Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
SlideShare a Scribd company logo

OFSAA - BIGDATA - IBANK

•Download as PPTX, PDF•
•
I
ibankuk

This document discusses using big data and analytics within Oracle's Financial Services Analytical Applications (OFSAA) platform. It provides examples of using additional unstructured data sources like news feeds, research reports, and social media to improve analytics for detecting fraud, predicting customer attrition, and more accurately estimating default correlation and pricing securitized bonds. The document outlines how OFSAA currently uses only structured data but could be enhanced by incorporating big data sources to power more predictive models.

1 of 21
Copyright © 2013, Oracle and/or its affiliates. All rights reserved.1
Financial Services Global Business Unit Analytics and Big Data Ambreesh Khanna VP, OFSAA Product Management FSGBU
Copyright © 2013, Oracle and/or its affiliates. All rights reserved.3 Program Agenda  Big Data – what does it have to do with OFSAA?  Customer Analytics  Fraud  Default Correlation for Securitized Bond Prices
Copyright © 2013, Oracle and/or its affiliates. All rights reserved.4 Oracle Financial Services Analytical Applications Performance Management & Finance Model Risk V2 061912 Performance Management Customer Insight Governance & Compliance Risk Management Hedge Management IFRS 9 – IAS 32/39 ICAAP/Risk Appetite Customer Profitability Stress Testing Loan Loss Forecasting Pricing Management Risk Adjusted Performance Know Your Customer Risk Management Operational Risk & Compliance Mgt.Regulatory Compliance (Financial Crime) Customer Insight Anti-Money Laundering Trading ComplianceBroker Compliance Fraud Detection Operational Risk Credit Risk Institutional Performance Retail Performance Marketing Customer Segmentation Capital Management Liquidity Risk Economic Capital Advanced (Credit Risk) Operational Risk Economic Capital Balance Sheet Planning Profitability Asset Liability Management Market Risk Basel Regulatory Capital Retail Portfolio Models and Pooling Funds Transfer Pricing Reconciliation Channel Insight Compliance Risk Business Continuity Risk Counterparty Risk Audit FSDF
Copyright © 2013, Oracle and/or its affiliates. All rights reserved.5  Relationship Pricing  NBO  Reputational Risk  Fraud, AML, TC/BC  Valuations for Credit Risk  Payments Analytics  Unified Data Model OFSAA and Big Data Use cases
Copyright © 2013, Oracle and/or its affiliates. All rights reserved.6 OFSAA – Current Architecture
Copyright © 2013, Oracle and/or its affiliates. All rights reserved.7 OFSAA High Level Architecture
Copyright © 2013, Oracle and/or its affiliates. All rights reserved.8 Use Case – Customer Attrition Customer Id: 12345 Name: Jane Doe Marital Status: Single Owns house: N No. of children: 0 CASA account Bi-weekly Direct deposit Avg. Balance: $10K Gold card Limit: $10K Balance: $7K 1 Event • Customer gets married 2 Event • Customer has a baby • Opens 529K with competing bank Event • Customer buys a house • Gets mortgage from competing bank 3 4 Event • Customer consolidates accounts • Moves all accounts to competing bank 5
Copyright © 2013, Oracle and/or its affiliates. All rights reserved.9 Use Case – Customer Retained with Better Insights Customer Id: 12345 Name: Jane Doe Marital Status: Single Owns house: N No. of children: 0 CASA account Bi-weekly Direct deposit Avg. Balance: $10K Gold card Limit: $10K Balance: $7K 1Event • Customer socially announces intent to get married 2 Event • Customer announces pregnancy and eventually birth of child 6 Event • Customer searches for mortgage on bank website 4 1. Bank updates customer record 2. Runs propensity models for NBO and makes time-bound loan offer for $50K for wedding at next point of customer interaction 3 1. Bank preapproves customer for mortgage 2. Makes offer at next point of customer interaction due to high propensity score 5 1. Bank analyzes purchase pattern and predicts change in status; Augments score with data from social networks 2. Makes 529K offer at next point of customer interaction as per propensity score 7
Copyright © 2013, Oracle and/or its affiliates. All rights reserved.10 Customer Attrition Functional Flow Weblogs, emails, call records CoreBanking,CRM User or segment matched
Copyright © 2013, Oracle and/or its affiliates. All rights reserved.11 Use Case – Trader and Broker Compliance, Internal Fraud 1 TC/BC/Fraud software monitors patterns of trading activity 2 Additional data points to be provided to TC/BC/Fraud software • Emails, SMSs, IMs, weblogs, social updates 3 Models to find co-relation between events such as large institutional trades and personal calls, or employee accessing a articular customer activity on a regular basis
Copyright © 2013, Oracle and/or its affiliates. All rights reserved.12 Use Case – Payments Fraud 1 Transaction persisted for detailed analytics 5 Real time fraud detection engine does rule matching and machine learning models try to enhance patterns 2 Additional data points • User, address, geo-location previously known? • Any known information from outside the bank about originator or destination? 4 Approval/Denial response Wire Transfer transaction through Bank • Enhanced user profiles and history kept on HDFS • Behavior detection models run on Map Reduce 3
Copyright © 2013, Oracle and/or its affiliates. All rights reserved.13 Use Case – Anti Money Laundering Monetary transactions 1 AML software monitors • Large cash transactions (CTR) • Patterns to identify money laundering (SARs) • KYC (checks against negative lists) 2 Additional data points to be provided to AML • External information about the customer 3 1. Graph analysis to detect patterns (vertices are entities, edges are transactions) 2. Co-relation between SARs 4 1. Graph analysis is extremely relevant to fraud detection 2. Extremely large graphs cannot be analyzed with traditional means – order of complexity is likely non- probabilistic in time and space 3. Some of these problems are hadoop-able
Copyright © 2013, Oracle and/or its affiliates. All rights reserved.14 SOAP C++Pipes Native Fraud Technical Architecture FSDF (DB 11.2.0.2+ with ORE) BDA (HDFS/ Cloudera ) Hive/NoSQL Discovery / adhoc Analytical Reporting Source Systems Trxns a Stochastic Modeling subsystem (with „R‟ support & ORE connectivity) Scenario Definitions (metadata) Post-Processing (pluggable services framework) Batch c b b b CI d“Sqoop” Batch process c HiveQL AAI d Behavior Detection Inline-Processing Engine OLTP Systems I I I I I I a I MSG queues OCI/JNDI-JDBC ODBC Endeca / OBIEE AAI AAI AAI R-connector for Hadoop ORE native connectivity Collective-Intellect HiveQL or EID *M/R – Map Reduce *M/R *M/R Endeca Information Discovery Web-services interfaces included (WSDL) move to structured store additional /enriched attributes Unstructured Data Blogs Newsfeeds Watch List Scans Financial / Marketing /Trade data providers/channels b I
Copyright © 2013, Oracle and/or its affiliates. All rights reserved.15 Using Big Data to Estimate Default Correlation Rating Agencies Players involved in securitization transactions and their roles Evaluate credit risk and deal structure, assess third parties, interact with investors, and issues ratings Asset Manager Financial Guarantor Servicer TrusteeOriginator Arranger Senior Mezzaine Junior Investors SPV Assets Liabilities Monitors complianceCollects & makes payments Pay outsFunds Funds Pay outs Pay outs Funds Trades assets Insures tranches Funds Pay outs Loans to Energy firms Loans to Agricultural firms Loans to Textile firms • Prices of Bonds (i.e. tranches) are very sensitive to default correlation of loans • We propose to use Big Data comprising of public and private information, Bloomberg and Reuters feeds, commercial transactions, analyst meets, and research reports to estimate default correlation Bonds with different ratings
Copyright © 2013, Oracle and/or its affiliates. All rights reserved.16 Estimating Default Correlation and Securitized Bond Prices – Current State Analytical Applications Infrastructure (Data Quality, Metadata, Stress Testing, Modeling, Execution, Big Data Connectors etc) Staging Area Common Input area for analytical processing Data Quality Checks, GL Reconciliations, Manual Data Adjustments Application-specific Processing Area Valuations Engine Stochastic Models to estimate default metrics Results Area Dashboards and Reports Bond and Tranche Prices, Attachment and Detachment Points, Regulatory Reserves Credit Risk Engine Market Risk Engine Default Metrics PD, LGD, EAD, Default Correlations Front Office Systems (like CRM, RTD etc) Core Banking Systems Treasury Systems Loans to Energy firms Loans to Agricultural firms Loans to Textile firms Basel Engine Company Specific Metrics • Demographic, Geographic and Industry information • Company Ratings • Risky Bond prices floated by firms • CDS spreads of the firms • Balance Sheet structure and information OBIEE • Currently the estimation of default metrics like PD, LGD and Default Correlation only considers structured information • Unstructured but rich information contained in Big Data sources like Bloomberg and Reuters feeds and news reports, Analyst comments and Research reports, News on commercial transactions etc. is completely ignored • This results in poor default metrics and hence very poor and inaccurate Securitized Bond Prices • Securitized Bond Prices are extremely sensitive to Default Correlation, and incorrect estimates of which was one of the main causes of 2008 market crash
Copyright © 2013, Oracle and/or its affiliates. All rights reserved.17 Estimating Default Correlation and Securitized Bond Prices – Future State Using Big Data Sources Analytical Applications Infrastructure (Data Quality, Metadata, Stress Testing, Modeling, Execution, Big Data Connectors etc) Staging Area Common Input area for analytical processing Data Quality Checks, GL Reconciliations, Manual Data Adjustments Application-specific Processing Area Valuations Engine Stochastic Models to estimate default metrics Results Area Dashboards and Reports Bond and Tranche Prices, Attachment and Detachment Points, Regulatory Reserves Credit Risk Engine Market Risk Engine Default Metrics PD, LGD, EAD, Default Correlations Front Office Systems (like CRM, RTD etc) Core Banking Systems Treasury Systems Loans to Energy firms Loans to Agricultural firms Loans to Textile firms Basel Engine Company Specific Metrics OBIEE Big Data Sources • Bloomberg & Reuters feeds and news • Analysts comments and Research reports • Commercial Transactions • Quarterly Investor meets, notes and public announcements • Augmenting traditional structured information with the new unstructured information from Big Data sources will result in better estimates of default correlation and PD, LGD, EAD • Better estimates of default will result in more accurate prices of Bonds offered to investors via Securitization of assets • Estimates of default can be updated quickly as new unstructured information becomes available
Copyright © 2013, Oracle and/or its affiliates. All rights reserved.18 OFSAA at OpenWorld  Monday, September 23 – 2:30-3:30 Making Sense of the Regulatory Challenges Facing Banks Today & Tomorrow  Tuesday, September 24 – 10:30-11:30 Driving Business Growth by Unlocking Rich Customer Insights – 5:15-6:15 Advanced Analytics for Insurance  Wednesday, September 25 – 10:15-11:45 Big Data in Financial Services – 4:15-5:15 Use-Case Driven Approach to Using OFS Data Foundation for Data Management Needs
Copyright © 2013, Oracle and/or its affiliates. All rights reserved.19 Graphic Section Divider
Copyright © 2013, Oracle and/or its affiliates. All rights reserved.20
Copyright © 2013, Oracle and/or its affiliates. All rights reserved.21

More Related Content

OFSAA - BIGDATA - IBANK

  • 1. Copyright © 2013, Oracle and/or its affiliates. All rights reserved.1
  • 2. Financial Services Global Business Unit Analytics and Big Data Ambreesh Khanna VP, OFSAA Product Management FSGBU
  • 3. Copyright © 2013, Oracle and/or its affiliates. All rights reserved.3 Program Agenda  Big Data – what does it have to do with OFSAA?  Customer Analytics  Fraud  Default Correlation for Securitized Bond Prices
  • 4. Copyright © 2013, Oracle and/or its affiliates. All rights reserved.4 Oracle Financial Services Analytical Applications Performance Management & Finance Model Risk V2 061912 Performance Management Customer Insight Governance & Compliance Risk Management Hedge Management IFRS 9 – IAS 32/39 ICAAP/Risk Appetite Customer Profitability Stress Testing Loan Loss Forecasting Pricing Management Risk Adjusted Performance Know Your Customer Risk Management Operational Risk & Compliance Mgt.Regulatory Compliance (Financial Crime) Customer Insight Anti-Money Laundering Trading ComplianceBroker Compliance Fraud Detection Operational Risk Credit Risk Institutional Performance Retail Performance Marketing Customer Segmentation Capital Management Liquidity Risk Economic Capital Advanced (Credit Risk) Operational Risk Economic Capital Balance Sheet Planning Profitability Asset Liability Management Market Risk Basel Regulatory Capital Retail Portfolio Models and Pooling Funds Transfer Pricing Reconciliation Channel Insight Compliance Risk Business Continuity Risk Counterparty Risk Audit FSDF
  • 5. Copyright © 2013, Oracle and/or its affiliates. All rights reserved.5  Relationship Pricing  NBO  Reputational Risk  Fraud, AML, TC/BC  Valuations for Credit Risk  Payments Analytics  Unified Data Model OFSAA and Big Data Use cases
  • 6. Copyright © 2013, Oracle and/or its affiliates. All rights reserved.6 OFSAA – Current Architecture
  • 7. Copyright © 2013, Oracle and/or its affiliates. All rights reserved.7 OFSAA High Level Architecture
  • 8. Copyright © 2013, Oracle and/or its affiliates. All rights reserved.8 Use Case – Customer Attrition Customer Id: 12345 Name: Jane Doe Marital Status: Single Owns house: N No. of children: 0 CASA account Bi-weekly Direct deposit Avg. Balance: $10K Gold card Limit: $10K Balance: $7K 1 Event • Customer gets married 2 Event • Customer has a baby • Opens 529K with competing bank Event • Customer buys a house • Gets mortgage from competing bank 3 4 Event • Customer consolidates accounts • Moves all accounts to competing bank 5
  • 9. Copyright © 2013, Oracle and/or its affiliates. All rights reserved.9 Use Case – Customer Retained with Better Insights Customer Id: 12345 Name: Jane Doe Marital Status: Single Owns house: N No. of children: 0 CASA account Bi-weekly Direct deposit Avg. Balance: $10K Gold card Limit: $10K Balance: $7K 1Event • Customer socially announces intent to get married 2 Event • Customer announces pregnancy and eventually birth of child 6 Event • Customer searches for mortgage on bank website 4 1. Bank updates customer record 2. Runs propensity models for NBO and makes time-bound loan offer for $50K for wedding at next point of customer interaction 3 1. Bank preapproves customer for mortgage 2. Makes offer at next point of customer interaction due to high propensity score 5 1. Bank analyzes purchase pattern and predicts change in status; Augments score with data from social networks 2. Makes 529K offer at next point of customer interaction as per propensity score 7
  • 10. Copyright © 2013, Oracle and/or its affiliates. All rights reserved.10 Customer Attrition Functional Flow Weblogs, emails, call records CoreBanking,CRM User or segment matched
  • 11. Copyright © 2013, Oracle and/or its affiliates. All rights reserved.11 Use Case – Trader and Broker Compliance, Internal Fraud 1 TC/BC/Fraud software monitors patterns of trading activity 2 Additional data points to be provided to TC/BC/Fraud software • Emails, SMSs, IMs, weblogs, social updates 3 Models to find co-relation between events such as large institutional trades and personal calls, or employee accessing a articular customer activity on a regular basis
  • 12. Copyright © 2013, Oracle and/or its affiliates. All rights reserved.12 Use Case – Payments Fraud 1 Transaction persisted for detailed analytics 5 Real time fraud detection engine does rule matching and machine learning models try to enhance patterns 2 Additional data points • User, address, geo-location previously known? • Any known information from outside the bank about originator or destination? 4 Approval/Denial response Wire Transfer transaction through Bank • Enhanced user profiles and history kept on HDFS • Behavior detection models run on Map Reduce 3
  • 13. Copyright © 2013, Oracle and/or its affiliates. All rights reserved.13 Use Case – Anti Money Laundering Monetary transactions 1 AML software monitors • Large cash transactions (CTR) • Patterns to identify money laundering (SARs) • KYC (checks against negative lists) 2 Additional data points to be provided to AML • External information about the customer 3 1. Graph analysis to detect patterns (vertices are entities, edges are transactions) 2. Co-relation between SARs 4 1. Graph analysis is extremely relevant to fraud detection 2. Extremely large graphs cannot be analyzed with traditional means – order of complexity is likely non- probabilistic in time and space 3. Some of these problems are hadoop-able
  • 14. Copyright © 2013, Oracle and/or its affiliates. All rights reserved.14 SOAP C++Pipes Native Fraud Technical Architecture FSDF (DB 11.2.0.2+ with ORE) BDA (HDFS/ Cloudera ) Hive/NoSQL Discovery / adhoc Analytical Reporting Source Systems Trxns a Stochastic Modeling subsystem (with „R‟ support & ORE connectivity) Scenario Definitions (metadata) Post-Processing (pluggable services framework) Batch c b b b CI d“Sqoop” Batch process c HiveQL AAI d Behavior Detection Inline-Processing Engine OLTP Systems I I I I I I a I MSG queues OCI/JNDI-JDBC ODBC Endeca / OBIEE AAI AAI AAI R-connector for Hadoop ORE native connectivity Collective-Intellect HiveQL or EID *M/R – Map Reduce *M/R *M/R Endeca Information Discovery Web-services interfaces included (WSDL) move to structured store additional /enriched attributes Unstructured Data Blogs Newsfeeds Watch List Scans Financial / Marketing /Trade data providers/channels b I
  • 15. Copyright © 2013, Oracle and/or its affiliates. All rights reserved.15 Using Big Data to Estimate Default Correlation Rating Agencies Players involved in securitization transactions and their roles Evaluate credit risk and deal structure, assess third parties, interact with investors, and issues ratings Asset Manager Financial Guarantor Servicer TrusteeOriginator Arranger Senior Mezzaine Junior Investors SPV Assets Liabilities Monitors complianceCollects & makes payments Pay outsFunds Funds Pay outs Pay outs Funds Trades assets Insures tranches Funds Pay outs Loans to Energy firms Loans to Agricultural firms Loans to Textile firms • Prices of Bonds (i.e. tranches) are very sensitive to default correlation of loans • We propose to use Big Data comprising of public and private information, Bloomberg and Reuters feeds, commercial transactions, analyst meets, and research reports to estimate default correlation Bonds with different ratings
  • 16. Copyright © 2013, Oracle and/or its affiliates. All rights reserved.16 Estimating Default Correlation and Securitized Bond Prices – Current State Analytical Applications Infrastructure (Data Quality, Metadata, Stress Testing, Modeling, Execution, Big Data Connectors etc) Staging Area Common Input area for analytical processing Data Quality Checks, GL Reconciliations, Manual Data Adjustments Application-specific Processing Area Valuations Engine Stochastic Models to estimate default metrics Results Area Dashboards and Reports Bond and Tranche Prices, Attachment and Detachment Points, Regulatory Reserves Credit Risk Engine Market Risk Engine Default Metrics PD, LGD, EAD, Default Correlations Front Office Systems (like CRM, RTD etc) Core Banking Systems Treasury Systems Loans to Energy firms Loans to Agricultural firms Loans to Textile firms Basel Engine Company Specific Metrics • Demographic, Geographic and Industry information • Company Ratings • Risky Bond prices floated by firms • CDS spreads of the firms • Balance Sheet structure and information OBIEE • Currently the estimation of default metrics like PD, LGD and Default Correlation only considers structured information • Unstructured but rich information contained in Big Data sources like Bloomberg and Reuters feeds and news reports, Analyst comments and Research reports, News on commercial transactions etc. is completely ignored • This results in poor default metrics and hence very poor and inaccurate Securitized Bond Prices • Securitized Bond Prices are extremely sensitive to Default Correlation, and incorrect estimates of which was one of the main causes of 2008 market crash
  • 17. Copyright © 2013, Oracle and/or its affiliates. All rights reserved.17 Estimating Default Correlation and Securitized Bond Prices – Future State Using Big Data Sources Analytical Applications Infrastructure (Data Quality, Metadata, Stress Testing, Modeling, Execution, Big Data Connectors etc) Staging Area Common Input area for analytical processing Data Quality Checks, GL Reconciliations, Manual Data Adjustments Application-specific Processing Area Valuations Engine Stochastic Models to estimate default metrics Results Area Dashboards and Reports Bond and Tranche Prices, Attachment and Detachment Points, Regulatory Reserves Credit Risk Engine Market Risk Engine Default Metrics PD, LGD, EAD, Default Correlations Front Office Systems (like CRM, RTD etc) Core Banking Systems Treasury Systems Loans to Energy firms Loans to Agricultural firms Loans to Textile firms Basel Engine Company Specific Metrics OBIEE Big Data Sources • Bloomberg & Reuters feeds and news • Analysts comments and Research reports • Commercial Transactions • Quarterly Investor meets, notes and public announcements • Augmenting traditional structured information with the new unstructured information from Big Data sources will result in better estimates of default correlation and PD, LGD, EAD • Better estimates of default will result in more accurate prices of Bonds offered to investors via Securitization of assets • Estimates of default can be updated quickly as new unstructured information becomes available
  • 18. Copyright © 2013, Oracle and/or its affiliates. All rights reserved.18 OFSAA at OpenWorld  Monday, September 23 – 2:30-3:30 Making Sense of the Regulatory Challenges Facing Banks Today & Tomorrow  Tuesday, September 24 – 10:30-11:30 Driving Business Growth by Unlocking Rich Customer Insights – 5:15-6:15 Advanced Analytics for Insurance  Wednesday, September 25 – 10:15-11:45 Big Data in Financial Services – 4:15-5:15 Use-Case Driven Approach to Using OFS Data Foundation for Data Management Needs
  • 19. Copyright © 2013, Oracle and/or its affiliates. All rights reserved.19 Graphic Section Divider
  • 20. Copyright © 2013, Oracle and/or its affiliates. All rights reserved.20
  • 21. Copyright © 2013, Oracle and/or its affiliates. All rights reserved.21