Moving from the Use of Analytics to B i Being Analytics Driven A l - PowerPoint PPT Presentation

Moving from the Use of Analytics to B i Being Analytics Driven A l i D i 2012 CAS RPM Seminar Philadelphia, PA M March 19 ‐ 21, 2012 h 19 21 2012 Robert J. Walling, III, FCAS, MAAA Pinnacle Actuarial Resources, Inc. , Experience the Pinnacle Difference! 1

Analytics Driven  Analytics has been used in several areas of insurance companies  Use of analytics has had a significant impact y g p on insurance companies  As analytics mature, successful companies will As analytics mature, successful companies will move from the use of analytics to being analytics driven in an incremental process analytics driven in an incremental process 2

Uses of Analytics Uses of Analytics 3

Pricing  Rating enhancements  Class refinement  Vehicle classification  Territory definition d f  Custom insurance scores and scorecards  Tiering plans  Expanded use of customer related data  Usage based insurance (commercial auto) 4

Underwriting Analyses y Data  Straight through processing  Historical underwriting actions  Selection/rejection  Underwriting criteria  Target report ordering  Credit reports/scores (MVR, CL CLUE)  MVR report data  Action indicators  Action indicators  CL CLUE report data  Audit rules  Loss control inspection reports  Loss control/prevention  Other external data feeds  Other external data feeds  Property characteristics  Demographic  Demographic 5

Marketing Analysis Analyses Data  Model the likelihood of a  Internal company information potential risk contacting company  Agency characteristics for a quote (“shopping”)   External demographic External demographic  Measure characteristics of information shoppers/quoters   ZIP code level Measure likelihood of insureds responding to marketing responding to marketing  Business/Building level i / ildi l l initiatives demographics  Measure the likelihood of a risk  Credit profiles responding to a cross ‐ sell contact espo d g to a c oss se co tact  Marketing efforts  Measure advertising  Focus groups effectiveness   Agency management g y g Internet/social media data / Goal: Determine which potential customers to target, how to effectively target them 6

Customer Response Analyses Ongoing Customer Quote Sale Retention Servicing Service  Quoting analysis: analysis of the likelihood of a prospective insured obtaining an insurance quote from you insured obtaining an insurance quote from you  Conversion analysis: analysis of the likelihood of a insured that has received a quote purchasing insurance from you  Retention analysis: analysis of the likelihood of a current l l f h l k l h d f insured renewing with you  Cross sell analysis: analysis of the likelihood of a current y y insured purchasing additional products with you 7

Claims Adjustment/ Occurrence Report Settlement Development •Occurrence Characteristics •Est. claim settlement value •Claim development •Likelihood of reopen •Claim fraud •Claim assignment •Claim service providers •Salvage/subrogation •Early warning indicator •Claim adjustment procedures •Customer satisfaction •Estimated cycle time •Fraud •Claim process rules •Claim procedures •Attorney Involvement •Reporting Lag •Contact Lag •Settlement Lag Data Geography (State or Regional Courts)  Time (Inflation, Settlement Lags) ( , g )  Claimant Characteristics (Age, Class)  Insured Characteristics (Vehicle Weight)  Attorney Involvement  Preferred Claim Network (Medical, Glass, Auto Repair, Attorney)  Other Claims Features (Arbitration/ADR, Settlement Lag)  8

Results Monitoring/Dashboards  How are our agents reacting to our decisions?  How is the market reacting to our decisions?  How is our book of business performing?  Are there discernable trends emerging?  Decision makers need:  Access to the right data  Access to the right data  In an understandable format  Agreement on the relative importance of the g p various metrics being monitored 9

Analytics Dashboards

Enterprise Risk Management  Companies that use analytics extensively need t to recognize the model risk inherent in their i th d l i k i h t i th i business model  The analytics and monitoring processes Th l ti d it i themselves can be a tremendous source of information for ERM development and information for ERM development and documentation  Coordination between the data used for  Coordination between the data used for analytics, monitoring and ERM creates a cohesive data platform cohesive data platform 11

Data

Benefits of Analytics  Present a truer representation of business realities using data and information liti i d t d i f ti  Smarter decisions  Identify profitable long term customers  Continually improve business fundamentals  Claims, audit  Competitive advantage  Improved financial results  Profitable growth 13

Tangible Results  Benefits  Increased production d d  Improved loss experience  Improved customer insight  Improved customer insight  Knowledge transfer  Dependent on: Dependent on:  Scope/penetration  Implementation plan p p  Buy ‐ In  Corporate culture 14

The Transition: Analytics Driven The Transition: Analytics Driven 15

Analytics Driven  Intentional  Begin with the end in mind Begin with the end in mind  Data collection, data processing, analytics, and implementation all reflect purpose  Complete  Across all departments in an insurance company  Translation of analytics to application Translation of analytics to application  Allow data to define analytics as well  Consistent/Cohesive Consistent/Cohesive  Analytics should be moving company in the same direction  Analytics by different areas should be coordinated Analytics by different areas should be coordinated 16

Analytics Driven Companies… 1. Process data intentionally 17

Process Data Intentionally  Data historically collected for a number of different purposes – not analytics  Creates challenges g  Missing information  Incorrect data  Intentional data processing  Identify the right data  Identify the right data  Collect and store data consistently and accurately  Prepare data once for multiple applications Prepare data once for multiple applications 18

Analytics Driven Companies… 1. Process data intentionally 2. Spend time investigating data 19

Spend Time Investigating Data Typical Analytics Process Identify Retrieve business and process Analytics problem problem data data Let the Data Lead You Retrieve Identify Data Further and process business analytics analytics data problem 20

Example of Association Analysis – Businessowners Policy Endorsements 21

Analytics Driven Companies… 1. Process data intentionally 2. Spend time investigating data 3. Apply multiple analytics techniques 3. Apply multiple analytics techniques 22

Apply Multiple Analytics Techniques Data Exploration Predictive Models  Clustering/segmentation  Clustering/segmentation  Decision trees  Decision trees analysis  Neural networks  Principal components  Clustering g  Association analysis  Principal components  Self ‐ organizing maps  Association analysis  Variable clustering  Rule induction  Variable selection Considerations Considerations  Purpose  Application Application  Technical considerations 23

Decision Tree – Rules Engines 24

Analytics Driven Companies… 1. Process data intentionally 2. Spend time investigating data 3. Apply multiple analytics techniques 3. Apply multiple analytics techniques 4. Apply analytics to all insurance functions 25

Apply Analytics to All Insurance Functions Customer Marketing Retention Service Service Sale Claims Pricing Cross Re‐ Quote Underwriting Sell Sell underwriting 26

All Insurance Functions?  Customer service  Agency placement/evaluation  Social media Social media  Human resources  Location based services L ti b d i 27

Analytics Driven Companies… 1. Process data intentionally 2. Spend time investigating data 3. Apply multiple analytics techniques 3. Apply multiple analytics techniques 4. Apply analytics to all insurance functions 5 E 5. Ensure analytics consistency across l ti i t organization 28

Ensure Analytics Consistency Customer Marketing Retention Service Service Sale Claims Pricing Cross Re‐ Quote Underwriting Sell Sell underwriting 29

Ensure Analytics Consistency  Board level analytics commitment  C ‐ level analytics responsibility  Consistency of analytics knowledge Consistency of analytics knowledge  Analytics research center  Internal analytics user group  Internal analytics user group  Consistent data  Consistent metrics Consistent metrics  Sharing of analytics projects  No silos 30

Analytics Driven Companies… 1. Process data intentionally 2. Spend time investigating data 3. Apply multiple analytics techniques 3. Apply multiple analytics techniques 4. Apply analytics to all insurance functions 5 E 5. Ensure analytics consistency across l ti i t organization 6. Design studies 31