Predictive Models

Question 1

Potential benefits of using predictive analytics in insurance (REL)

Answer 1

• Reveals insights into insurance costs
• Encourages better risk management
• Lowers many consumer costs

Question 2

Challenges state insurance regulators face with predictive models

Answer 2

many lack the necessary tools to effectively review rapidly evolving predictive models

Question 3

2 main responsibilities given to Casualty Actuarial and Statistical (C) Task Force

Answer 3

• draft and propose changes to the Product Filing Review Handbook
• provide state guidance for rate filings based on predictive models

Question 4

Purpose of the guidance provided in the Predictive Models white paper

Answer 4

enhance uniformity in regulatory processes while considering state-specific insurance needs

Question 5

Purpose of regulatory best practices for predictive models (SIP)

Answer 5

• Support parameter valuation
• Improve model understanding
• Provide baseline for state regulators

Question 6

Do regulatory best practices create standards for filings with predictive models

Answer 6

No (but they help identify model elements and improve rating plans for consumers)

Question 7

How do regulatory best practices help state insurance regulators and the industry (5) (GIFIA)

Answer 7

• Guide regulators
• Identify key model elements
• Facilitate resource sharing
• Improve review quality
• Aid in training

Question 8

How do regulatory best practices benefit state insurance marketplaces

Answer 8

enhance market speed and competitiveness by improving the review process

Question 9

How do regulatory best practices assist new insurance regulators

Answer 9

provide training and help identify needed resources for model reviews

Question 10

Characteristics a predictive model should satisfy and regulators should verify (3)

Answer 10

• model is cost-based
• model is compliant with state law
• model improves the company’s rating plan

Question 11

Review items that should be included in regulatory reviews of predictive models (RMIM)

Answer 11

• check Rating factors
• check Data and model
• check Interaction of model with rating plan
• check whether model has desired characteristics regarding insurance Marketplace

Question 12

Regulatory review should check these rating factor characteristics (3) (PNC)

Answer 12

• Produce fair rates
• Not cause excessive premium disruptions
• Comply with state practices

Question 13

Regulatory review should check these data and model characteristics (4) (HAAF)

Answer 13

• How model was built
• Accuracy of input data
• Adjustments to raw data
• Update frequency of risk characteristics

Question 14

Regulatory review should check these interactions of the model with the rating plan (3)

Answer 14

• must understand input characteristics of model
• must understand integration of model with rating plan
• must understand interaction with non-modeled variables

Question 15

Regulatory review should check these desired effects on the insurance marketplace (3) (EPA)

Answer 15

• enable competition and innovation
• protect model confidentiality
• allow timely reviews for speed to market