1 compared to their transactions made by the customers

1 Introduction

A savings
account is a deposit account held at a retail bank that pays interest
but cannot be used directly as money in the narrow sense of a medium of
exchange (for example, by writing a cheque). These accounts let customers set
aside a portion of their liquid assets while earning a monetary return . It is
considered to be one of the classical services offered by the banks.

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!


order now

With the increasing literacy rate around
the world, and the directives of governments, people are increasingly opening
account in different financial institutions. This phenomenon leads to multifold
increase of transactions in these financial institutions. Moreover,
technologies such as Internet, ATM card and credit card are the major catalysts
for increasing the number of transactions in the financial institutions. In
this competitive market, financial institutions such as banks are opening their
shops at every possible place. Thus, most of the banks in these days are
accumulating a large amount of data over a short span of time.

The savings bank system of a bank is the
most prominent service that a bank offers to the customers. Customers’ account
data are also kept in the database. That may be negligible data as compared to
their transactions made by the customers in the context of their savings
accounts. Various transactions of savings bank can be considered as a sequence
database ordered over time. It forms a big data, especially for large banks
like State Bank of India, established by Government of India. It is the largest
financial institution in India. It has more than 24,000 branches and 59,000
ATMs across the globe .

With the advent of cheap network
technologies and various data collection devices, large data sets are now
originating from different sources. Pattern recognition and data analysis now become
natural problems to deal with Solutions of these problems may lead to a greater
understanding of the situations, issues and performances, and hence, it could
be possible to take better decisions and control of the organizations.

There have been a large number of
transactions collected at different branches of a bank. At the end of every
year, a large bank might collect billions of transactions.  Such data might provide useful knowledge to
the bank management. The present work surveys different pieces of work done
based on savings bank account systems and savings bank data. Although savings
bank account system is a classical service offered by a bank, no detailed
survey has not been reported recently on patterns and predictions on the
savings bank data.

The rest of the paper is organized as
follows. Section 2 discusses related work on this issue.

 

 

 

2 Related work

Lowe  discussed the changing patterns in household
saving and spending in Australia. Such patter will eventually affect their
savings bank account balances. This issue is not only interesting in its own
right, but understanding these changes also helps us understand some of the
broader changes that are occurring within the economy of the country.

Phua et al.  presented an extensive summarization of data
mining-based fraud detection research. Authors categorise, compare, and
summarise  automated fraud detection reported
in the decade 2000 to 20009. Authors also highlighted promising new directions
from related adversarial data mining fields/applications such as
epidemic/outbreak detection, insider trading, intrusion detection, money
laundering, spam detection, and terrorist detection.

Batty et al.  discussed how data mining and multivariate
analytics techniques can be used to improve decision making processes in different
functions of life insurance organizations.

Shee et al. presents an overview big data
in banking. Authors discusses many aspects such as trends in data analytics,
attributes of big data, sentiment analytics, customer analysis and
segmentation.

3 Saving bank system

Different
banks provide different types of savings bank accounts.  State Bank of India offers five types savings
bank accounts: premium savings
account, savings plus account, basic savings bank account, small account, and savings
bank account for minors. Each of these type of savings bank accounts has a set
of conditions and a set of services.  Also, these accounts are governed by a set of
rules influenced by the government of the country.  Normally, the following facilities are
available along with a savings bank account: 
safe deposit lockers (as
per availability), nomination facility, SMS alerts and e-statement. Savings
bank account can be linked to multi-option deposit account for earning higher
term deposit interest on surplus money.

The core components of business analytics for
banking include the following functionalities

Business          intelligence:  It deals with finding, analyzing and sharing information
that may be needed for decision-making with the help of querying, reporting,
analysis, scorecards and dashboards.

Performance    management: It guides management strategy in
the most profitable directions with timely, reliable insights, scenario
modeling and transparent and timely reporting.

Predictive        analytics: It discovers patterns and
relationships in data to predict behaviours and optimize decision-making.

Analytical        decision           management:
It uses predictive analytics, rules, scoring and optimization techniques to
empower workers and systems on the front lines to optimize customer
interactions and improve business outcomes.

Risk     management:
This component makes risk-aware decisions and meets regulatory requirements
with smarter risk management programs and methodologies.

4 Patterns in saving bank data

Savings account comprises the major part
of the banking data. There is not much research done to find the patterns in
the saving data , but some research is done when the time there is no
centralized data base available. Some of the interesting patterns are observed
in the data from the basic analysis.

From the data we can observe that the
total amount is low than compared to the other types of accounts. The number of
transactions done is increasing recently as the most people are tending to use
the online type of transactions recently. Saving account holders tend to use
the account either very actively or very scarcely it is related to the age of
the account holder in many ways as the rate of usage is high among young users.
The rate is high in urban area than compared to the rural areas. These are some
of the interesting patterns we can find from the available data.

5 Select applications

Birant  discussed a data mining application using RFM
analysis. This analysis makes use of recency (R) of a customer in making a
transaction, how frequently (F) a customer makes a transaction and how much
money (M) a customer spends during a transaction. It is a useful method to
improve customer segmentation by dividing customers into various groups for
future personalization services and to identify customers who are more likely
to respond to promotions.

Identifying different trends in the large
number of transactions is an important task. L
Perriton  discussed 19th century patterns
of use data from a number of English savings banks. It
establishes a different, more immediate and accessible, financial history that
focuses on the social, rather than occupational, categories of savers, the
movement between different categories of account holders and the patterns of
use in accounts in two sample years.

6 Conclusions

Savings account has many restrictions
comparatively the data generated and the way of developing the systems has been
enhanced in this methodology. Savings account has usually low transactions
scale, no overdraft facility. Dormant account has greater impact on the saving
bank system and funds can be claimed by the beneficiary at any time, Current
accounts doesn’t possess these options .The Economy and the digital
transactions has impact on the technological growth and e-governance

 

 

7 References

1 Savings account: https://en.wikipedia.org/wiki/Savings_account

2 State Bank of India: https://en.wikipedia.org/wiki/State_Bank_of_India


Animesh Adhikari, Jhimli Adhikari, Witold Pedrycz, Data analysis and
pattern recognition in multiple database,. Intelligent Systems Reference
Library 61, Springer 2014, ISBN 978-3-319-03409-6, pp. 1-236

4 Amita Pal, Sankar K Pal, Pattern
recognition and big data, World Scientific
Publishing, 2017

 

5 Philip Lowe, Changing
patterns in household saving and spending, Australian Economic Forum, 2011

 

6 Clifton Phua,
Vincent Lee, Kate Smith, Ross Gayler, A comprehensive survey of data
mining-based fraud detection research, arXiv:1009.6119,
2010

 

7
Savings bank account systems: https://www.sbi.co.in/portal/web/personal-banking/savings-bank-account

 

8 IBM Business analytics for
banking, pp. 1-7

 

9 Mike Batty et al., Predictive
modeling for life insurance, Deloitte Consulting LLP, 1-29, 2010

 

10
Y-P Shee, D Crompton, H Richter, S-P Maehle, Big data in banking, Ervy, 1-66

 

11 D Birant, Data mining using RFM analysis,
Knowledge-Oriented Applications in Data Mining, pp 91-108

12 L Perriton, Depositor trends in the
Limehouse Savings Bank, World Savings Bank Institute,
pp 1-2, 2012