Predictive Modeling & Marketing. The views expressed by the presenter does not necessarily represent the views, positions, or opinions of ISO.

Transcription

1 Predictive Modeling & Marketing 1 The views expressed by the presenter does not necessarily represent the views, positions, or opinions of ISO. 1

2 Business Environment Why things are becoming so data driven. The Market Electronic connectivity is expected Touch point knowledge is anticipated Personalized service is assumed Ease of doing business is desired Low tolerance for not learning Each Company Define, attract, retain, and grow good customers Match offering to customer Improve customer facing processes Reduce expenses while building skills 2

3 Insurance Company System Dynamics Identify the processes and actions that drive profitability and highlight interactions. Profitability Claims Expense Cost of Revenue Underwriting Revenue Sales & Marketing Claim Rates Claim Severity Inflation Complexity Uncertainty Risks Regulations Competition Litigation Catastrophe Pricing Risk Selection Stock/Bond Market Investments Policy Holders Agents Incremental improvements to many areas will be needed. 3

4 The Grief Cycle roller-coaster ride as the person wriggles in their desperate efforts to avoid the change. 4

5 Private Passenger Auto: Top 25 Writers Market Share 85% 80% 75% 70% 65% 60% 66.3% 68.8% 74.2% 81.4% Substantial consolidation evident over the past 25 years, suggesting: M&As more successful Scale economies Barriers to entry exist Capital (esp. foreign capital) cannot enter easily 55% 50% Sources: A.M. Best, Morgan Stanley, Insurance Information Institute. 5

6 Indication of Increased Competition Number of Companies writing Personal Auto Insurance in the US 1/3 of companies gone in 12 years 6

7 Indication of Increased Competition 100% Consolidation of Auto Insurance Markets 90% Market Share 80% 70% Top Carrier Group Top 10 Top 25 Top 50 60% 50% Below 50 now has only 9% for remaining 280 groups 7

8 How Analytics Fuel Competition My Book of Business (Actual Cost per Policy) My Rate (Average) Total Revenue $600 $800 $1000 $600 $800 $1000 $600 $800 $1000 $800 $2400 $900 $1800 $1000 $1000 If your competitor has advanced analytics, your book and your profitability are vulnerable 8

9 Analytic Value Effort Framework Reporting = Having the data Timeliness and accuracy Reports and Tables Surfacing data with agility Descriptive Analyses = Seeing the data Scorecards / Measurements Profiles and Exceptions Segmentation Analytic Modeling = Knowing the data Understand Trends Evaluate Business Practices Choice Models and What ifs Predictive Analytics = Acting on the data Informed decision-making Actionable Information Engines 9

10 Customer Focus: Products across life stages $ over time Car insurance Family needs Mortgage Travel Student Expenditure Income Coverage At School Coverage Out of country Auto Insurance Life Home SVP Umbrella As income increases, the needs for insurance grow 10

11 Stackable Coverage can show wallet share of customers and point out opportunities for cross-sell and up-sell $1.3 million Personal Umbrella $1 million $300K $300K $100K $50K $250 $250 $250 Personal Auto Policy Homeowners 11

12 Optimization using Customer Life Cycle Management Best Practice use of CLTV is to incorporate it into all stages during a customer s lifecycle and longevity Prospect Responder Current Customers Target Market Responder Cross-sell Campaigns Upsell Campaigns New Customer Most Profitable Next Most Profitable NOT Profitable Former Voluntarily Left You Forced Churn Acquisition Campaigns Segmentation Risk Selection Pricing Yield Management Attrition Prediction Forced Cancellation Winback Campaigns 12

13 Case Study: Database Marketing Implementation Approach SERVICE DIFFERENTIATION BASED ON PORTFOLIO POSITION Most Profitable Retention Programs Cross-sell / Up-sell Next Most Profitable Loss Control Services Agency Contact Re-underwriting Cross-sell / Up-sell NOT Profitable Forced Churn (where legally appropriate) Price to Risk 13

14 14 Portfolio View for Underwriting Analysis

15 15 Grow Your Book in the Right Direction

16 16 A vast array of CRM applications demand a common glue -- Analytics

17 Sales Funnel Lead Universe of all Prospects Your Selected Prospects Cold Warm Hot Process Lead Gathering and Targeting Lead Qualification Opportunity Sales Pipeline Customer Analyze, learn, grow customer Selling, Contracting 17

18 General Advertising and Direct Mail A Simple Comparison Advertising Mass Competitive Attention Breadth Remember Impression Pay for Everyone Direct Marketing Targeted Selective Attention Depth Respond Decision Pay for Targets 18

19 Selection Factors 19 Consumer Lists Age Income Gender Marital Status Homeowner Dwelling Type (home or apartment) Mail order buying (by product type) Interests Presence of children Geographical Geospatially (zip, SCF, derived county, estimated state, carrier loss route) costs Business Lists SIC (Standard Industrial Classification) Employee Size Annual Sales/Revenue Title Any other information captured on subscription form (publications) Corporate linkage information # of years in business Geographical (zip, SCF, county, state) Credit information

20 Data Driven Campaign Management and Pricing Optimization Cross sell Retention & Loyality Credit Risk New Product New Services New Channels Targeted Marketing Data Driven Campaign management Reporting OLAP Data Market Analysis Mining Research Segmentation & Scoring Data Analysis Data Warehouse 20

21 ISO Risk Analyzer Personal Auto Framework Rating Plan ISO Risk Analyzer Input State Territory Environmental Risk Module: Weather, Street, Businesses, Traffic Density, Driving Patterns etc State Address Vehicle Age & Symbol Vehicle Risk Module: Weight, Engine Size, etc. VIN Class Limits & Deductibles Special Adjustments Refined Points Module Credit Module (optional) No Change No Change Policy Risk Module Interactions of all indicators Personal Identifiers Address, Drivers, Vehicles 21

22 ISO Risk Analyzer Personal Property Framework Old Rating Plan State Territory New By Peril Rating Plan Refined Home Risk Factor: Weather, Demographic, Distance to Businesses, ISO Stat Plan, BCEGS, mold, Location, AOI, etc. Construction, Protection, AOI Prior claims, Credit score Resident Risk Factor: Loss Histories, Gender, Age, Marital Status, Pets, Smoking, etc. Credit optional Total Policy Risk Interactions of all indicators 22

23 ZIP Code 94109: A Tour Fishermen s Wharf Robert Louis Stevenson declared "Nob Hill, the Hill of Palaces, must certainly be counted the best part of San Francisco." The Tenderloin: not quite Nob Hill Japantown 23

24 24 Small-Area Geography Overview

25 Newark NJ Area Combined Relativity West Caldwell Cedar Grove Passaic Ridgefield Park Wallington Little Ferry Palisade Livingston Verona West Orange Rutherford Montclair Nutley Lyndhurst Bloomfield Belleville North Arlington Secaucus Ridg Fai Gutten W Orange East Orange Kearny Union City Summit Millburn South Orange Maplewood Irvington Newark Harrison Jersey City Hoboken Springfield Union Hillside Westfield Plains Cranford Roselle Park Roselle Linden Elizabeth Bayonne Clark 25

26 26 Combining Risk Scores for Marketing

27 Competitive Advantage Carriers establish a base rate for each rating territory that represents the average expected loss cost. Loss $ Base Rate Risk 27

28 Competitive Advantage Loss $ Actual Costs Base Rate Carriers establish a base rate for each rating territory that represents the average expected loss cost. In reality there is a distribution of risk and expected loss costs, even within a territory. Risk 28

29 Competitive Advantage Loss $ Actual Costs Prescreen Score Base Rate Carriers establish a base rate for each rating territory that represents the average expected loss cost. In reality there is a distribution of risk and expected loss costs, even within a territory. Risk The Prescreen Score more closely follows the actual distribution of risk. 29

30 Competitive Advantage Loss $ Actual Costs Prescreen Score Base Rate Carriers establish a base rate for each rating territory that represents the average expected loss cost. In reality there is a distribution of risk and expected loss costs, even within a territory. Risk Users of Prescreen can let their competitors waste resources chasing these marginal accounts! The Prescreen Score more closely follows the actual distribution of risk. 30

31 Summary Portfolio Management is a key to future success Sophisticated risk-based pricing will be essential Marketers can use sophisticated models Underwriting processes should be a focal point It is not a competitive advantage if you don t use it 31

32 Predictive Modeling & Marketing Presenter : Marty Ellingsworth mellingsworth@iso.com 32