Industry Introduction(Banking):

Banks play a crucial role in market economies. They decide who can get finance and on whatterms and can make or break investment decisions. For markets and society to function,individuals and companies need access to credit.

The banking industry is data-intensive with typically massive graveyards of unused andunappreciated ATM and credit processing data. As banks face increasing pressure to stayprofitable, understanding customer needs and preferences becomes a critical success factor.New models of proactive risk management are being increasingly adopted by major banksand financial institutions, especially in the wake of Basel II accord. Through Data mining andadvanced analytics techniques, banks are better equipped to manage market uncertainty,minimize fraud, and control exposure risk.

Banking technology, few transactions actually use cash. In fact, hard currency represents only11% of the money supply in the U.S. The rest of our “money” flows digitally from a salary toa bank to a retailer, and then through the retailer’s supply chain, to be deposited in anotherbusiness’ account. to start the journey over again. That means our money has beentransformed into zeros and ones.

According to IBM’s 2010 Global Chief Executive Officer Study, 89 percent of banking andfinancial markets CEOs say their top priority is to better understand, predict and givecustomers what they want. Financial metrics and KPIs provide effective measures forsummarizing your overall bank performance.

But in order to discover the set of critical success factors that will help banks reach theirstrategic goals, they need to move beyond standard business reporting and sales forecasting.By applying data mining and predictive analytics to extract actionable intelligent insights andquantifiable predictions, banks can gain insights that encompass all types of customerbehavior, including channel transactions, account opening and closing, default, fraud andcustomer departure.

Introduction to Business Analytics:

Analytics is the use of modern data mining , pattern matching , data visualization andpredictive modelling tools for analyses and algorithm to make better business decisions.

Business analytics focuses on developing new insights and understanding of businessperformance based on data and statistical methods.

Business analytics makes extensive use of data, statistical and quantitative analysis,explanatory and predictive modeling and fact-based management to drive decision making.Analytics may be used as input for human decisions or may drive fully automated decisions.

Business analytics can answer questions like why is this happening, what if these trendscontinue, what will happen next (that is, predict), what is the best that can happen (that is,optimize .

Generally Industry uses three types of analytics as per requirement to find insights from alarge volume of data:

1.Descriptive (business intelligence and data mining)

2.Predictive (Prediction or likelihood /forecasting)

3.Prescriptive (optimization and simulation)

I am giving you some brief knowledge about these analytics step by step:

1.Descriptive analytics looks at data and analyzes past events for insight as to how toapproach the future. Descriptive analytics looks at past performance and understands thatperformance by mining historical data to look for the reasons behind past success or failure.Almost all management reporting such as sales, marketing, operations, and finance, uses thistype of post-mortem analysis.

Descriptive models can be used, for example, to categorize customers by their productpreferences and life stage. Descriptive modeling tools can be utilized to develop furthermodels that can simulate large number of individualized agents and make predictions.

For example, descriptive analytics examines historical electricity usage data to help planpower needs and allow electric companies to set optimal prices.

2.Predictive analytics turns data into valuable, actionable information. Predictiveanalytics uses data to determine the probable future outcome of an event or a likelihood of asituation occurring.

Predictive analytics encompasses a variety of statistical techniques from modeling, machinelearning, data mining and game theory that analyze current and historical facts tomake predictions about future events.

In business, predictive models exploit patterns found in historical and transactional data toidentify risks and opportunities. Models capture relationships among many factors to allowassessment of risk or potential associated with a particular set of conditions, guiding decisionmaking for candidate transactions.

Three basic cornerstones of predictive analytics are:

Predictive modelingDecision Analysis and OptimizationTransaction Profiling.

Simple example is for an organization that offers multiple products, predictive analytics canhelp analyze customers’ spending, usage and other behavior, leading to efficient cross sales,or selling additional products to current customers. This directly leads to higher profitabilityper customer and stronger customer relationships.

Another example is When a client applies for a loan the bank would like to be sure that theclient will pay back the full amount of the loan. So predictive analytics uses regressiontechnique to past data and use this to produce a probability that the borrower will repay theloan. This probability, along with the lenders experience is then used to decide if the bankshould lend to a particular client.

3.Prescriptive analytics is generally used for optimization of or business mode to makepredictions and then suggests decision options to take advantage of the predictions.

Prescriptive analytics goes beyond predicting future outcomes by also suggesting actions tobenefit from the predictions and showing the decision maker the implications of eachdecision option. Prescriptive analytics not only anticipates what will happen and when it willhappen, but also why it will happen.

Further, prescriptive analytics can suggest decision options on how to take advantage of afuture opportunity or mitigate a future risk and illustrate the implication of each decisionoption. In practice, prescriptive analytics can continually and automatically process new datato improve prediction accuracy and provide better decision options.

An example is energy and utilities. Natural gas prices fluctuate dramatically depending uponsupply, demand, econometrics, geo-politics, and weather conditions. Gas producers,transmission (pipeline) companies and utility firms have a keen interest in more accuratelypredicting gas prices so that they can lock in favorable terms while hedging downside risk.Prescriptive analytics can accurately predict prices by modeling internal and externalvariables simultaneously and also provide decision options and show the impact of eachdecision option.

In model optimzation we use prescriptive analytics to find out best optimal solution thatbank can use this for allow us to predict if a client will pay back the loan(80 % accuracy).

For example, prescriptive analytics can benefit healthcare strategic planning by usinganalytics to leverage operational and usage data combined with data of external factors suchas economic data, population demographic trends and population health trends, to moreaccurately plan for future capital investments such as new facilities and equipment utilizationas well as understand the trade-offs between adding additional beds and expanding anexisting facility versus building a new one.

Role of Analytics:

While analytics aren’t exactly new to the world of banking, plenty of banks are gearing up fortheir next big analytics push, propelled by a load of data and new, sophisticated tools andtechnologies. Why has business analytics jumped to the top of the priority list for banks? Picka reason. Regulatory reform, managing risk, changing business models, expansion into newmarkets, a renewed focus on customer profitability – any one of these is reason enough formany banks to reconsider what today’s analytics capabilities can offer.

As per Deloitte research, three business drivers increase the importance of analytics withinthe banking industry

Regulatory reform – Major legislation such as Dodd-Frank, the CARD Act, FATCA(Foreign Account Tax Compliance Act) and Basel III have changed the businessenvironment for banks. Given the focus on systemic risk, regulators are pushing banksto demonstrate better understanding of data they possess, turn data into informationthat supports business decisions and manage risk more effectively. Each request hasmajor ramifications on data collection, governance and reporting. Over the nextseveral years, regulators will finalize details in the recently passed legislation.However, banks should start transforming their business models today to comply witha radically different regulatory environment.

Customer profitability – Personalized offerings are expected to play a big role inattracting and retaining the most profitable customers, but studies show that a smallpercentage of banks have strong capabilities in this area. The CARD Act and DurbinAmendment make it even more important to understand the behavioural economics ofeach customer and find ways to gain wallet share in the most profitable segments.

Operational efficiency – while banks have trimmed a lot of fat over the past fewyears, there is still plenty of room for improvement, including reducing duplicativesystems, manual reconciliation tasks and information technology costs.

Credit Scoring Modelling for Retail Banking Sector:

Our problem is concerned with who a bank should loan its money to. When a client applies for a loan, the bank would like to be sure that the client will pay

back the full amount of the loan.

We need effective models that allow us to predict if a client will pay back the loan.

What we have is historical data for several variables.

We are trying to fit a model to this historical data so we can estimate a probability ofdefault.

So analytics helps to determine the answers to all these questions and build astrategy for effective decision making in banks so that banks can reduce the risk forgranting loan to which customers according to defaulting probability for respectivecustomers in a bank.

With banking analytics your organization gains a complete and consistent view of all keyprofitability drivers so you can:

• Manage risk effectively

• Track and monitor sales, margins and operational performance

• Analyze results and identify and predict trends in channels, regions, products, demographicsand customer behaviour.

• Dynamically adjust plans to achieve profitable growth.

• Help meet regulatory demands.

How analytics can help you increase customer profitability and satisfaction, manage risk andbe more operationally efficient.?

Fraud detection in banking is one of the major complicated task that discover by the use ofanalytics.

Fraud detection in banking is a critical activity that can span a series of fraud schemes andfraudulent activity from bank employees and customers alike. Since banking is a relativelyhighly regulated industry, there are also a number of external compliance requirements thatbanks must adhere to in the combat against fraudulent and criminal activity.

Banks Need To Improve Use of Customer Analytics.

Banks also can use analytics to enhance their strategic, back-office activities by:

● Identifying the profitability of customers across lines of business

● Reducing risk by better forecasting defaults and late payments

● Using predictive analytics technology to determine the amount of money each uniquecustomer is allowed to withdraw from an ATM

● Segmenting customers based on demographics, relationships and transaction behaviours toincrease wallet share and individual profitability

● Enhancing online merchandizing by analyzing customers’ purchasing

● Supporting mobile phone transactions and analysis of those transaction

Conclusion:

In banks, analytics can help immensely in a variety of areas ranging from fraud detection andprevention to risk management. At last we can say that the world is dynamic , time is less ,data is large so for taking smarter decisions we have to address most impacting factors thatinfluence core issues regarding any domain knowledge and companies can answerfundamental questions such as What is happening?, Why is it happening?, What is likely tohappen in the future?, and How should we plan for that future? and helps your organizationrise to the challenge with better business insight, planning and performance.

CASE STUDY :

We have a banking data and based on this data we can analyse certain questions that bankmanager would likely to ask:

1. Create a dataset with only those Sales officers who have highest number of accountswithin every branch.

2. Which branch officer has highest number of accounts?3. Calculate the total number of accounts from every zone?4. Which zone has highest accounts? Also find the zone with maximum branches?5. Create a dataset with only those Sales officers who are from central 1 zone and main

branch.6. Categorize the account officers into the following 4 categories:

a. Top performer – greater than 65% active accountsb. Average performer– between 45% to 65% active accountsc. Below average performer – less than 45% of active accounts

7. Which is the worst performing zone?8. Create a new variable by combining Sales officer’s name with their respective branch

code.9. Create a pdf report by listing only those Sales officers whose dormant (inactive)

accounts is 0.

10. Give the list of Sales officers who has neither dormant (inactive) accounts nor activeaccounts in a HTML file.

11. Create a new variable in the dataset, wherever number of dormant (inactive) is greaterthan active accounts then give it as bad else give it as Good.

12. Create a new dataset consisting of account officers with 100% dormancy (inactive)percentage.

Create the following:

a. A report consisting of total number of accounts and balance under differentcategories for “Main Branch”

b. A branch level report of total number of accounts and balance, listed in the orderof the best performing branch to the least.

c. List out performing and non-performing account officers in 2 reports, consistingof the details of their zone, branch, accounts and balance. Also, detail the criteriaused for this differentiation.