Banking Analytics Training Program

Transcription

1 Training (BAT) is a set of courses and workshops developed by Cognitro Analytics team designed to assist banks in making smarter lending, marketing and credit decisions. Analyze Data, Discover Information, Gain Knowledge, Attain Wisdome. Cognitro s training program is an industry-standard program designed to introduce the concept of banking analytics and its applications in various domains of credit, operational and marketing to banking professionals and analysts. It allows banks to acquire advanced quantitative skills and knowledge of cutting-edge data mining techniques to assist thier bank executives in making information-driven decisions and gain competitive advantage. What is? 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. For the past decade, Cognitro Analytics has been empowering banks to learn from their abundant historical data, by applying data mining and predictive analytics to extract actionable intelligent insights and quantifiable predictions. These insights 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. The collective use of descriptive and predictive analytic techniques to the banking industry is called Banking analytics. Why? 1, 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 Basel II accord that explicitly emphasizes the need to embrace intelligent credit management methodologies in order to manage market uncertainty and minimize exposure risk. 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.

2 BAT Program Structure Track 1 Track 2 Marketing and CRM Credit Risk Management Course Data Mining Techniques: Theory and Practice Course I: Banking CRM Analytics Course II : Banking Risk Analytics Applied Customer Segmentation Design of Experiments for Direct Marketing Credit Risk Modeling for Basel II Credit Scorecard Development and Practice Data Mining: Project Management 2

3 Course Description Course I : Banking CRM Analytics Who Should Attend - Bank marketing and customer relation executives and officers - All Bank personnel and IT staff running or supporting CRM activities - Bank marketing managers who wish to improve customer retention rates and increase campaign revenues. - Technology Experts, BI directors, developers, DBAs, as well as analysts and consultants. 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. This two-day course is designed to show banks how to compete for customers effectively through analytics; enabling them to profit from thier data extracted from data warehouse and survey analysis by discovering key drivers for customer retention and loyalty. Course Benefits At the end of the course, attendants should be able to find answers to questions such as: -Which financial instruments are more likely to be requested together by groups of customers -What is the profile of a frequent ATM customer. -What transactions a customer typically do before closing his/her accoun -How profitable is a customer over the lifespan of his/her account Banking CRM Analytics Course Example of Case Studies 1) National Bank of Canada increased Customer Retention rate by 40% through the development of an accurate early-warning alert system for Customer Retention and Loyalty estimation. 2) The Banco Santander Totta (Portugal) increased conversion rates on credit card offers from 5% to 30% and reduced the churn by 25% by using data mining techniques to know the wants and needs of the least risky Credit Card holders. 2 Topics Discussed DAY ONE A- Introduction to data mining - Definition of data mining - Divisions of data mining tasks (& introduction to algorithms) Supervised learning (and example business uses) Categorical target, vs. Continuous target Unsupervised learning Cluster analysis Anomaly detection - CRISP-DM Standard Data Mining Process Model - Fields that contribute to data mining B- Data Mining & Analytics in Banking Intelligence - What data to mine? Warehouse data Customer characteristics: age, income, branch Customer behavior: transactions, fees Products, balances, tenure, etc. - Appended data Credit bureau, Demographics / firmographics Call center data (text mining), Survey data DAY TWO C- Applications across the customer lifecycle - Acquisition and Advertising - Direct marketing Response, Account opening, Account usage - Cross sell / Up-sell / Balance growth - Traditional direct marketing (mail & phone) - Targeted recommendations at every customer contact point: phone, branch, ATM, web - Loyalty / retention / attrition - Assigning predictive score to customer record indicating the likelihood that a customer close the account or the entire relationship 4) Data Mining & Analytics for Customer Insights - Customer profitability - Customer segmentation - Branch & ATM site selection - New & Lost Customer analyses - Customer Satisfaction tracking - Competitive analyses - Open & Closed Account research Open Survey: everything go fine? Closed Survey: why close? - Problem resolution follow-up research

4 Course Description Course II : Banking Risk Analytics Who Should Attend - Bank executives and risk officers - All Bank personnel and IT staff supporting risk managemenet - Anyone involved in building predictive risk management or responsible for validating and monitoring their behavior and performance. New models of proactive risk management is being increasinlgy adopted by major banks and financial insititutions, 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. This two-day course introduces an overview of industry best-practice risk management models and how to develop them in the conext of Basel-II compliance and guidelines. Course Benefits At the end of the course, the attendant should be able to find answers to complex questions: -How can you improve your Basel-II compliance through advanced analytics methodolgies -How can you implement fraud detection and prevention and minimize operational risk -How can you predict bad loans and minimize risk of default. Topics Discussed DAY ONE DAY TWO 3 Banking Risk Analytics Course Example of Case Studies 1) Bank of America reported a net reduction of 17% in loan defaults following the adoption of predictive analytics in their credit scoring system. 2) The Royal Bank of Canada saved over $15m after the implementation of a new Fraud Rules Engine. A- Introduction to data mining - Definition of data mining - Divisions of data mining tasks (& introduction to algorithms) Supervised learning (and example business uses) Categorical target, vs. Continuous target Unsupervised learning Cluster analysis Anomaly detection - CRISP-DM Standard Data Mining Process - Fields that contribute to data mining B- Data Mining & Analytics in Banking - What data to mine? Customer characteristics: age, income, branch Customer behavior: transactions, fees Products, balances, tenure, etc. C- Data Mining for Risk Management and Basel II - Introduction to Basel II - Objectives of the new Basel Capital Framework - Structure of the new Accord - Credit Risk - Menu of Approaches - Operational Risk - Menu of Approaches - Market Risk - Menu of Approaches C- Data Mining for Risk Management and Basel II (cont) -A Bird s eye view of Basel II -Pillar II : Improvises Supervisory Review -Pillar III: Enhances disclosure and transparency -Potential benefits of using Data mining techniques in Basel II implementation Default prediction Reduce loan loses by predicting bad loans High risk detection Tune loan parameters ( e. g. interest rates, fees) in order to maximize profit D- Data Mining & Analytics in Fraud Prevention - Magnitude of Fraud & Types of Fraud Challenges Data security Fraud is rare Difficulties in Obtaining "Ground Truth" - Traditional Judgmental Approaches Experience-driven Issues: Variable cutoff values, Relative importance of variables, Redundancies - Predictive Scoring Models Calculate context variables Build predictive scores Minimize the total cost, i.e., fraud loss plus opportunity loss

5 Banking Risk Analytics s Credit Risk Modeling for Basel II Course Overview Banking Risk Analytics - Credit Risk Modelling for Basel II - Credit Scorecard Development and In this course, the attendees will learn, hands-on, how to develop credit risk models in the context of the recent Basel II guidelines. The course provides a sound mix of both theoretical and technical insight, as well as practical implementation details, illustrated by several real-life case studies. Learn How To - Develop PD, LGD, and EAD models for Basel II - Validate and stress-test Basel II models - Ensure your organization is in compliance. Prerequisits Before attending this course, you should have business expertise in credit scoring and an understanding of statistical classification methods. Previous SAS software and SAS Enterprise Miner experience is helpful but not necessary. Cognitro Banking Analytics s Target Audience Anyone involved in building scoring/predictive credit risk systems, or responsible for validating and monitoring their behavior and performance Banking CRM Analytics - Applied Customer Segmentation - Design of Experiments for Direct Marketing Course Contents - Review of Basel I and Basel II - Sampling and Data Preprocessing - Developing PD Models for Basel II - Developing LGD and EAD Models for Basel II - Validation, Backtesting, and Stress Testing - New Techniques to Develop PD, LGD, and EAD Models for Basel II - Survival Analysis for Profit Scoring Duration 4 Days 4

6 Banking Risk Analytics s Credit Scorecard Development and Course Overview Banking Risk Analytics - Credit Risk Modelling for Basel II - Credit Scorecard Development and This business-focused course provides the necessary knowledge to plan, develop, implement, and maintain risk scorecards in-house. The course offers a high-level introduction to credit risk management and covers scorecard implementation strategies. Learn How To - Create business and project plans for scorecard development - Develop and validate intelligent credit risk scorecards in a step-by-step fashion - Generate scorecard and portfolio performance reports. Prerequisits Cognitro Banking Analytics s Banking CRM Analytics - Applied Customer Segmentation - Design of Experiments for Direct Marketing Before attending this course, you should have business expertise in credit scoring and an understanding of statistical classification methods. Previous SAS software and SAS Enterprise Miner experience is helpful but not necessary. Target Audience Credit risk/scoring managers and data miners; those involved in model vetting/ validation and auditing; risk strategy developers; and credit risk executives Course Contents - Introduction to Credit Risk Management - Scorecard Development Roles - Scorecard Development Stage 1: Preliminaries and Planning - Scorecard Development Stage 2: Data Review and Project Parameters - Scorecard Development Stage 3: Development Database Creating - Scorecard Development Stage 4: Model Development - Scorecard Development Stage 5: Scorcard Management Reports - Scorecard Development Stage 6: Scorecard - Post- 5 Duration 2 Days

7 Banking CRM Analytics s Applied Customer Segmentation Course Overview Banking CRM Analytics - Applied Customer Segmentation - Design of Experiments for Direct Marketing Emphasizing practical skills as well as providing theoretical knowledge, this hands-on course covers segmentation analysis in the context of business data mining. Topics include the theory of segmentation, as well as four main analytic tools for segmentation: hierarchical clustering, K-means clustering, RFM cell method, and SOM/Kohonen method. Learn How To - Understand and apply both attitudinal and behavioral segmentation tools and techniques on customer data - Profile and validate segments - Evaluate stability of segments over time Prerequisits Cognitro Banking Analytics s Banking Risk Analytics - Credit Risk Modelling for Basel II - Credit Scorecard Development and Data Mining knowledge is helpful but not necessary. Target Audience Anyone who wants to learn how to find meaningful segments in their customer data, focusing on practical business solutions rather than statistical rigor; business analysts, managers, marketers, programmers, and others can benefit from this course Course Contents - Segmentation Basics - Hierarchical Clustering for Segmentation - Applications of Hierarchical Clustering - k-means Clustering - A Priori Segmentation Using RFM Cells - Product Affinity Clusters - Decision Trees - Variables Selection, SOM/Kohonen, and Take-aways 6 Duration 2 Days

8 Banking CRM Analytics s Design of Experiments for Direct Marketing Course Overview Banking CRM Analytics - Applied Customer Segmentation - Design of Experiments for Direct Marketing This course teaches you how to design marketing experiments with more than one factor and how to maximize the information that is gleaned from a marketing campaign. Learn How To - Determine the appropriate sample size for your tests - Build efficient experimental designs that generate as much information as possible for minimum cost - Identify challenges associated with analyzing experimental designs - Test as many factors as possible in a given campaign - Apply well-known experimental design practices to direct marketing efforts Prerequisits Cognitro Banking Analytics s Data Mining knowledge is helpful but not necessary. Target Audience Business analysts and market researchers Banking Risk Analytics - Credit Risk Modelling for Basel II - Credit Scorecard Development and Course Contents - Introduction to Direct Marketing - Testing with Two or More Factors - Improving Design Efficiency - Too Many Treatments Duration 3 Days 7

9 s Data Mining Techniques: Theory Course Overview Banking CRM Analytics - Applied Customer Segmentation - Design of Experiments for Direct Marketing In this course explore the inner workings of data mining techniques and how to make them work for you. Students are taken through all the steps of a data mining project, beginning with problem definition and data selection, and continuing through data exploration, data transformation, sampling, portioning, modeling, and assessment Learn How To - Use a data mining methodology (e.g., CRISP-DM or SEMMA). - Build, interpret and score several types of predictive models (e.g., regression, trees, SVM, neural nets). - Use survival analysis and create survival curves or create anomaly / fraud detection models Prerequisits No prior knowledge of statistical or data mining tools is required. Cognitro Banking Analytics s Target Audience Business analysts, their managers, and statisticians Course Contents Banking Risk Analytics - Credit Risk Modelling for Basel II - Credit Scorecard Development and - Introduction to Data Mining - Data Mining Methodology - Data Exploration - Statistics and Regression - Predictive modeling algorithms: Decision Trees, Neural Networks, Support Vector Machines (SVM) - Clustering - Survival Analysis - Miscellaneous Techniques - Putting Data Mining Techniques to Work Duration 3 Days 8

10 About Cognitro BAT Courses Cognitro Training program is designed to explain the art and science of analytics in finance and banking in simple and easy language. The main goal is to enable average bank analysts and professionals to understand analytics terminology, capabilities, limitations, risks, rewards, and best practices to reap its full benefits and obtain the maximum return on investment. All courses contain a balance mixture of theory and practice with interactive breakout sessions. The courses provide methodological and practical coverage of Analytics, offering a comprehensive look into best practices and underlying its value to banks performance and profitability. About Cognitro Analytics Speakers Our seasoned instructors are PhD researchers and developers of data mining and predictive analytics algorithms with years of deep involvement in innovative research and development of real-world data mining solutions.the speakers, which include scientists, professionals, and analysts from Cognitro Analytics, have been working in the trenches and leading data mining engagements at top US banks. They make the course material real using examples and case studies from these banks. Attendants will be exposed to the most popular data mining techniques and software tools and will engage in a hands-on demonstration. Contact Us... About Cognitro Analytics Cognitro Analytics is a US-based company specialized in providing advanced business analytics solutions and data mining services. We help clients, reduce risk, optimize marketing, uncover fraud and retain customers, by maximizing the value of data to make more insightful and informed business decisions. For further information, please contact your Cognitro Analytics representative or call/ Phone: training@cognitro.com 9 Web: