Big Data Use-cases – Banking and Financial Services

Big data has become the latest buzz word in Information Technology world and in the business arena from board room to product development and sales & marketing. There is lot of hype and noise in the industry. Many business leaders are curious about the business use case for Big data that can give them competitive edge and head-start in reaching the finish line before others. Many IT vendors from IBM, SAP, Informatica, Microsoft, Oracle, HP, Cloudera, FOSS vendors are investing and pushing their solutions & offerings into the market place. IBM has invested millions of dollars into Smarter Planet initiative and primarily with BigInsights platform. Since 2005, IBM has spent over $14 billion to acquire twenty-five software companies specializing in data analytics, and today it has over 8,500 analytics consultants. During March of this year. H-P said it will reallocate the $3 billion to $3.5 billion between now and 2014 to Big Data analytics, cloud computing and security infrastructure. Moreover, the U.S. government is investing $200 million in big data projects to help the U.S. jump ahead in the next frontier of computing.

So Big Data is here to stay and change our world. MIT economist Erik Brynjolfsson compares the implications of data analytics to an important invention four centuries ago. Brynjolfsson noted that the invention of the microscope resulted in a “revolution in measurement” that enabled scientists to examine objects at the cellular level, objects that were previously invisible to the naked eye. Using this analogy, data analytics is a key enabler for organizations to see previously undetectable patterns in data in order to better understand risk exposure and to better predict decision outcomes (predictive analytics).

Some of the industry in general like ECommerce, Retail, Banking and Financial has made some capital investment in Big Data in past 2 years while Healthcare, Manufacturing and Utility are gaining traction. Here’s few that I have seen as industry use case that’s being considered as Pilot or Proof of Concept/Value projects.

Big Data use-cases in Banking & Financial Services

1. Fraud Detection:

You may not be surprised that Banks and Credit cards are monitoring your spending habits on real-time basis. One of the large credit card issuing bank has implemented fraud detection system that would disable your card if they see suspicious activity based on your past history with spending patters and trends. In addition to the transaction records for authorization and approvals, banks and credit card companies are collecting lot more information from location, your life style, spending patterns. Credit card companies manage huge volume of data from individual Social Security number and income, account balances and employment details, and credit history and transaction history. All this put together helps credit card companies to fight fraud in real-time. Big Data architecture provides that scalability to analyze the incoming transaction against individual history and approve/decline the transaction and alert the account owner.

2. Customer Segmentation

Customer Segmentation applies in every industry from Banking to Retail to Aviation to Utility and others where they deal with end customer who consume their products and services. In Banking & Financial industry, customer segmentation is a key tool in risk scoring analysis and for sales, promotion and marketing campaigns. In addition to existing information that banks and FIs collect from day to day transactions from customers, they are also buying external data like home values, merchant records from hotels, aviation, retailers, etc. The 360 degree view of customer is still a work in progress and Big Data is enabling filling in the gaps by providing the processing power needed to mine for intelligence from underlying data.

The major objectives of segmentation are:
  • Customized product offering
  • Customized and priority service
  • Improve relationship with profitable customers and cut resources spent on loss making customers
  • Better offering to new customers based on the intelligence gained from the existing customer segment they belong to
  • New product development and bundling as per the customer segment profile

3. Customer Sentiment Analysis

The bank can now respond to negative (or positive) brand perception by focusing its communication strategies on particular Internet sites, countering – or backing up – the most outspoken authors on Twitter, boards and blogs. When a company releases a new product that’s causing problems, analyzing comments in social media sites or product review sites can enable it to quickly remediate.

4. Crowdsourcing

Some of the larger institutions have realized they can use analytics to learn about new lines of business and products, to ask customers what they think, and to get ideas. In a move to expand its utility beyond simply finding better answers to known statistical problems, data-science startup Kaggle is now letting its stable of expert data scientists compete to tell companies how they can improve their businesses using machine learning.

4. Sales and Marketing Campaigns

On the customer experience side, every time you get closer to delighting your customer by showing that you understand what their real needs are, without blindly sending them emails and credit card offers, it makes the customer view their institution as caring about them and understanding what their needs are.

5. Call Center Analysis

For decades, companies have been analyzing call center data for staffing, agent performance, network management. But with big data age, many new interesting software are being implemented today in attempt to take unstructured voice recordings and analyze them for content and sentiment. Banks are applying text and sentiment analysis to this unstructured data, and looking for patterns and trends. Many banks are integrating this call center data with their transactional data warehouse to reduce customer churn, and drive up-sell, cross-sell, customer monitoring alerts and fraud detection.

These are just few of the use cases that I have highlighted here to give a fair idea about how Big Data is being leveraged in this industry. If you have use-case that you are working with, please add it to the comment section.



Analytics in Banking Services

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

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

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

Insights about these banking behaviors can be uncovered through multivariate descriptive analytics, as well as through predictive analytics, such as the assignment of credit score. Banking analytics, or applications of data mining in banking, can help improve how banks segment, target, acquire and retain customers. Additionally, improvements to risk management, customer understanding, risk and fraud enable banks to maintain and grow a more profitable customer base. The importance of these measures has been implied in the Basel II accord that explicitly emphasizes the need to embrace intelligent credit management methodologies in order to manage market uncertainty and minimize exposure risk.

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

A host of significant, recent changes in the banking industry have resulted in a long list of business challenges that the practice of business analytics may be positioned to address. A number of financial institutions have been quick to recognize and adopt this emerging technology – and it is changing the banking landscape and giving banks and financial institutions previously untapped savings, margins and profit. For example, Bank of America Merrill Lynch is using Hadoop technology to manage petabytes of data for advanced analytics and new regulatory requirements.

As per Deloitte research, three business drivers increase the importance of analytics within the 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 business environment for banks. Given the focus on systemic risk, regulators are pushing banks to demonstrate better understanding of data they possess, turn data into information that supports business decisions and manage risk more effectively. Each request has major ramifications on data collection, governance and reporting. Over the next several years, regulators will finalize details in the recently passed legislation. However, banks should start transforming their business models today to comply with a radically different regulatory environment.
  • Customer profitability – Personalized offerings are expected to play a big role in attracting and retaining the most profitable customers, but studies show that a small percentage of banks have strong capabilities in this area. The CARD Act and Durbin Amendment make it even more important to understand the behavioral economics of each 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 few years, there is still plenty of room for improvement, including reducing duplicative systems, manual reconciliation tasks and information technology costs.

Let us consider some of the prominent use cases for banking analytics:

Fraud Analysis

The Association of Certified Fraud Examiners’ 2010 Global Fraud Study found that the banking and financial services industry had the most cases across all industries – accounting for more than 16% of fraud.

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

In a sample study conducted by ACFE, it was observed that most of the fraud occurred due to Corruption and Cash on Hand. Here is the breakdown of the results:

Banking/Financial Services – 298 Cases


Number of Cases

Percent of Cases




Cash on Hand






Check Tampering












Expense Reimbursements



Financial Statement Fraud






Register Disbursements




The following techniques are effective in detecting fraud. Auditors should ensure they use these, where appropriate.

  • Calculation of statistical parameters (e.g., averages, standard deviations, high/low values) – to identify outliers that could indicate fraud.
  • Classification – to find patterns amongst data elements.
  • Stratification of numbers – to identify unusual (i.e., excessively high or low) entries.
  • Digital analysis using Benford’s Law – to identify unexpected occurrences of digits in naturally occurring data sets.
  • Joining different diverse sources – to identify matching values (such as names, addresses, and account numbers) where they shouldn’t exist.
  • Duplicate testing – to identify duplicate transactions such as payments, claims, or expense report items.
  • Gap testing – to identify missing values in sequential data where there should be none.
  • Summing of numeric values – to identify control totals that may have been falsified.
  • Validating entry dates – to identify suspicious or inappropriate times for postings or data entry

Customer Analytics

Banks and credit unions are constantly at risk of losing customers or members, and in order to stem the flow, they may offer their best customers better rates, waive annual fees and prioritize treatments. However, such retention strategies have associated costs, and you cannot afford to make such offers to every single customer. The success and feasibility of such strategies is dependent on identifying the right action for the right customer. Consumers today want to bank anywhere, anytime with the convenience of using their smartphones and iPads at their fingertips. As we move toward a cashless society, the future of banking will be shaped by how the physical and virtual worlds of banking converge. Smarter banks will increasingly invest in customer analytics to gain new customer insights and effectively segment their clients. This will help them determine pricing, new products and services, the right customer approaches and marketing methods, which channels customers are most likely to use and how likely customers are to change providers or have more than one provider.

Risk Analytics

Accenture recently completed a global study capturing and synthesizing the insights from more than 450 risk management analytics professionals in three industries to examine how they use risk analytics to tackle industry challenges and market volatility. The study was intended to assess companies’ current level of risk analytics maturity—their quantitative and qualitative tools and techniques designed to estimate the impact and frequency of specific risks, as well as their ability to use analytics to drive business outcomes and proactively manage risks and rewards. Across the industries studied, banking is predicting the greatest increase in risk analytics investments, with 73 percent of banking respondents foreseeing more than a 10 percent rise in expenditure. In terms of specific capabilities, risk analytics spending is expected to increase most in areas of data quality and sourcing, systems integration and modeling. Here are other key findings:

  • Forty-two percent of banks calculate risk indicators by collecting data from the execution environment that feeds monitoring dashboards.
  • Better modeling is a critical component of credit risk analytics, with European banks more likely to use only internal models (18 percent versus 13 percent globally), while Chinese banks are more likely to use only external models (14 percent versus 7 percent globally).
  • Most banks have a dedicated risk analytics group with between one and 20 people deployed.
  • Eighty-five percent of banks have a risk analytics group for credit risk validation.
  • Significant majorities of banks across all regions have quality controls in place over the collection of historical data. ASEAN institutions are most likely to do so at 85 percent, and Europe is least likely, at 64 percent.
  • More than three-quarters (77 percent) of banks across all regions use stress-testing regularly to verify capital adequacy.

American Banker Research recently set out to discover the demand and usage for customer analytics throughout the banking industry. To their surprise, most (71%) of the 170 bankers in the weighted survey do not use customer analytics, but within a year that might not be true. Among those non-users, the plans to buy analytics are not impressive. Only 2% plan to buy customer analytics in the next six months, 4% in the six to 12 months and 14% in more than a year from now.

Cost was the biggest barrier, noted by 36%. Another issue is more pressing IT issues taking precedence – about 32% of bankers surveyed said a focus on other initiatives was the primary obstacle to using customer analytics at their institution. The third primary reason for not using customer analytics, given by 23% of these bankers, was skepticism about the ability of the software to provide business value or a return on investment. On the other hand, 33% of bankers who do use customer analytics say they plan to increase spending on such programs by a mean of 15% in 2013. About 35% of these users are interested in adding social media content to the data they analyze.

And these bankers reported several benefits to using the software. More than a third (37%) said the software improves the impact of marketing efforts. About 28% of respondents said that an increase in wallet share was the top benefit their institution reaped from customer analytics. A smaller group, 18%, identified improved underwriting and/or a reduction in loan loss rates as the primary benefit.

There have been many exciting advances in analytics and business intelligence recently including:

  • IBM’s Watson platform, which beat human champions on the trivia show Jeopardy! by using natural-language analytics to understand questions, context and semantics, then analyze terabytes of data to identify and rank likely answers
  • Algorithms that measure their own accuracy and feed that information back into the model to create self-improving predictive analysis
  • Unstructured data analytics that can incorporate information from online discussion forums, social networks and call scripts to determine customer sentiment or market opportunities
  • Real-time analysis of data sources, such as financial markets, stock exchanges, or news.

Implementing business analytics across the bank can be a daunting and potentially expensive prospect, due to:

  • Complex, heterogeneous technology architectures
  • Operationally optimized but siloed processes and systems
  • Data fragmented across multiple databases
  • Constrained investment budgets with competing agendas
  • Lack of skilled resources
  • Perception that the data available is of insufficient quality to support analysis.

All of these are genuine obstacles, but it should not be assumed that analytical insight cannot be extracted until they have all been resolved. That road leads either to major programs striving to create perfect data able to answer any question, or to an acceptance that any such efforts are futile. Organizations do not necessarily have to solve all of these issues before a successful analytics project can begin.

A more pragmatic approach starts with selecting a critical question or objective, identifies the necessary data and, recognizing that the data is not perfect, and derives the answer and information correlations with a corresponding confidence level. This approach does not replace the strategic architecture investment required to reach accuracy, but it provides a framework for business owners to control the level of their expenditures in a way that is commensurate with the benefit to be unlocked.


  1. Accenture 2012 Risk Analytics Study: Insights for the Banking Industry
  2. Analytics in Banking by Deloitte
  3. 2010 Global Fraud Study: Report to the Nations on Occupational Fraud and Abuse, Association of Certified Fraud Examiners
  4. Global Technology Audit Guide: Fraud Prevention and Detection in an Automated World. The Institute of Internal Auditors, 2009.
  5. The shift to analytics: the next wave for transaction banking by IBM
  6. IDC Financial Insights, 2010
  7. IDC’s Vertical Research Survey, 2010