PREDICTIVE ANALYTICS IN FINANCE

A Project Submitted
in Partial Fulfillment of the Requirements
for the MBA- TECHNOLOGY MANAGEMENT

by
MUHAMMAD ASHRAF HUSSAIN

DEPARTMENT OF BUSINESS MANAGEMENT

OSMANIA UNIVERSITY, HYDERABAD, INDIA
MAY, 2019
 UNDERTAKING

I declare that the work presented in this project titled “PREDICTIVE

ANALYTICS IN FINANCE”, submitted to the DEPARTMENT OF BUSINESS
MANAGEMENT, Faculty of MBA Technology, OSMANIA University,
HYDERABAD

Month, Year
Place
________________________________
(Student Name)

ii
Preface
Predictive analytics can help CFO’s to
use the existing data and identify trends for more
accurate planning, forecasting and decision making. By
using predictive analytics your organization can predict
outcomes, identify untapped opportunities, expose hidden
risks, anticipate the future and act quickly

Every company wants to see into the

future. How much will a product sell next month or will
the demand drop off? How much will the business have to
spend on manufacturing, distribution and other
overheads? Does the business have a “next best offer” for
a product or an estimated revenue for a newly launched
product? Predictive analytics techniques are used to help
answer all these questions and to create a better
understanding of possible variables to aid smarter
decisions

iii
Contents

Undertaking ii

Preface iii

1 Introduction v

2 Reviews of literature xviii

3 Study Methodology xx

4 About the Industry

5 About the Company

6 Conclusions And Suggestions

Bibliography

Appendix

Websites

iv
Chapter 1

Introduction

What is Predictive
Analytics ?

What is Predictive Analytics? Predictive analytics is the

branch of the advanced analytics which is used to make
predictions about unknown future events. Predictive
analytics uses many techniques from data mining, statistics,
modeling, machine learning, and artificial intelligence to
analyze current data to make predictions about future. It
uses a number of data mining, predictive modeling and
analytical techniques to bring together the management,
information technology, and modeling business process to
make predictions about future. The patterns found in
historical and transactional data can be used to identify risks
and opportunities for future. Predictive analytics models

v
capture relationships among many factors to assess risk
with a particular set of conditions to assign a score, or
weightage. By successfully applying predictive analytics the
businesses can effectively interpret big data for their
benefit.

The data mining and text analytics along with statistics,

allows the business users to create predictive intelligence by
uncovering patterns and relationships in both the structured
and unstructured data. The data which can be used readily
for analysis are structured data, examples like age, gender,
marital status, income, sales. Unstructured data are textual
data in call center notes, social media content, or other type
of open text which need to be extracted from the text, along
with the sentiment, and then used in the model building
process.

Predictive analytics allows organizations to become

proactive, forward looking, anticipating outcomes and
behaviors based upon the data and not on a hunch or
assumptions. Prescriptive analytics, goes further and
suggest actions to benefit from the prediction and also
provide decision options to benefit from the predictions and
its implications.

vi
Predictive Analytics Value Chain

Predictive Analytics Process

1.Define Project:

Define the project outcomes, deliverables, scoping of the

effort, business objectives, identify the data sets which are
going to be used.

vii
2.Data Collection:

Data Mining for predictive analytics prepares data from

multiple sources for analysis. This provides a complete view
of the customer interactions.

3. Data Analysis:

Data Analysis is the process of inspecting, cleaning,

transforming, and modeling data with the objective of
discovering useful information, arriving at conclusions.

4.Statistics:

Statistical Analysis enables to validate the assumptions,

hypotheses and test them with using standard statistical
models.

5.Modeling:

Predictive Modeling provides the ability to automatically

create accurate predictive models about future. There are
also options to choose the best solution with multi model
evaluation.

6.Deployment:

Predictive Model Deployment provides the option to deploy

the analytical results in to the every day decision making
process to get results, reports and output by automating the
decisions based on the modeling.

viii
7.Model Monitoring:

Models are managed and monitored to review the model

performance to ensure that it is providing the results
expected.

Predictive Analytics Process

Prescriptive Analytics

Prescriptive Analytics automatically automate complex

decisions and trade offs to make predictions and then
proactively update recommendations based on changing
events to take advantage of the prediction.

ix
 Applications of Predictive Analytics

1. Customer relationship management

(CRM)

Predictive analysis applications are used to achieve CRM

objectives such as marketing campaigns, sales, and
customer services. Analytical customer relationship
management can be applied throughout the customers life
cycle, right from acquisition, relationship growth, retention,
and win back.

2. Health Care

Predictive analysis applications in health care can determine

the patients who are at the risk of developing certain
conditions such as diabetes, asthma and other lifetime
illnesses. The clinical decision support systems incorporate
predictive analytics to support medical decision making at
the point of care.

3. Collection Analytics

Predictive analytics applications optimize the allocation of

collection resources by identifying the effective collection
agencies, contact strategies, legal actions to increase the
recovery and also reducing the collection costs.

x
4. Cross Sell

Predictive analytics applications analyze customers

spending, usage and other behavior, leading to efficient
cross sales, or selling additional products to current
customers for an organization that offers multiple products

5. Fraud detection

Predictive analytics applications can find inaccurate credit

applications, fraudulent transactions both done offline and
online, identity thefts and false insurance claims.

6. Risk management

Predictive analytics applications predicts the best portfolio

to maximize return in capital asset pricing model and
probabilistic risk assessment to yield accurate forecasts.

7.Direct Marketing

Predictive analytics can also help to identify the most

effective combination of product versions, marketing
material, communication channels and timing that should be
used to target a given consumer.

8.Underwriting

Predictive analytics can help underwrite the quantities by

predicting the chances of illness, default, bankruptcy.
Predictive analytics can streamline the process of customer

xi
acquisition by predicting the future risk behavior of a
customer using application level data.

Predicitve Analytics

Industry Applications

Predictive analytics is used in insurance, banking,

marketing, financial services, telecommunications, retail,
travel, healthcare, pharmaceuticals, oil and gas and other
industries.

xii
More Information on Predictive Analysis
Process

Predictive Analytics Process Flow

Leveraging Predictive Analytics

for Finance: The why and how?

Gain valuable insights

One of the biggest developments in SAP’s Predictive Analysis
Tool has been its integration with SAP HANA. HANA provides
remarkable output possibilities by using complex and heavy
algorithms run on the in-memory platform.

Big Data which is the large volume of unstructured data from

data sources such as external financial reporting systems,
RFID sensors, Twitter, Facebook and other social media, can
now be used to its advantage by using this powerful tool to
forecast future performance and drive strategic decision
making.

There are several routine processes that can be improved or

enhanced using predictive analytics, including:

xiii
 Target more profitable customers:
By analysing the customers it is possible to identify
small customer segments which are highly profitable.

 Cash forecasting:
Cash flow management is a key aspect of business to
plan its future cash requirements to avoid a liquidity
crisis. Leveraging data insights, financial professionals
can look at trends to identify slow payers, detect and
address system issues and improve receivable
management.

 Detection of financial risks:

Financial departments can leverage predictive analytics
to establish baseline criteria that makes it easier to
identify outliers before they can damage overall company
performance.

 Demand planning:
Predictive analytics can be used to forecast the sales
over a period determining the demand of the product.
This will help reduce returns from the customer and
scrapping of the product, increasing the profitability of
the company.

 Company performance risk

management:

xiv
 Predictive analytics can also help finance professionals
get a forecasted “sneak preview” into the financial mid-
period to avoid surprises.

 Receivables aging:

Finance professionals can optimise receivables aging

processes and collect overdue amounts faster by setting
alerts when customers deviate from past payment
patterns.

Planning and Predictive Finance:

It is important for an organization to have instant financial analytics
across multiple departments. After getting the data it becomes
very important for an organization to analyze the data. The data
modeling and prediction is done to test the potential impact of
strategic business decisions. SAP S/4HANA provides the option of
using planning and what if analysis, to predict both forward and
backward strategic decisions for your business. The special
benefits of this feature of SAP S/4HANA are:
There is a wide usage of real-time simulations and prediction. The
process helps in building a model of business patterns like
operating costs, revenue margin. The process is rapid and
beneficial in taking key decisions.
It analyses various trends, patterns, correlations obtained from the
business performance. It does cost analysis and real time revenue
prediction. This enables the finance department to do continuous
planning and forecasting for a month, quarter and year. The real
time monitoring also helps in updating earlier forecast with no time
lag.
There is a single view of all planning and forecasting information.
The planning of data across the organization remains consistent.
Every department remains aware of the planning of the other
departments within the organization. This brings a synergy in the

xv
organization and help in achieving more success. There are no
silos.
The accuracy of data forecasted using this feature increases and
the profit margin to improve. There is maximum utilization of cash
flow.

Budget Management:
The budget management feature is one of the basic functions of
the finance department of any organization. The central finance
team monitored various processes carefully. This process helps in
allocating money as per the needs of the various departments of
the organization. A deep analysis is necessary to get real and
future expenses. The most important aspect is to take critical
decisions about future expenses. The SAP S/4HANA model is
designed to meet the need of budget management for the
organization. The benefits included in this feature are:
There is a real-time monitoring and forecasting of data happening
on a daily basis. This helps in getting an early view into future
expenses before financial budget exceeds. The management can
take necessary decisions like channelizing their budget into
required departments or overheads. There is proper control and
management of the budget.
This also helps in simulations of decisions about expenses and the
budget situation of the organization. The manager has the options
to adjust reporting model as per the needs of the organization. The
manager is given real-time forecast of future cost development.
They have real-time insight into budget expenses and a recent
overview of expenses requests.
The advantages of using this feature are that decision-making
becomes simpler and faster. The organization remains aware of
their budget. The chances of exceeding the budget remain zero.
There is a reduction in unnecessary costs. The savings are used
for maintaining key performance indicators. It dynamically
improves the budget management process.

xvi
Continuous Cross System Control Monitoring:

Continuous Cross System Control Monitoring is the key to the

success of any profitable organization. The time spent by control
and compliance expert in performing control operation is
significant. They use manual processes to perform control
operations. However, the result obtained from them is outdated
and not up to mark. The failure in control and compliance is the
biggest risk for any organization. But, with the latest innovations,
SAP Process Control application help in test controls, finds
problems involved and provide a solution for them as soon as
possible. This helps the organization in reducing cost and leads to
efficient use of the efforts. The unique features of this are:
The monitoring of processes and controlling data are done easily
from the central repository data using automated high quality
business guidance system. The data are continuously tested and
monitored across large data volumes. The power of automated
testing and monitoring rules is also enhanced.
The best aspect here is one common view of control effectiveness
across the organization. This allows monitoring of problems across
multiple dimensions timely and resolution of them as soon as
possible. There is a systematic alignment of business. This
reduces cost and efforts and data reliability increases across the
organization.
Such high performance augments high transaction volumes. It
also provides robust views for CCM rules created by structured
query language or graphical user interfaces.

Scanning High Volume Data for Potential

Fraud:
The data used in the organization are obtained from various
sources like the customer’s data, inventory reports, financial
transactions, marketing details, phone calls, etc. These data sets

xvii
are kept in various forms like spreadsheets, loose sheets, emails,
etc. These data are also used by other stakeholders, including
auditors, third-party collaborating organization. In this scenario, it
becomes difficult to protect the data and keep up the sanctity of
the same. The risk of fraud increases as it is difficult to find the
leak. If a fraud is found at later stages, then it impacts the
company’s reputation and overall business.

xviii
Chapter 2

Predictive analytics in Finance

Predictive analytics in finance is the art and science of using
massive amounts of data to find patterns. These insights can
reveal what will happen next: what a customer will buy or how
long an employee might last. Predictive analytics involve
everything from sophisticated statistical modeling to
relatively simple data mining, and the practice is transforming
virtually every industry, as it provides the ultimate competitive
advantage

Corporate planning, budgeting and forecasting

Strategic planning

Operational planning

Capital planning

Expense planning

Profitability analysis

xix
Analytics discovers patterns in data, by turning raw data
into meaningful information. Analytics implies
being able to generate insights by analyzing data
generated by business systems. Because every business
has
several systems that support each business process, it is
important that data from these different systems is
merged before data analysis begins. This is critical to
attaining a holistic view of business processes and the
data generated by them. This chapter explains the
importance of merging data and its attendant challenges
and solutions

xx
Chapter 3

Study Methodology
Nature of Study
Objective of Study
Data Collected
Techniques of Analysis

xxi
Chapter 4
About the industry

xxii
Chapter 5

xxiii
Chapter 6
Conclusions and Suggestions

xxiv
Bibliography

1. Financial Analysis and Modeling using Excel and VBA, Chandan

Sengupta, Second Edition, 2017 , (MISL-WILEY)
2. Predictive Analytics For Dummies, Anasse Bari , Second Edition, 2016,
For Dummies
3. From big data to big profits: Success with Data Analytics, Russell Walker , First
Edition, 2015 , Oxford University Press
4. Business unIntelligence: Insight and Innovation beyond
Analytics and Big Data, Dr. Barry Devlin, First Edition, 2013 ,
Technics Publications, LLC
5. Applied Predictive analytics, Dean Abbott, First Edition, 2014, Wiley

xxv
 6. Appendix
Financial statements of companies

xxvi
Appendix A

Some Complex Results and their Proofs

xxvii
References

xxviii
xxix
Websites

https://www.predictiveanalyticstoday.com/what-is-predictive-analytics/

https://www.invenio-solutions.com/blog/leveraging-predictive-analytics-for-finance-the-why-and-how-
1

https://www.zarantech.com/blog/transforming-financial-reporting-analytics-using-sap-s4hana-finance/

https://www.ibmbigdatahub.com/blog/4-ways-predictive-analytics-finance-can-help-companies-see-
future

xxx