In the latest edition of FINsights, Infosys partners with FICO to walk you through the various issues and roadmaps of analytics with the goal of providing insights to help launch successful analytics initiatives.
Post-crisis analytics: Six imperatives
By Dr. Andrew Jennings, FICO
In the post-crisis era, companies that succeed with analytics will not be those that simply use more of them, but those that use them in smarter ways. To succeed with analytics, one needs to understand the context of the data, the operational context of the decision and the underlying business relationships. FICO has identified six imperatives for analytics in an environment where the past may no longer be a good model for the future. At the core of these imperatives is the decision model – a working model that explains the relationships between all the drivers of a decision and its results. The decision model can be used in business planning and is a critical element in strategy optimization. Using such tools is essential in understanding the business situation and creating lasting business advantage.
Structuring the Unstructured Data: The Convergence of Structured and Unstructured Analytics
By Bala Venkatesh, Kiran Kalmadi and Shivani Aggarwal, Infosys Limited
Financial services firms are increasingly analyzing unstructured data - documents, call center logs, blogs, wikis, tweets, and surveys to understand customer needs, prevent frauds and expand customer base. The rapid adoption of social media by financial services industry has resulted in the generation of large amounts of unstructured data. This has prompted firms to look at social analytics to derive structured insights out of social media. As unstructured and structured data analytics are converging, financial institutions need analytic vendors to come up with products that blend unstructured analytics (like social analytics) with structured analytics (risk analytics). This article analyzes unstructured data, the various analytics vendors in the space, and applications in the financial services industry.
Fusing Economic Forecasts with Credit Risk Analysis
By Dr. Andrew Jennings, Carolyn Wang, FICO
As the financial services industry prepares for a measured economic recovery, it is critical to take stock of a key lesson of the financial crisis – that risk, by its nature, is dynamic. There's no better time for lenders to re-evaluate risk management practices in order to be better prepared for measured growth or buffer against a lingering recession. Today's economic realities call for a paradigm shift in risk management - one that includes new analytics that go beyond the traditional assumption that past risk levels are indicative of future risk. This article discusses new methods for systematically incorporating economic data into scoring systems, allowing lenders to balance consumer level information with changing economic trends. It also shares results from lender applications of this methodology to 'get ahead of the curve' by more closely aligning risk strategies with future performance.
Unstructured Data Analytics for Enterprise Resilience
By Dilip Nair, Srinivasan V. Ramanujam, Allen Selvaraj, Infosys Limited
Enterprise resilience is an effort across the organization to anticipate and successfully navigate adversity. The recent financial crisis has exposed the ability (or lack thereof) of companies, industries and even countries to plan and respond to changes. Decision making processes are limited by the information available through restricted traditional channels. This article explains how moving to automated, fact-based and real-time monitoring of risk by utilizing the power of digital media can help an organization plan for resilience well in advance.
Why Real-Time Risk Decisions Require Transaction Analytics
By Brad Jolson, Cecilia Mao, James Patterson, FICO
The double shock of recession-spurred delinquencies and new regulatory inroads on profit is making creditors acutely aware of the need to make sharper risk distinctions among customers. In both account management and collections, they need precise insights to guide more targeted and timely actions. Every bank with transacting accounts has the potential to achieve this higher level of risk precision, using credit card and debit card account transaction data. This article demonstrates how combining transaction scores with traditional behavior scores and credit bureau risk scores, increases accuracy of risk predictions. It also discusses the advantages of deploying transaction analytics in real-time mode, to accelerate awareness of developing risk and to enable early intervention to mitigate losses.
Ten Questions to Ask of Your Optimization Solution
By Lisa Kart, Karthik Sethuraman, FICO
With several optimization solutions in the market today, how do banking institutions evaluate which one will work best for their business? This article defines the criteria needed to evaluate alternative solutions and make this determination - from assessing data sensitivities, stress-testing, and leveraging other analytics assets to validating 'optimal' points, handling business trade-offs and deployment. Banks that follow these guidelines, in combination with sound methodology, deep domain expertise and the right software, typically see 5%–20% profit improvement.
Practical Challenges of Portfolio Optimization
By Lisa Kart, Mac Belniak, FICO
The word 'optimization' is often used informally to describe any technology that improves business results. But optimization is a mathematical methodology used to make decisions for allocating finite resources to achieve an overall objective, subject to constraints imposed by the environment. There are many practical challenges when applying optimization to develop superior decision strategies. FICO experts examine these challenges and demonstrate how optimization enables organizations to improve performance by quickly identifying the best offer for each customer, while balancing objectives under existing business constraints.
Analytics in Cross Selling – A Retail Banking Perspective
By Yamini Aparna Kona, Balwant C. Surti, Infosys Limited
The case for cross-selling to existing customers of a bank is an easy one - the difficult part is executing it. Today, there are several different techniques for effective cross-selling. The common thread that runs across them is data and analytics. Data mining and analytics have helped in discovering trends and populating models that are the backbone of predictive analytics. Value analytics is another approach to cross-selling. The call center, the branch, the web - every distribution/ service channel - all leverage analytics in some way, to cater to the entire gamut of customer needs. This article analyzes the different ways in which cross-selling works with analytics, its intrinsic challenges, and the emerging trends in the analytics field.
Analytics as a Solution for Attrition
By Sivaramakrishnan Rajagopalan, Infosys Limited
Switching banks surprisingly requires very little impetus for consumers today - it can be a slightly higher savings rate, a free bonus offer, or a non-satisfactory customer service call. Attrition is a serious concern for the financial services industry. Analytical techniques such as customer profiling and predictive modeling hold great promise as powerful tools to enhance customer retention, drive revenue growth, profitability, and manage attrition, explains the author.
Customer Spend Analysis: Unlocking the True Value of a Transaction
By Vinay Prasad, Infosys Limited
Financial institutions have compiled a wealth of customer transaction data over the years. When properly analyzed, such data can unlock a treasure trove of predictive information including customer spend patterns. This article analyzes spend events, techniques to identify spend events, and the process of utilizing spend patterns to predict customer spending behavior. The information extracted can provide powerful insights, driving improved targeted marketing efforts.
A Dynamic 360° Dashboard: A Solution for Comprehensive Customer Understanding
By Vishal Gupta, Dr Radha Krishna Pisipati, Infosys Limited
In today's financial services marketplace, competitiveness hinges on achieving a dynamic view of your customer. Applications and databases in silos, coupled with myriad social and user generated information form a tidal wave of data. Our experts explain how this data can be managed and transformed into actionable information by developing a modern 360° dashboard.
Developing a Smarter Solution for Card Fraud Protection
By Manoj Pandey, Infosys Limited
Card fraud losses for the US payment industry are estimated at nearly $10 billion. Due to cost constraints and the current economic condition, banks are reluctant to invest in fraud detection alternatives that require high investments in infrastructure. The most effective and cost-friendly answer to this problem is developing advanced analytics-based solutions. This article explains in detail how banks should focus on advanced concepts such as dynamic profiling, advanced analytics and fraud metrics to increase transaction processing speed and accuracy of fraud detection.
Using Adaptive Analytics To Combat New Fraud Schemes
By Jehangir Athwal, Larry Peranich, Scott Zoldi, FICO
The fight against payment card fraud resembles an arms race, with card issuers deploying ever more sophisticated anti-fraud measures, and fraudsters continually evolving strategies to evade those measures. Issuers typically rely upon neural network fraud models that take advantage of huge historical datasets to recognize recurring fraud patterns and reduce fraud losses. However, the fraudsters' decentralized nature and short time-frame give them an evolutionary advantage over the issuers' multi-month to multi-year analytic development cycles. Adaptive analytics, when used with these neural network models, swing the advantage back to the issuers by continually adapting the fraud detection models based on the latest fraud behavior. This not only improves model performance, but also extends the useful lifetime of the static neural network models. In a test described in this article, adaptive modeling techniques, improved fraud account detection by nearly 20% and real-time value detection by more than 15%, at a 10:1 Account False Positive Ratio.
To Fight Fraud, Connecting Decisions is a Must
By Scott Zoldi, Kyle Hinsz, FICO
Financial institutions provide customers various types of accounts and an ever-increasing number of ways to access them. Traditional fraud detection systems are highly specialized to compute risk for a particular access method, but this approach is running up against serious limitations. It is vital for future systems to take the next step in fraud detection, by profiling a wider range of information and connecting it across customers and accounts. Advanced analytics must not only intelligently use data across these diverse accounts and access combinations, but dynamically detect new fraud patterns with accuracy, even as service/ channel usage and other facets of customer behavior change.
Productizing Analytic Innovation: The Quest for Quality, Standardization and Technology Governance
By Scott Zoldi, Alexei Betin, FICO
The use of predictive analytics is becoming ubiquitous within modern financial IT solutions. However, with the increased complexity of analytic offerings, comes the need for a standardized process and build methodology across all analytic model development. The software engineering profession, facing nearly identical constraints, has created governance methodologies that are re-usable for analytic development. As such, the quest of the analytics manager is two-fold:
Analytics in Retail Banking: Why and How?
By Anjani Kumar, Raghavendra Shenoy, Infosys Limited
Given today's hyper-competitive environment and customer acquisition costs, banks need to ensure that their existing customers remain satisfied with the quality of service and offerings. It is imperative for banks to implement robust analytics solutions, incorporating defined metrics that provide a unified view of customers, across lines of business and channels. This article examines the various applications of analytics and provides pointers for analytics implementations.
Business Analytics in the Wealth Management Space
By Guruprasad Rao, Harpreet Arora, and K N Rao, Infosys Limited
Today's difficult investing environment has created an increasingly demanding breed of investors. From managers of institutional investments, to high net-worth individuals, to trusts; investors want an increased breadth and depth of information. To effectively respond to these demands, wealth management firms must invest in improved information management and analytics. This article provides a roadmap for firms to harness the power of information, through analytics by understanding their data and structuring it appropriately.
Zero Distance at Infosys
Learn about how Infosys innovates through Design Thinking
Our representative will get in touch with you shortly.