Big Data, Voice Analytics and Unstructured Data Help Tackle the Compliance Conundrum

38 %
62 %
Information about Big Data, Voice Analytics and Unstructured Data Help Tackle the...
Business & Mgmt

Published on February 4, 2014

Author: DeloitteAnalytics


Big Data, Voice Analytics and Unstructured Data Help Tackle the Compliance Conundrum Omer Sohail Lloyd Wirshba Deloitte Consulting LLP October 17, 2013

The CFPB is a data driven regulator whose rulemaking authority influences the entire consumer finance spectrum Source (L to R), accessed September 12-17, 2013, web articles

The CFPB Complaint Database provides perspective on industry trends and issues CFPB Complaint Database by Product 4528, 3% 20278, 15% • Contains over 130,000 complaints across seven products, where the date of first data collection varies by product 3769, 3% 24850, 18% 72436, 53% • Mortgage complaints represent both the majority and an increasing trend: 53% overall, from 48% in March 2012 to 63% in March 2013 10012, 8% 192, 0% Bank account or service (March 2012) • The timely response rate is 97.6% (acknowledgement within 15 days) Consumer loan (March 2012) Credit card (November 2011) Credit reporting (October 2012) Money transfers (April 2013) Mortgage (December 2011) Student loan (March 2012) Source: CFPB complaint database, accessed August 28, 2013 • Consumers disputed 21.2% of proposed resolutions, while 12.6% are still awaiting response

Finding complaint root causes requires identifying predictive indicators within other data sources Mortgage Complaint Issues over Time 6000 Complaints 5000 4000 3000 2000 1000 2011 / 12 2012 / 1 2012 / 2 2012 / 3 2012 / 4 2012 / 5 2012 / 6 2012 / 7 2012 / 8 2012 / 9 2012 / 10 2012 / 11 2012 / 12 2013 / 1 2013 / 2 2013 / 3 2013 / 4 2013 / 5 2013 / 6 2013 / 7 0 Loan modification,collection,foreclosure • Nearly 85% of mortgage complaints relate to loan mods and servicing • During origination, consumers find another lender instead of complaining • Consumer awareness is increasing • The mortgage servicing arm of a large bank sought to identify the root cause of an increase in mortgage complaints • Each complainant that could be connected to internal records contacted the bank at least three times prior to the CFPB complaint Loan servicing, payments, escrow account Application, originator, mortgage broker Settlement process and costs Other Credit decision / underwriting Source: CFPB complaint database, accessed August 28, 2013 The CFPB database has no predictive indicators, so it must be joined with other sources to analyze and respond to CFPB complaints

The CFPB taxonomy provides more issue types for credit card complaints Credit Card Complaint Issues Product Num. Issues Bank Account/Service Consumer Loan 16% 10% 48% 7% 7% 6% 6% Billing disputes APR or interest rate Credit reporting Identity theft / Fraud / Embezzlement Closing/Cancelling account Other Named other issues (27 categories) Source: CFPB complaint database, accessed March 31, 2013 Nilson Report, February 2012 (outstandings at end of 2011) 5 7 Credit Reporting 5 Money Transfers 6 Student Loan 3 • The top five of 33 issues constitute 46% of the 24,850 credit card complaints • Integrate data from complaint handling, process improvement initiatives and product offerings to train a system that suggests a bankspecific root cause

Providing relief is not a primary tactic to reduce consumer disputes Complaint Resolution Statistics 35% 30% • Despite resolutions in favor of the consumer decreasing, consumer disputes also decreased (Originally the CFPB only had one category of relief. In May 2012, the options were expanded to monetary and non-monetary relief) 25% 20% 15% 10% 5% 2011 / 11 2011 / 12 2012 / 1 2012 / 2 2012 / 3 2012 / 4 2012 / 5 2012 / 6 2012 / 7 2012 / 8 2012 / 9 2012 / 10 2012 / 11 2012 / 12 2013 / 1 2013 / 2 2013 / 3 2013 / 4 2013 / 5 2013 / 6 2013 / 7 0% Disputes Responses in favor of consumer Source: CFPB complaint database, accessed August 28, 2013 • Better communication with customers may help firms manage consumer expectations and support process improvement

Providing relief has a different effect on dispute rates depending on the product Dispute Rate by Product and Response 30% • For consumer loans and mortgages, providing relief reduces the dispute rate by 7% 25% • For other products in the original database, providing relief reduces the dispute rate by 13% Dispute Rate 20% 15% 10% 5% 0% Consumer Mortgage Bank Credit card Student loan account or loan service Closed with relief Closed without relief Source: CFPB complaint database, accessed August 28, 2013 • To better allocate resources while reducing complaint volume, it is critical to understand the relationship between providing relief and customer satisfaction. Which opportunity is greater?

For bank account and service complaints, disputes are greatly reduced with fee refunds 26% • Nearly a quarter of bank account and service complaints resolved without relief were disputed 74% • Compared to providing non monetary relief, providing monetary relief reduces dispute rates from 18% to 9% Bank Account or Service Complaint Disputes 100% 90% 80% 12% 11% 11% 9% 21% 24% 10% 0% 14% 0% 18% 70% 60% 50% 40% 30% 20% 10% 0% 80% 66% 65% 86% 72% Pending Response Disputed Not Disputed • Does the refund amount relative to the fee(s) responsible for the complaint impact the dispute rate? Source: CFPB complaint database, accessed August 28, 2013 Pennsylvania PIRG CFPB Complaint Database analysis, accessed September 19, 2013

Complaints are more likely to originate from zip codes with older and more affluent residents Mortgage Complaints by Median Age 100% 1.17 80% D (>= 41) 1.05 60% C (37.5-40.9) 40% 1.00 B (33.5-37.4) 20% 0% 80% 60% 40% • Complainants in the database may not precisely represent the customer population at a financial institution • Banks should understand their exposure, especially which involves Mortgage Complaints by Median Income consumer segments that are important 1.43 to the CFPB: underbanked, lower H (>= $69,000) income, or other disadvantaged 1.08 G ($52,000-$68,999) populations Population 100% A (<33.5) 0.75 • Adjust for penetration, separating out each banking product Complaints F ($41,000-$51,999) 0.84 20% E (<$41,000) 0.62 0% Population Complaints Source: CFPB complaint database, accessed August 28, 2013 Values > 1 indicate a larger share of complaints from that age/income group than is represented in the population

Deriving value from complaint data analysis

Components of an enterprise-wide complaint analytics capability With structured data, collect unstructured and external data Perform historical reporting and advanced data analytics Integrate with a cross-functional complaint management program Data aggregation and cleansing Call Transcripts and Agent Notes Email Create relevant variables Data and Analytics Governance and Controls Escalation Process Employee Training Develop predictive models Refine modeling outcomes Social Media Focus Groups Online Chat News Develop reason codes and business rules Building and deploying leading analytics requires a combination of domain, data management, data intuition, statistics and technology skills Regulatory Reporting Independent Compliance Audit

Complaint analytics drive value across all bank functions Enhance investment to improve satisfaction Improve Customer Service Identify and mitigate high risk complaints Operations Consumers Improve customer outcomes (e.g. loyalty, spend) Complaint Analytics Compliance Marketing Proactive approach to regulators Refine channel marketing strategy Product Design Proactive monitoring of customer reactions

A complaint analytics system includes multiple use cases for each function

Complaint Analytics Applications 1 Text analytics to understand the voice of customer 2 Voice analytics to address complaint escalation 3 External lifestyle data to support complaint handling 4 Consumer treatments post fraud, disputes, complaints

1 Text analytics can be used to understand the voice of the customer Collect structured and unstructured data streams across products and channels Call Transcripts and Agent Notes Email Social Media Online Chat Focus Groups News Classify Text to Quantify Known Issues Integrate with Dashboards • Hypothesis Testing Cluster Documents to Identify Emerging Issues • Emerging Trends/Surges Analyze Sentiment and Top Keywords to Improve Predictive Models • Product Monitoring

1 Text analytics reveals origination experience drivers for wealth management customers The top factors driving satisfaction and likelihood to recommend depend on competent bank staff Source: Deloitte survey and analysis A difficult process with poor communication leads to dissatisfaction. The bank in blue should focus on process

2 Near real time voice analytics enables integration with predictive modeling and reporting Outbound or Transfer Call Center Customer Call Record Calls Voice Analytics (phonemes, text) Queue CSR Customer IVR and Switch Logs CRM Contact Center Sample metrics • Wait time • Transfer rate • First contact resolution • Abandon rate • Escalation rate Customer Warehouse Sequence Based Predictive Model Demographic, Lifestyle Data Prediction Score Customer Operations Accelerators

2 Voice analytics can provide data for predictive models that prevent complaint escalation Model Repeat Callers Root cause and metric driven Approach analysis to reduce callbacks Escalated Complaints Post Complaint Churn Near real time propensity model gives agents feedback Sequence analysis identifies churn and reduced spending factors Join internal data with CFPB database to preempt escalation • Real time retention offer generation • Decisions based on customer lifetime value forecasts • Reperform tests in CFPB examination manual • Integrate with complaint responses • Cross channel • Agent desktop context for integration Implement agents • Specialist call • Volume forecast center agents and IVR changes • Outbound call • Test and learn center CFPB Escalation

3 External lifestyle data can enhance the power of predictive analytics Data Categories Data Vendors Wage Data Wealth Indicators Unemployment Stats EEOC Complaints DB Ec. Freedom Index Aggregated IRS Data Occupational Codes Real Property Data Affluent Homeowners Home Equity Borrower Govt. Housing Survey Home Value Scoring Foreclosure Data Purchase Behaviors Purchase Propensities Spend by Category DTC Spend by Retailer Brand Usage Statistics Retailer Trans Data Purchase Triggers Disability Data US Hospital Directory Nursing Home Data Medical Provider Data Hosptial Visit Statistics Doctor Practice Data Health Interest Data Auto Data Carfax Vehicle History Motor Vehicle Reports Auto Injury / Loss Data Driver Device Usage Road Rage Survey VIN Decoding Data Lifestyle and Life Traits Working Mothers Active Seniors High-Tech Segments Life Stage Clustering Demo. Census Data Crime Statistics Hail Vector Data Storm Events DB Climate Data Geographic Mapping College Rankings Firehouse Data Fire Incident Data Judicial Hellholes Fed. Case Law DB Florida Tax Records Lit. Trends Survey Lawsuit Climate Data DUI/DWI Laws CA/FL Lawyer Data Tort Liability Index Bus. Hazard Grade Bus.Insurance Scores Bus.Financial Statistics UCC Filings Small Bus. Data Bus. Credit Score OSHA Bus. Data Tax Liens & Bankruptcy Acxiom AM Best AMA American Housing Survey American Tort Reform Foundation Burueau of Labor Statistics Cap Index Carfax CDS Hail Database Census Point Choicepoint Corporate Research Board DataLister Directory of US Hospitals Dun & Bradstreet EASI Analytics EEOC Equifax ESRI Experian Fastcase Legal Research System Florida Tax Assessment Records Fulbright Lititgation Trends Survey Insurance Information Institute Insurance Institue for Highway Safety Internal Renvue Service Knowlege Based Marketing (KBM) Lawyer Data – Florida & California LexisNexis Martindale/Hubble Attorney Listing MRI Purchasing Propensities NFIRS – National Fire Reporting NHTSA OSHA US Census

3 Augmenting outcomes monitoring with external data can improve complaint handling policy Integrating analytics with operations • Proactive pre-complaint issue handling. Some segments tend to have certain complaint issues. • Perform segment based complaint resolution subject to fair treatment • Develop a communication approach to reduce complaints and disputes Example: customer A expressed interest in a simple resolution process without a notarized form. Subject to fraud loss risk guidelines, if Customer B is has similar lifestyle attributes to Customer A, omitting the notarized form can help build trust Source: Building Consumer Trust in Retail Payments, available at

4 Predicting how customers react after fraud handling is key to reducing complaints and churn Collect Data • Customer data • Demographics • Product relationships • Profitability • Contact event data • Potentially fraudulent transactions • Consumer trust indices and survey data derived from an existing Deloitte study • Deloitte administered focus group (for updated data) Build Analytics • • • Identify indicators that explain consumer behavior following a fraud incident Develop a propensity model that predicts customer churn, reduced spending, or inactive accounts • Who is likely to churn? • What are the risk factors? Analyze free form survey and focus group data to identify trends in unmet customer needs. For example • Ensured I didn’t lose money • Stopped transactions quickly • Limited paper forms • Went beyond minimum legal requirements Integrate with Operations • Convert model results to reason codes that correspond to process changes • Provide service reps and complaint investigators with relevant context from previous interactions • Expedite a fraud investigation • Issue a credit for the transaction(s) under investigation • Retention offer as appropriate • Make recommendations about the fraud handling policy based on predicted customer profitability and behaviors

Summary • The CFPB Complaint Database provides a starting point consumer complaint analysis, but it can provide greater insights when properly integrated with internal process and complaint data • Big data technologies are a key component of an enterprise-wide complaint analytics and response capability • Text analytics can be applied to identify emerging issues and focus areas for improving customer satisfaction • Using voice analytics to support predictive modeling represents an emerging area that can provide substantial incremental benefits to complaint analytics • External data sources can augment a predictive model or provide context for customer interactions following complaints

Copyright © 2013 Deloitte Development LLC. All rights reserved. As used in this document, "Deloitte" means Deloitte Consulting LLP, a subsidiary of Deloitte LLP. Please see for a detailed description of the legal structure of Deloitte LLP and its subsidiaries. Certain services may not be available to attest clients under the rules and regulations of public accounting. This publication contains general information only and Deloitte is not, by means of this publication, rendering accounting, business, financial, investment, legal, tax, or other professional advice or services. This publication is not a substitute for such professional advice or services, nor should it be used as a basis for any decision or action that may affect your business. Before making any decision or taking any action that may affect your business, you should consult a qualified professional advisor. Deloitte shall not be responsible for any loss sustained by any person who relies on this publication.

Add a comment

Related presentations

Canvas Prints at Affordable Prices make you smile.Visit http://www.shopcanvasprint...

30 Días en Bici en Gijón organiza un recorrido por los comercios históricos de la ...

Con el fin de conocer mejor el rol que juega internet en el proceso de compra en E...

With three established projects across the country and seven more in the pipeline,...

Retailing is not a rocket science, neither it's walk-in-the-park. In this presenta...

What is research??

What is research??

April 2, 2014

Explanatory definitions of research in depth...

Related pages

Big Data, Voice Analytics, and Unstructured Data Helps the ...

Read more

What is Big Data Analytics? Webopedia Definition

Big data analytics can help organizations to better understand the information contained within the ... (both structured and unstructured data) ... Big ...
Read more

Unstructured data - Wikipedia, the free encyclopedia

Unstructured data (or unstructured information) ... and text analytics provide different methods to find patterns in, ... Unstructured, Big Data.
Read more

What Is Big Data? | SAS - Analytics, Business Intelligence ...

Big data’s big potential. The amount ... With the help of big data analytics, ... risk and fraud while maintaining regulatory compliance. Big data brings ...
Read more

Voice Analytics | LinkedIn

View 505 Voice Analytics posts, presentations, experts, and more. Get the professional knowledge you need on LinkedIn.
Read more

Credit & Risk Management | Banking Analytics Symposium

Big Data, Voice Analytics, and Unstructured Data Helps the Tackle the Compliance Conundrum. ... customer demographics and product data can help: ...
Read more

Omer Sohail | LinkedIn

Omer Sohail; Banking on Big Data and Analytics ... VOICE ANALYTICS, AND UNSTRUCTURED DATA HELPS THE ... center data streams to improve compliance and ...
Read more

IBM Power Systems | big data and analytics

IBM Power Systems. Analytics and big data inform business ... simplify and accelerate unstructured big data analytics. ... Help ensure every decision ...
Read more