PlumBot: Bot: Creating new article from JSON

2026-03-27T06:02:43Z

Bot: Creating new article from JSON

New page

📈 '''Propensity score''' is the estimated probability that an individual unit receives a particular treatment, conditional on observed pre-treatment characteristics. In insurance analytics, propensity scores serve as a dimension-reduction tool that allows analysts to compare policyholders, [[Definition:Claim | claimants]], or risk units with similar likelihoods of being exposed to an intervention — such as participation in a [[Definition:Loss prevention | loss prevention]] program, selection of a particular [[Definition:Deductible | deductible]] level, or enrollment with a specific [[Definition:Managing general agent (MGA) | MGA]] — thereby isolating the intervention's causal effect from [[Definition:Selection bias | selection bias]] embedded in observational [[Definition:Insurance | insurance]] data.

⚙️ Estimation typically involves fitting a logistic regression or, increasingly, a [[Definition:Machine learning | machine learning]] classifier on covariates such as policyholder demographics, prior [[Definition:Loss experience | loss experience]], [[Definition:Coverage | coverage]] characteristics, and geographic risk indicators. Once scores are computed, analysts deploy them through matching (pairing treated and control units with similar scores), stratification (grouping units into propensity score bins), weighting (inverse probability of treatment weighting), or as a covariate in [[Definition:Regression analysis | regression]] models. Each approach carries trade-offs in bias, variance, and sensitivity to model misspecification. A critical diagnostic step is assessing [[Definition:Overlap assumption | overlap]]: if the propensity score distributions for treated and untreated groups barely intersect, causal estimates depend on extrapolation and become unreliable. Insurance datasets, particularly in specialty lines like [[Definition:Cyber insurance | cyber]] or [[Definition:Professional liability insurance | professional liability]], can exhibit thin overlap when [[Definition:Underwriting | underwriting]] rules sharply segregate risk classes.

💡 Propensity score methods have become a mainstay in insurance research and operations because they make the identification strategy transparent. When a [[Definition:Reinsurance | reinsurer]] evaluates an [[Definition:Insurtech | insurtech]] platform's claim that its [[Definition:Underwriting | underwriting]] model produces superior [[Definition:Loss ratio (L/R) | loss ratios]], propensity score analysis can reveal whether the improvement stems from the model's skill or from favorable risk selection that would have occurred regardless. Regulatory applications are expanding as well: supervisors across the [[Definition:National Association of Insurance Commissioners (NAIC) | NAIC]], [[Definition:Solvency II | Solvency II]], and [[Definition:China Risk Oriented Solvency System (C-ROSS) | C-ROSS]] regimes increasingly expect carriers to demonstrate that [[Definition:Rating factor | rating factors]] reflect genuine risk differentiation. Propensity score diagnostics — particularly balance checks showing that treated and control groups are comparable after adjustment — provide intuitive, visual evidence that even non-technical stakeholders on boards and regulatory panels can evaluate.

'''Related concepts:'''
{{Div col|colwidth=20em}}
* [[Definition:Inverse probability weighting]]
* [[Definition:Causal inference]]
* [[Definition:Selection bias]]
* [[Definition:Overlap assumption]]
* [[Definition:Potential outcomes framework]]
* [[Definition:Matching methods]]
{{Div col end}}

Definition:Propensity score - Revision history

PlumBot: Bot: Creating new article from JSON