5: Dashboard 2 design for the banking marketing

The number of clients who have gotten housing after taking out a bank loan is depicted in the graph
above. In the bar graph, the data is separated into two bars: Yes for clients who have housing and No for
those who do not. A bar chart depicting the educational levels of the bank's customers who have taken
out loans is also included in the report. The last bar chart shows the months when customers took out a
bank loan.

Conclusion
The numerous procedures and processes utilized to evaluate the data set of account holders who took
out a loan, and also the connections between the clients in terms of infrastructure, credit state, level of
education, and the periods wherein the loans were taken out, are described in this article. The report
also includes a decision tree evaluation of the y value in the sample group. On the dashboard produced
for the data set analysis, the percentage of customers who took out such a loan from a bank was also
displayed. From original data through input data, this booklet describes the whole data collection
process.
Appendix

You might also like