phidea

Customer retention analytics for US insurers: which vendor for your situation (April 2026)

A decision guide for US P&C carriers adding churn prediction, retention scoring, and price-optimisation to their renewal flow. The right vendor depends on whether the buyer wants a standalone retention model, an integrated component of a dynamic-pricing platform, or a third-party data service predicting shopping behaviour.

Bottom line

Dynamic pricing + retention in one platform: Earnix.

Shopping-behaviour data via third-party signals: LexisNexis Risk Solutions or Verisk.

CRM-layer retention workflow: Salesforce Financial Services Cloud or embedded Duck Creek / Guidewire modules.

Specialist ML-retention for auto personal lines: Akur8 retention use case.

Which to pick

ScenarioRecommended
Carrier integrating retention with dynamic pricingEarnix
Carrier wants shopping-behaviour signalsLexisNexis Risk Solutions
Insurance-specific CRM with retention + save-deskSalesforce Financial Services Cloud
Mid-market auto personal lines ML-retention modelAkur8 (retention use case)
Carrier on Guidewire/Duck Creek wants native retentionNative PAS retention modules

Ranking criteria

  • Standalone retention model vs integrated platform
  • Use case (renewal price-optimisation vs cross-sell vs save-desk)
  • Existing vendor stack (Guidewire, Duck Creek, Salesforce)
  • Data-enrichment partners (LexisNexis, Verisk, IHS)
  • ML transparency / state-DOI defensibility
#1

Earnix

modern · rating
Fiche →

Default for carriers unifying dynamic pricing and retention on one platform.

Situation fit. Mid-to-tier-1 carriers wanting to unify price optimisation and retention scoring on one programmable platform. Multi-region operators needing consistent retention logic across countries.

Why Earnix. Category-spanning platform; retention is an integrated use case rather than a bolt-on. Strong analyst coverage and broad named-carrier footprint.

When Earnix is the wrong pick. Pure CRM / save-desk workflow (Salesforce fits). Lightweight retention use case where a native PAS module suffices.

#2

LexisNexis Risk Solutions

modern · data-platform
Fiche →

Default for carriers needing third-party shopping-behaviour signals.

Situation fit. Carriers whose retention risk is driven by competitive-quoting behaviour they cannot see in their own data. LexisNexis Shopping Insights / retention-score products fill this gap.

Why LexisNexis. Broad US insurance-data footprint; unique visibility into multi-carrier quote activity because LexisNexis is the data provider for most US quote-comparison platforms. Verisk offers related capabilities.

When LexisNexis is the wrong pick. Buyers who want an integrated pricing+retention platform (Earnix wins). Buyers who do not need shopping-behaviour signals because their churn is driven by other factors.

#3

salesforce-financial-services-cloud

Default for carriers where save-desk / agent workflow is the retention lever.

Situation fit. Carriers where retention is operationalised in the agent / call-centre layer. Carriers already on Salesforce looking to extend into insurance-specific workflows.

Why Salesforce FSC. Broad CRM footprint plus insurance-vertical templates. Strong save-desk / agent productivity features.

When Salesforce is the wrong pick. Direct carriers where retention is a pricing problem not an agent-workflow problem.

Buyer reality

What a carrier procurement team should expect on scope, budget, and integration cost.

Situation-scoped diligence.

  • Pricing + retention unified buyer: ask Earnix for measured retention lift on named carrier deployments similar to yours. Ask specifically about state-DOI defensibility of retention-model-driven pricing differences.
  • Shopping-signal buyer: ask LexisNexis for a proof-of-concept on your book to measure shopping-score predictive accuracy vs your existing model before signing.
  • Save-desk workflow buyer: ask Salesforce FSC for insurance-specific implementation references with named US carrier save-desk deployments.
  • ML-retention buyer: ask Akur8 or similar vendors whether their retention-model outputs have been accepted in your state's rate filings.

Deployment realism.

  • Retention-analytics deployments tend to be 6-12 months. Primary friction is data integration (pulling policy history + claims + third-party signals into one scoring layer).
  • Measurable lift typically shows at 2+ renewal cycles post-deployment.
  • Regulatory risk: state DOIs have begun scrutinising ML-driven price variations by retention factor. Keep a paper trail of explainability and bias testing.

Also considered

  • Akur8

    ML-rating platform. Retention can be framed as a pricing elasticity problem and modelled inside Akur8. Strong for mid-market personal-lines auto where retention and pricing are tightly coupled.

  • verisk-rx

    Verisk data services for US P&C retention use cases. Secondary option to LexisNexis; evaluate both.

  • Guidewire PolicyCenter

    Native Guidewire retention analytics. Usually not the primary choice but fits if the carrier is Guidewire-native and the use case is light.

Sources

Last reviewed 2026-04-23. Vendor-sourced aggregate claims are flagged [self-reported]in the justification text. Ranking refreshes when a vendor’s fiche is revised or when a new material event (acquisition, analyst report, major deployment) changes the order.