Regulation & Fairness

199 articles in this topic

05 Apr 2026

Why Stacking Fairness, Calibration, and Drift Corrections Breaks Your Pricing Model

Applying fairness constraints, calibration corrections, and drift monitoring as sequential post-hoc steps is how most UK pricing teams work. It is also architecturally broken. E...
05 Apr 2026

What PRA Auditors Will Ask to See in 2026: Mapping SS1/23 to Automated Pricing Model Monitoring

SS1/23 is in active enforcement for banks. Its monitoring principles — operating boundaries, outcome analysis, documented escalation — are the benchmark the whole market is bein...
05 Apr 2026

Repricing at the floor: how to find headroom in UK motor without triggering Consumer Duty

UK motor NCR is at 111% (EY Q4 2024). The market is at or near technical floor. Here is how to identify underpriced segments using loss cost trending, A/E monitoring, and Bühlma...
05 Apr 2026

The Fairness Audit That Passes Without Measuring Anything: Proxy Race Bias in UK Insurance Pricing

A companion post to our March coverage of arXiv:2603.17106. This one walks through the code: where exactly in a UK proxy-based fairness audit does the bias from Xin et al. enter...
05 Apr 2026

What PRA auditors will ask to see in 2026: mapping SS1/23 to automated pricing model monitoring

SS1/23 applies to banks, not insurers — but its monitoring principles are the benchmark auditors use regardless. This post maps the five SS1/23 validation principles to what a p...
05 Apr 2026

Building a regulatory-grade AI pricing model for the FCA's Live Testing sandbox

FCA cohort 2 is live as of April 2026. This post maps the four things a submission actually needs to include — outcome monitoring, proxy bias detection, uncertainty quantificati...
05 Apr 2026

Who Owns Fair Value in a Delegated Authority Chain?

The FCA is consulting in Q2 2026 on exactly this question. Every layer in a DA chain — insurer, MGA, broker, PCW — is expected to evidence outcomes, not just process. Here is wh...
05 Apr 2026

Building a regulatory-grade AI pricing model: what the FCA's Live Testing cohort actually requires

FCA AI Live Testing cohort 2 opened in January 2026. Testing is live from April. Firms in scope for AI underwriting and pricing need to demonstrate four things: outcome monitori...
05 Apr 2026

Conformal Prediction Passes 90% Coverage, But Your Young Drivers Get 82%: ConditionalCoverageAssessor Fixes That

insurance-conformal v1.3.1 adds ConditionalCoverageAssessor — a tool for detecting and decomposing conditional coverage failures in conformal prediction intervals. Here is the p...
04 Apr 2026

Survival Analysis for Insurance Lapse Modelling in Python: A Complete Tutorial

A hands-on Python tutorial for insurance pricing analysts on survival analysis and lapse modelling. Covers Kaplan-Meier, Weibull AFT, mixture cure models, customer lifetime valu...
04 Apr 2026

The Fairness Impossibility You Cannot Optimise Away — and What Boonen et al. Get Right About It

Chouldechova (2017) proved that when group base rates differ, no classifier can simultaneously achieve calibration within groups, equal false positive rates, and equal false neg...
04 Apr 2026

Motor Finance Redress: What PS26/3 Tells Insurance Pricing Teams About Their Own Exposure

The FCA confirmed its motor finance redress scheme on 30 March 2026 — £7.5bn, 12.1m agreements, going back to 2007. The enforcement pattern is not motor-finance-specific. Insura...
04 Apr 2026

Insurance Model Monitoring in Python: A Practitioner's Guide

How to set up insurance model monitoring in Python from scratch: PSI, Gini drift, and A/E with the insurance-monitoring library. Know when to redeploy, recalibrate, or refit.
04 Apr 2026

Detection vs Mitigation: insurance-fairness and EquiPy Are Not Competing

EquiPy (Fernandes Machado, Charpentier et al.) does distributional fairness correction via Wasserstein barycenters. insurance-fairness does proxy discrimination auditing for UK ...
04 Apr 2026

Insurance Fairness Audit in Python: A Complete FCA Consumer Duty Walkthrough

Step-by-step Python tutorial for running an insurance fairness audit. Covers proxy discrimination detection, exposure-weighted bias metrics, FCA Consumer Duty mapping, and gener...
04 Apr 2026

glum Insurance Pricing in Python: Fitting, Intervals, Monitoring, Fairness, Governance

glum fits the Tweedie GLM in seconds. Here is how our libraries handle everything around it: distribution-free prediction intervals, PSI/CSI drift monitoring, Consumer Duty prox...
04 Apr 2026

GAM Insurance Pricing in Python: An EBM Tariff Tutorial with insurance-gam

A hands-on tutorial on GAM insurance pricing in Python using the insurance-gam library. Covers EBM tariff construction, shape function extraction, GLM comparison, Shapley values...
04 Apr 2026

Five Libraries, One Pipeline: End-to-End Motor Pricing in Python

A single freMTPL2 motor pipeline running through insurance-gam, insurance-conformal, insurance-monitoring, insurance-fairness, and insurance-governance. No other open-source eco...
04 Apr 2026

Fairness in the Tail: Why Mean Demographic Parity Is the Wrong Test

Le, Denis and Hebiri (arXiv:2604.02017, April 2026) show that enforcing demographic parity over the full prediction distribution is both accuracy-costly and unnecessary. The rig...
04 Apr 2026

Causal Inference for Insurance Pricing in Python: A Complete DML Tutorial

A hands-on tutorial on causal inference for insurance pricing in Python using the insurance-causal library. Covers double machine learning (DML), CatBoost nuisance models, ATE/C...
04 Apr 2026

Three Things Your Pricing Model Needs to Survive in Production — and One Framework That Provides All of Them

Nayak's Calibrated Credit Intelligence (arXiv:2603.06733) is a credit paper, but UK insurers should read it. It addresses uncertainty quantification, fairness constraints, and t...
04 Apr 2026

Actuarial Model Validation in Python: Automated Reports for UK Insurance Pricing

How to run actuarial model validation in Python for UK insurance pricing models. Covers Solvency II Article 120 and Consumer Duty requirements, the five-test validation suite, a...
03 Apr 2026

Your SHAP Feature Importance Bar Chart Has No Error Bars — Here Is How to Fix That

A February 2026 paper provides the first statistically valid confidence intervals for global SHAP feature importance. We explain what changes for UK insurance pricing teams, whe...
03 Apr 2026

Per-Policyholder Proxy Discrimination Scores: From Research Metric to Consumer Duty Evidence

The Lindholm-Richman-Tsanakas-Wüthrich EJOR 2026 paper gives pricing teams something they did not previously have: an instance-level proxy discrimination score for every policy ...
03 Apr 2026

Multi-State Fairness: Four Things arXiv:2602.04791 Doesn't Tell You

The per-transition Lindholm correction for multi-state models is sound. But arXiv:2602.04791 has four gaps that matter before you build on it: no accuracy degradation figures, d...
03 Apr 2026

Consumer Duty Audits One Firm. This Paper Asks What Happens to the Market.

Thibodeau et al. build a multi-firm market simulator and train an RL social planner to design fairness tax schedules. The collusion result stops the paper cold: a cartel that ex...
03 Apr 2026

Building an FCA Ethnicity Fairness Evidence Pack Without Holding Ethnicity Data

An FCA Research Note (December 2025) found a £28 unexplained ethnicity residual across six million motor policies. Your pricing team cannot measure it because you do not hold et...
03 Apr 2026

KL Fairness Corrections and Multiplicative GLMs: The Production Deployment Problem

Miao & Pesenti's KL discrimination-insensitive result is theoretically clean. Deploying it in a production GLM-based pricing system is not. The paper is silent on how to extract...
03 Apr 2026

What You Can Actually Say in a Fairness Attestation (and What You Cannot)

Most fairness sections in model validation reports say nothing. The KL discrimination-insensitive result from Miao & Pesenti (2026) gives you a precise, defensible claim: we app...
03 Apr 2026

Minimum-Distortion Fair Pricing: What Miao & Pesenti Actually Prove (and What We Already Build)

Miao & Pesenti (2026) derive the nearest fair probability measure in KL divergence. Their existence theorem is useful for FCA Consumer Duty attestation. Our insurance-fairness l...
03 Apr 2026

Five Ways Insurance Fraud ML Papers Mislead You (And How to Spot Them)

Insurance fraud ML papers routinely overstate their results through five avoidable errors: wrong evaluation metric, no external baseline, random train/test split, foreign data, ...
03 Apr 2026

The FCA's AI Evaluation Is Coming: Do You Have Per-Decision Audit Trails?

Most pricing teams have model documentation. Almost none have per-decision audit trails. The FCA's Q2 2026 AI evaluation will test exactly this gap. Here is what the FCA actuall...
03 Apr 2026

Bayesian Doubly Robust Causal Inference: What Entropic Tilting Adds and Why We Are Watching, Not Building

Orihara, Momozaki & Sugasawa (arXiv:2506.04868) produce a Bayesian posterior over the ATE by tilting the product of independent posteriors to satisfy the DR moment condition. We...
02 Apr 2026

Your SHAP Bar Chart Has No Error Bars

SHAPInference (in development for shap-relativities): asymptotically valid confidence intervals on global SHAP feature importance using de-biased U-statistics. Every SHAP import...
02 Apr 2026

Your Model Comparison Has No Error Bars

insurance-monitoring v1.2.0 adds ScoreDecompositionTest: HAC-robust p-values on the miscalibration and discrimination components of any scoring rule. When your pricing team argu...
02 Apr 2026

Your Challenger GBM Beats the GLM — But Does It Deserve Deployment?

When a challenger GBM outperforms the production GLM on deviance, the improvement is often entirely in miscalibration — meaning the GLM could be recalibrated to match without a ...
02 Apr 2026

Pricing Fairly Without Seeing the Data: Local Differential Privacy for Insurance

insurance-fairness v1.2.0 adds PrivatizedFairPricer: discrimination-free pricing when the sensitive attribute is privatised via local differential privacy. Based on Zhang, Liu &...
02 Apr 2026

Tensors for Mortality: What MDMx Does That Lee-Carter Can't, and Why CMI Still Wins for Now

Samuel Clark's MDMx (arXiv:2603.20518) applies Tucker tensor decomposition to HMD mortality data across 50 countries, producing coherent forecasts, disruption detection, and mod...
02 Apr 2026

Your GLM Passes Mean Fairness. Does It Pass the Tier Test?

insurance-fairness v0.8.0 adds LocalizedParityCorrector and LocalizedParityAudit — enforcement of demographic parity at pricing tier boundaries, not just on portfolio averages. ...
02 Apr 2026

Can LLMs Pass Their Insurance Exams? The Wrong Question for Pricing Teams

Beauchemin & Khoury (arXiv:2603.07825) benchmark 51 LLMs on Quebec insurance regulatory certification questions. Passing insurance exams is the wrong success metric for pricing ...
02 Apr 2026

Building-Level Flood Pricing: What Flood Re's 2039 Phase-Out Means for Your Models

Flood Re ends in 2039. From that date, 350,000+ currently subsidised properties need risk-reflective pricing. We work through Moriah et al. 2026's sequential GLM using geolocate...
02 Apr 2026

FCA MS24/1 and Income Protection: What Occupation Class Is Actually Doing to Your Premiums

The FCA's pure protection market study interim report landed in January 2026. The final report is due Q3 2026. For income protection pricing teams, the central question is wheth...
02 Apr 2026

FCA 2026 Insurance Regulatory Priorities: What Pricing Teams Need to Know

The FCA published its first consolidated insurance priorities report on 24 February 2026. It replaces individual portfolio letters and signals where regulatory action is coming ...
02 Apr 2026

The Fairness Pareto Front: Why There Is No Single Dial

Pricing teams treat fairness as a single slider between accuracy and parity. NSGA-II reveals it is a landscape with multiple competing criteria. Here is what the Pareto front lo...
02 Apr 2026

Conformal Fairness When the Protected Attribute Is Missing

Kong, Liu & Yang prove that standard conformal coverage guarantees degrade unevenly when protected attributes are absent at test time. With post-ECJ gender prohibition and GDPR ...
02 Apr 2026

Per-Prediction Audit Trails for Pricing Models: insurance-governance v0.3.0

insurance-governance v0.3.0 adds ExplainabilityAuditTrail: a per-prediction audit log that records SHAP values, fairness flags, and plain-language summaries for every pricing de...
02 Apr 2026

Your Conformal Intervals Lie About Some Policyholders

Marginal 90% coverage can hide severe undercoverage for specific risk profiles. ConditionalCoverageAssessor — new in insurance-conformal v1.2.0 — quantifies it with CVI, decompo...
02 Apr 2026

CLV-Integrated Ratemaking: When Customer Lifetime Value Belongs in the Technical Premium

Most pricing teams treat acquisition and retention as separate problems. CLV-aware ratemaking integrates expected policy duration, cross-sell probability, and claim cost traject...
02 Apr 2026

From Competitor Quotes to Risk Parameters: ABC for Entry Pricing in Python

A runnable Python implementation of Goffard, Piette, and Peters (ASTIN Bulletin 2025): infer claim frequency and severity from competitor PCW quotes using ABC-SMC with isotonic ...
01 Apr 2026

Applying Bonus-Malus to Driving Behaviour, Not Just Claims

Yanez, Guillen and Nielsen (ASTIN Bulletin 2025) apply a bounded Bonus-Malus System not to claims but to telematics signals themselves, updating weekly. The result: Gini from 0....
01 Apr 2026

What Machine Learning Can (and Cannot) Do for Vulnerable Customer Underwriting

The FCA has flagged travel insurance for mental health conditions and contents insurance for social renters as supervisory priorities. Here is what ML can genuinely help with, w...
01 Apr 2026

Territory Rating Beyond Postcode Lookup Tables

UK territory rating is mostly postcode-to-band lookup tables. That creates both actuarial and regulatory risk. We work through the spatial statistics toolbox that does better: B...
01 Apr 2026

Semi-Structured Multi-State Models for Policy Lapse: A Mortgage Paper Worth Watching

Medina-Olivares, Xia, Lessmann and Klein (arXiv:2603.26309, March 2026) build a semi-structured neural network model for mortgage delinquency transitions. The method combines a ...
01 Apr 2026

SafeDriver-IQ: Telematics Scoring via Inverse Crash Probability

Roy, Singh, and Das (arXiv:2603.14841) build a 0-100 driver safety score by inverting a crash classifier and multiplying in condition-specific penalty factors. The maths is clea...
01 Apr 2026

Protected NCD Is a Fair Value Problem Waiting to Happen

Protected NCD is widely misunderstood by consumers, and the product may not deliver the value it charges for. The Consumer Duty fair value test and the hunger-for-bonus literatu...
01 Apr 2026

Your GLM Confidence Intervals Are Wrong After Lasso — Here Is the Bias-Corrected Fix

PenalizedGLMInference in insurance-gam v0.5.0 implements Manna et al. arXiv:2410.01008: bias-corrected confidence intervals for Poisson, Gamma, and Tweedie GLMs after Lasso or e...
01 Apr 2026

Lindholm Fairness Is Not Enough for Income Protection Pricing

Standard discrimination-free pricing applies to a single outcome. Income protection premiums are derived from a matrix of transition rates. Applying Lindholm to the aggregate pr...
01 Apr 2026

MGA Entry Pricing: A Four-Stage Architecture from Day Zero to Year Three

An MGA launching on a UK PCW needs prices on day one with zero claims history. Here is the full architecture: market ABC as the prior, Bühlmann-Straub blending as claims arrive,...
01 Apr 2026

Mahalanobis Conformal Prediction: When Ellipsoids Beat Rectangles (and When They Do Not)

Braun et al. (arXiv:2507.20941) replace the standard hyperrectangular joint prediction set with an ellipsoid built from a Mahalanobis nonconformity score. For d=2 (frequency + s...
01 Apr 2026

LDP Optimal Mechanism for Privatised Fairness Auditing in Insurance Pricing

k-ary randomised response applies symmetric noise — wasteful and fairness-suboptimal. The Ghoukasian-Asoodeh optimal mechanism is asymmetric: minority groups get a higher correc...
01 Apr 2026

Intersectional Fairness in Insurance Pricing: Why Auditing Age and Gender Separately Is Not Enough

A model can pass its age fairness audit and its gender fairness audit and still systematically overprice young women. This is fairness gerrymandering. We explain the CCdCov meas...
01 Apr 2026

FCA Consumer Duty Outcome Testing: Automating the Evidence Pack

The FCA's February 2026 insurance priorities report signals active supervisory review of AI pricing in Q1-Q2 2026. Under existing PRIN 2A, firms must already demonstrate Consume...
01 Apr 2026

FCA 2026 Insurance Priorities: A Pricing Actuary Checklist

The FCA published its first annual insurance regulatory priorities document in February 2026. Here is everything a pricing actuary needs to do in response — ten action items wit...
01 Apr 2026

The EU AI Act's Age Problem: Why Solvency II and Article 21 Cannot Both Be Right

Solvency II requires age-based pricing. EU AI Act Article 21 lists age as a prohibited characteristic. Chouldechova's impossibility theorem shows you cannot satisfy both fairnes...
01 Apr 2026

The EU AI Act and Insurance Pricing Fairness: The Tension Nobody Has Resolved

Age is a legally permitted rating factor under Solvency II. Age is also a protected characteristic under EU law. The EU AI Act imposes non-discrimination obligations on high-ris...
01 Apr 2026

Five Ways to Get Market Data for Entry Pricing — and What Each Actually Delivers

A UK MGA at launch has five routes to market data: competitor quote reverse-engineering, rate indices from Consumer Intelligence, ABI aggregate statistics, capacity provider dat...
01 Apr 2026

EIOPA's AI Governance Opinion: What UK Pricing Teams Need to Do

EIOPA published its AI Governance Opinion (EIOPA-BoS-25-360) in August 2025. It names the actuarial function as responsible for AI controls, endorses SHAP and LIME explicitly, a...
01 Apr 2026

Cross-Product Claim Scores: Do They Work in the UK?

Verschuren (2021) showed that a Dutch insurer's home claim history predicts motor risk, and vice versa. The framework is technically clean. The UK structural context — aggregato...
01 Apr 2026

Your Prediction Intervals Are Unfair (And You Haven't Checked)

Vadlamani et al. (ICLR 2025, arXiv:2505.16115) formalise fairness at the prediction-set level. A model can be statistically valid at 90% coverage while covering elderly policyho...
01 Apr 2026

Conformal Control Charts: Replacing PSI Thresholds With a Proper False Alarm Rate

PSI thresholds of 0.1 and 0.2 are industry convention, not statistical calibration. Burger (arXiv:2512.23602, Dec 2025) replaces them with conformal p-values, giving a distribut...
31 Mar 2026

Conformal Prediction for Lapse Timing When Your Book Has Shifted

Shin, Lee and Kang (arXiv:2512.03738, Dec 2025) provide the first finite-sample coverage guarantee for time-to-event prediction under covariate shift. Here is what it means for ...
31 Mar 2026

Text Embeddings for Insurance Pricing — When Do They Actually Help?

Text embeddings can compress 13,000 business categories into 24 useful features and add 2-3% Gini lift on commercial lines. For UK personal motor FNOL they do essentially nothin...
31 Mar 2026

Sequential Optimal Transport for Multi-Attribute Fairness in Insurance Pricing

Naively applying Wasserstein barycenter corrections sequentially across multiple protected attributes is miscalibrated: the ECDF for attribute k was fitted on the original predi...
31 Mar 2026

Measuring Proxy Discrimination in Insurance Pricing: The LRTW Scalar Metric

Lindholm, Richman, Tsanakas and Wüthrich (EJOR, January 2026) give us a scalar proxy discrimination measure with a property none of the existing methods share: PD=0 if and only ...
31 Mar 2026

Risk-Informed Renewal Classification: Bridging the Pricing-Retention Silo in UK Motor

Boonkrong et al. (MDPI Risks 14(3):57, March 2026) show that adding actuarial pricing features to a renewal classifier materially improves prediction — the insight being that th...
31 Mar 2026

Retention-Aware UBI Pricing: Risk Score, Churn Elasticity, and Consumer Duty

Li, Luo, Zhang, Huang and Jiang (IME 2025) combine telematics risk scoring with individual price sensitivity estimation and constrained discount allocation. Here is how to adapt...
31 Mar 2026

Profit-Fairness Market Equilibria: Why Consumer Duty Audits the Wrong Unit

Thibodeau et al. build a multi-firm market simulator and demonstrate the collusion pathology: a cartel that excludes every income group equally passes standard demand-fairness m...
31 Mar 2026

Pricing SME Cyber with Python - What Works and What Doesn't

UK SME cyber is growing at 13% CAGR with 2.8% standalone penetration. The data is terrible, the commercial tools are six figures, and the best published frequency model explains...
31 Mar 2026

Offset vs Ratio Exposure in Insurance Frequency Modelling: When It Matters and When It Doesn't

Boucher & Coulibaly (arXiv:2502.11788) prove that for Poisson frequency models, log-exposure offset and exposure-weighted ratio approaches are identical. The distinction only bi...
31 Mar 2026

Balance and Fairness Are the Same Problem — Multicalibration in Insurance Pricing

Denuit, Michaelides & Trufin (arXiv:2603.16317) prove that autocalibration and group fairness are mathematically equivalent. A GBM that is well-calibrated overall but miscalibra...
31 Mar 2026

Multi-State Fairness in Income Protection and Critical Illness: Why Lindholm on the Aggregate Premium Is Wrong

Lim, Xu & Zhou (arXiv:2602.04791) show that multi-state models decompose into independent Poisson GLMs — one per transition — making every single-period fairness method directly...
31 Mar 2026

From Competitor Quotes to Risk Parameters: Implementing Market-Based Ratemaking in Python

The Goffard/Piette/Peters ABC-SMC method infers risk parameters from competitor quotes with no claims history. No Python implementation exists - only IsoPriceR in R. Here is the...
31 Mar 2026

Proxy Discrimination Risk When LLM-Generated Features Enter Insurance Pricing Models

LLMs encode societal stereotypes. When you use one to generate rating features, those stereotypes enter your pricing model. The insurer is responsible. Here is the testing proto...
31 Mar 2026

LLM Feature Engineering for Insurance Pricing — What Actually Works

Three published frameworks use LLMs to generate tabular features and beat classical search tools on generic benchmarks. None has been tested on an actuarial dataset. We explain ...
31 Mar 2026

KL Discrimination-Insensitive Pricing: The Information-Theoretic Foundation

Miao & Pesenti (arXiv:2603.16720) derive the discrimination-insensitive pricing measure from first principles: find the nearest probability measure Q to the real-world P, in KL ...
31 Mar 2026

Gini Drift Tests and Murphy Decomposition: What Insurance Model Monitoring Was Missing

Brauer, Menzel & Wüthrich (arXiv:2510.04556) give us two things we have been missing: a formal hypothesis test for Gini drift and a Murphy score decomposition that tells you whe...
31 Mar 2026

GAMs vs Neural Additive Models: A Decision Guide for UK Pricing Teams

arXiv:2510.24601 reviewed 143 papers across 430 datasets and found no consistent accuracy advantage for neural networks over GAMs on tabular data by 2024. What that means for th...
31 Mar 2026

Focal Loss for Insurance Fraud Detection — Why You Should Use XGBoost Instead

Focal loss is a clever idea from computer vision that does not translate well to tabular insurance fraud data. AUC=0.63 from a three-stage focal loss neural network versus 0.75-...
31 Mar 2026

Why your rate change evaluation should be doubly robust

Sun, Xie & Zhang (arXiv:2503.11375) combine parallel trends and synthetic control into a single estimator that remains consistent if either assumption holds. We explain the math...
31 Mar 2026

Distribution-Free Prediction Intervals for Insurance Pricing — Conformal Methods That Actually Work

GLM prediction intervals targeting 95% coverage achieved 57.8% actual coverage on real personal injury data. Conformal prediction fixes this without distributional assumptions. ...
31 Mar 2026

Discrimination-Free Pricing When You Don't Have the Protected Attribute

Zhang, Liu and Shi (arXiv:2504.11775, 2025) extend discrimination-free pricing to the case where you only have a noisy privatised version of the protected attribute. The correct...
31 Mar 2026

Constrained Neural Networks for Insurance Pricing — Architectural vs Post-Hoc

If you are using XGBoost's monotone_constraints or applying isotonic regression post-hoc, you may already have everything you need. Or you may not. The answer depends on your mo...
31 Mar 2026

Conformal Prediction with Change Points: When Your Coverage Guarantee Breaks and What to Do About It

Conformal prediction with change points (CPTC, arXiv:2509.02844, NeurIPS 2025) extends adaptive conformal inference to detect structural breaks and reset coverage guarantees pro...
31 Mar 2026

Testing Conditional Coverage in Conformal Prediction — The ERT Diagnostic

Conformal prediction gives valid marginal coverage but says nothing about conditional coverage — your intervals can fail for young drivers or flood-zone properties while the por...
31 Mar 2026

Competing Risks Calibration: Why Your Fine-Gray Validation Is Wrong

D-calibration and ICI are mathematically invalid for competing-risks models. If F_k(inf|x) < 1 — which is always true for lapse, claim, and MTA competing causes — the probabilit...
30 Mar 2026

Your Fairness Audit Is Underreporting Bias — Proxy Measurement Error in Insurance Pricing

Every UK fairness audit that uses LSOA ethnicity percentages as its protected attribute is reporting a lower bound on bias, not the true figure. Here is what that means in pract...
28 Mar 2026

Survival Models for Insurance Lapse Prediction: What Actually Works

Deep learning survival models underperform Cox regression on tabular insurance data. Cure models are the real story post-GIPP. Here is what the research says and what UK pricing...
28 Mar 2026

Reinforcement Learning for PCW Insurance Pricing: What Actually Works

A practitioner-oriented deep dive on applying reinforcement learning and contextual bandits to PCW margin optimisation for UK personal lines. Two serious papers exist, six hard ...
28 Mar 2026

The PRA Just Named AI a Supervisory Theme. What That Means for Your Pricing Models.

In January 2026 the PRA named AI as an insurance supervisory theme for the first time. The FCA published a bias research note in December 2024. The FRC updated TAS 100 to make b...
28 Mar 2026

What PRA SS1/23 Validation Looks Like on Real Data: 677K French Motor Policies

Most governance tooling is tested on toy examples with clean DGPs and inflated Gini coefficients. We ran the full insurance-governance validation suite on 677K freMTPL2 policies...
28 Mar 2026

FCA Premium Finance Market Study MS24/2 — What Pricing Teams Need to Know

The FCA published its final premium finance market study on 3 February 2026. No APR cap was imposed. That does not mean your book is clean. Here is what changed, what double dip...
28 Mar 2026

FCA Access to Insurance: What Pricing Teams Actually Need to Do

The FCA's 2026 access priorities are not a compliance problem — they are an actuarial evidence problem. The question is whether the data exists to justify what your models are d...
28 Mar 2026

Fairness-Accuracy Tradeoffs in Insurance Pricing — Pareto Frontiers with NSGA-II

Single-objective fairness constraints force a binary choice. NSGA-II finds the full tradeoff surface, so governance committees can make an explicit, documented decision about wh...
28 Mar 2026

EU AI Act update: motor pricing probably isn't high-risk (and your GLMs may not be AI)

We published a post three weeks ago treating all insurance pricing models as potentially high-risk under the EU AI Act. After reading the primary sources, we need to correct thr...
28 Mar 2026

EU AI Act and Insurance Pricing — What You Actually Need to Know

Most industry guidance on the EU AI Act and insurance pricing is wrong in ways that matter. Motor and property pricing is not high-risk AI. Traditional GLMs may not be AI system...
28 Mar 2026

Building an EU AI Act Conformity Assessment for Your Pricing Model

A step-by-step guide to building an EU AI Act conformity assessment for an insurance pricing model. Covers risk classification, Article 11 technical documentation, Article 14 hu...
28 Mar 2026

EU AI Act Article 13: what transparency actually requires for a pricing model

Article 13 of the EU AI Act is not about SHAP values. It is about deployer-facing documentation — what the underwriter or product team needs to interpret and use a pricing model...
28 Mar 2026

Your Elasticity Model Has a 3x Bias

Most UK motor insurers think they know their price elasticity. They are probably wrong by a factor of 3–5, in the direction that makes them systematically mispricing. The eviden...
28 Mar 2026

Dynamic Pricing for UK Motor and Home Insurance — Build or Buy?

A practitioner's guide to dynamic pricing in UK insurance: what GIPP actually permits, why your elasticity model likely has a 3-5x bias, and an honest assessment of whether Earn...
28 Mar 2026

Does Proxy Discrimination Testing Actually Work?

Manual Spearman correlation missed postcode as an ethnicity proxy in 100% of 50 benchmark runs. CatBoost proxy R-squared caught it in 100% of runs. The difference is the non-lin...
28 Mar 2026

Does Constrained Rate Optimisation Actually Work?

We benchmarked constrained portfolio optimisation against a uniform +7% rate change on a 2,000-policy UK motor book. The optimiser achieved the same GWP target with £4,000–8,000...
28 Mar 2026

The Nearest Fair Price: KL-Divergence and Discrimination-Insensitive Pricing

Miao & Pesenti (arXiv:2603.16720) derive discrimination-insensitive premiums by finding the probability measure nearest to the real-world measure in KL-divergence, subject to ze...
27 Mar 2026

Multicalibration: Portfolio Balance and Fairness Are the Same Test

Denuit, Michaelides and Trufin (March 2026) unify autocalibration and non-discrimination into a single actuarial test. If your model fails it, you have a pricing problem and a r...
27 Mar 2026

What a Real Fairness Audit Finds: Gender Bias Testing on 67,856 Motor Policies

We ran insurance-fairness against ausprivauto0405 — a real Australian motor dataset with an explicit Gender field. Here is what FairnessAudit, MulticalibrationAudit, and Indirec...
26 Mar 2026

Portfolio-Anchored Telematics Risk Scoring with Wavelets

Lee, Badescu, and Lin (2026) replace ad-hoc event counts with a principled actuarial risk index: MODWT decomposes the acceleration signal, a Gaussian-Uniform mixture anchors tai...
26 Mar 2026

Robust Discrete Pricing Optimisation via Knapsack

A new paper from ETH Zürich (arXiv:2603.18653) frames the conversion from technical price to commercial premium as a Multiple-Choice Knapsack Problem. Under 1% revenue cost for ...
26 Mar 2026

Proxy Race Distortion in Fairness Audits: The Direction of Error Is Not What You Think

A new paper (Xin, Hooker, Huang 2026) shows that BIFSG proxy race distorts regression-based fairness audits in two distinct mechanisms — and the direction of distortion is group...
26 Mar 2026

Text Embeddings on Claims Data: The Pipeline, the Papers, and the Limits

How to turn insurance claims descriptions into GLM features using sentence-transformer embeddings and PCA. What Troxler & Schelldorfer (2024, BAJ) actually showed, what the Kagg...
26 Mar 2026

Multi-Dimensional Mortality Modelling with Tucker Decomposition

Samuel Clark's MDMx organises the Human Mortality Database as a four-way tensor and applies Tucker decomposition to produce structurally coherent mortality models across 50 coun...
26 Mar 2026

FCA SMCR Rollback: What It Actually Means for Pricing Governance

Two deregulatory signals in the FCA's February 2026 insurance priorities document. The SMCR one is almost entirely administrative. The Consumer Duty one is real but has no CP nu...
26 Mar 2026

Is Your Pricing Engine a Material System Under FCA PS26/2?

FCA PS26/2 (March 2026) creates mandatory incident reporting and material third party registers for all authorised insurers. Every pricing actuary who owns a rating API, renewal...
26 Mar 2026

The Mills Review: What the FCA's Long-Term AI Inquiry Means for Pricing Teams

The FCA's Mills Review is not another compliance checklist — it is the regulator thinking aloud about how UK financial services might look in 2030. Pricing teams should read it ...
26 Mar 2026

Connected-Car Data Sources for Insurance Pricing: Beyond the Black Box

OEM APIs, smartphone SDKs, and charging data — what connected-car data sources UK pricing teams can actually access, and how to turn them into rating factors.
25 Mar 2026

PS21/5 End-to-End: Renewal Pricing Optimisation That Actually Satisfies the FCA

The complete PS21/5 compliance workflow: CATE estimation with insurance-causal, ENBP-constrained optimisation with insurance-optimise, fairness audit with insurance-fairness, an...
25 Mar 2026

Privacy-Preserving Pricing: Federated Learning and Differential Privacy

UK GDPR constrains what pricing data you can share across entities. Federated learning and differential privacy offer a way around the constraint — but only if you understand wh...
25 Mar 2026

Premium Finance APR as a Pricing Problem

FCA MS24/2 (February 2026) means pricing teams now own the APR question. Here is how to treat it as a pricing problem — with the same tools used for the insurance itself.
25 Mar 2026

Pet Insurance Pricing in 2026: Why the FCA Is Watching

The FCA has explicitly flagged pet insurance for monitoring in its 2026 regulatory priorities. FOS complaint upheld rates hit 52% in Q1 2025 — the highest of any UKGI business l...
25 Mar 2026

Multi-Objective Insurance Pricing: Finding the Pareto Front of Accuracy, Fairness, and Profit

NSGA-II finds the non-dominated pricing strategies across accuracy, group fairness, and counterfactual fairness simultaneously. TOPSIS turns that front into an auditable regulat...
25 Mar 2026

Our 12-Module Insurance Pricing Course Is Now Free and Open Source

Modern Insurance Pricing with Python and Databricks - all 12 modules, free, on GitHub. GLMs through causal elasticity, fairness auditing, spatial BYM2 territory models, and mode...
25 Mar 2026

How to Model BI Claims Trajectory Under Whiplash Reform Uncertainty

Scenario modelling for UK motor bodily injury claims under whiplash reform uncertainty — Taylor separation, severity distributions, and conformal prediction intervals.
25 Mar 2026

Detecting Model Decay: Gini Drift Testing with Statistical Power

The first Python implementation of the asymptotic Gini drift test from Brauer et al. (2025). A proper z-test for ranking degradation — not a heuristic, not a threshold, a p-value.
25 Mar 2026

FCA Pure Protection Market Study: What Pricing Teams Should Prepare For

The FCA's interim report on MS24/1 landed in January 2026 with a Q3 2026 final report expected. Here is what pure protection pricing teams need to build before that lands.
25 Mar 2026

What FCA EP25/2 Actually Shows: Cost-Push, Not Regulation, Drove UK Insurance Inflation

FCA EP25/2 published July 2025. Expected claim costs per home policy up 49% from £92 to £138. Average inception premium up only 5%. The data says insurers absorbed the shock — n...
25 Mar 2026

What Can I Change to Lower My Premium? The Consumer Duty Obligation Most Pricing Teams Are Ignoring

FCA Consumer Duty PRIN 2A requires insurers to tell policyholders what they can change to get a better outcome. Most pricing teams have not built this. insurance-recourse does i...
25 Mar 2026

FCA AI Evaluation 2026: What the Regulator Is Looking at

The FCA has committed to evaluating how UK insurers use AI in pricing, underwriting, and claims. No new AI-specific rulebook is coming — but the regulator now expects evidence, ...
25 Mar 2026

The FCA's First Consolidated Insurance Priorities: What Pricing Teams Need to Do Now

The FCA replaced 40+ portfolio letters with a single annual priorities document on 24 February 2026. Here is what it says, what it means for pricing teams, and which library too...
25 Mar 2026

Fair Pricing in Long-Term Insurance: What arXiv:2602.04791 Means for UK Actuaries

A February 2026 paper from Lim, Xu, and Zhou cracks open the problem of fair pricing in multi-state insurance products — the ones that matter most for Consumer Duty obligations ...
25 Mar 2026

EU AI Act August 2026: What Your Pricing Team Must Do

Life and health insurance pricing models are high-risk AI under Annex III of the EU AI Act. General insurance (motor, home) may also be in scope but the classification is not ex...
25 Mar 2026

Embedded Insurance Pricing and the API Underwriting Model

BCG's 2025 analysis puts embedded insurance at 30% CAGR. The pricing architecture question is not whether to do it - it's whether your model can answer in under 100ms without co...
25 Mar 2026

Discrimination-Insensitive Pricing: Beyond Removing the Protected Variable

insurance-fairness v0.6.3 ships DiscriminationInsensitiveReweighter. Here's why dropping the protected column doesn't work, how propensity-based reweighting does, and what the A...
25 Mar 2026

Consumer Duty Outcomes Monitoring: What Data to Collect and What to Report

The FCA's first full outcomes monitoring year under Consumer Duty is under way. Here is what data to collect, what the regulator actually wants to see in MI, and how insurance-g...
25 Mar 2026

Consumer Duty Fair Value Evidencing: A 12-Step Technical Checklist for Pricing Actuaries (2026)

EP25/2 (the FCA's evaluation of GIPP price-walking remedies) flags ongoing fair value supervision in motor and home. No single technical checklist exists for the pricing actuary...
25 Mar 2026

Algorithmic Pricing on PCWs: The Collusion Risk Nobody Is Talking About

arXiv:2504.16592 formalises what pricing teams have been quietly observing for years: autonomous pricing algorithms can converge to supra-competitive prices without any firm eve...
24 Mar 2026

Stop Peeking at Your A/B Test — Or Use a Test That Doesn't Care

Every insurance team checks their champion/challenger results monthly. Every month you look, you inflate the false positive rate. Here is how to do it correctly using sequential...
24 Mar 2026

Sequential A/B Testing for Insurance Champion/Challenger Experiments

Monthly peeking at champion/challenger results with a t-test inflates your false positive rate to ~25%. The mixture SPRT (Johari et al. 2022) is an e-process: valid at every int...
24 Mar 2026

What FCA PS25/21 Actually Means for Your Pricing Team

PS25/21 abolished the mandatory 12-month product review cycle in December 2025. Harm-proportionate review cadence is now the requirement. Here is what that means for actuarial g...
24 Mar 2026

LLM Feature Engineering for Insurance Pricing: What the Research Actually Shows

What large language models can genuinely contribute to insurance pricing feature engineering — text embeddings, zero-shot classification, synthetic features — and where the evid...
24 Mar 2026

GLM, GAM, and GBM for UK Motor Pricing in Python

The Python equivalent of the IFoA MLR Working Party's R tutorial: Poisson GLM baseline, EBM GAM, and CatBoost GBM on UK motor data, with the full pipeline from data to governance.
24 Mar 2026

Safe Model Deployment for Insurance Pricing: Champion/Challenger with a Full Audit Trail

insurance-deploy provides the champion/challenger infrastructure, audit trail, and ICOBS 6B compliance tooling that MLflow does not. Here is how to use it.
23 Mar 2026

Motor Model Mispricing Caught by Monitoring: A Case Study

A UK motor frequency model drifts after an upstream vehicle group reclassification. We show how insurance-monitoring's PSI, A/E ratios, and Gini drift test caught the problem be...
23 Mar 2026

Exposure-Weighted Gini Coefficient in Python

Exposure-weighted Gini for insurance pricing: correct formula, Python implementation, and why ignoring exposure distorts motor model governance.
22 Mar 2026

Three Ways to Detect Proxy Discrimination in Your Pricing Model: When They Agree and When They Don't

Mutual information, proxy R-squared, and SHAP proxy scores all flag proxy discrimination but catch different things. A practical guide to interpreting conflicting signals in ins...
22 Mar 2026

Python Insurance Pricing Cookbook: 20 Recipes for Common Tasks

20 short code recipes for common insurance pricing tasks. Each recipe uses a real API from one of our open-source libraries. Copy and adapt.
22 Mar 2026

Insurance Model Monitoring in Python: Gini, A/E, and Double-Lift

Tutorial on monitoring insurance pricing models using actuarial KPIs. Gini tracking, segmented A/E, double-lift for champion/challenger. Why generic drift tools miss what matters.
22 Mar 2026

Why Evidently Isn't Enough for Insurance Pricing Model Monitoring

Evidently is excellent for generic ML monitoring. It doesn't do exposure-weighted PSI, Poisson A/E ratios, Gini drift testing, or anytime-valid sequential tests. For UK insuranc...
22 Mar 2026

GLMs for UK Insurance Pricing in Python: What the Generic Tutorials Miss

GLM insurance Python for UK pricing actuaries: exposure handling, Consumer Duty, frequency-severity split, and Emblem/Radar deployment with glum.
22 Mar 2026

FCA Proxy Discrimination Testing in Python: A Practical Guide

Under Consumer Duty and the Equality Act 2010, non-life insurers must test whether rating factors act as proxies for protected characteristics. Here is exactly how to run that t...
21 Mar 2026

NannyML vs insurance-monitoring: Drift Detection Built for Insurance Portfolios

NannyML is the best general-purpose ML monitoring library for teams without ground truth labels. For insurance pricing, it doesn't do exposure-weighted PSI, segmented A/E ratios...
21 Mar 2026

Insurance Model Monitoring in Python: Beyond Generic Data Drift

Insurance model monitoring in Python that understands exposure weighting, development lags, and Gini drift. Why Evidently and NannyML miss what matters for pricing, and what ins...
20 Mar 2026

FCA Consumer Duty Pricing Fairness in Python

The FCA expects pricing teams to demonstrate their models don't proxy-discriminate under Consumer Duty. Most teams do this in Excel. Here is how to do it properly in Python, usi...
20 Mar 2026

Fairness Auditing When You Don't Have Sensitive Attributes

Most UK insurers don't hold ethnicity, religion, or disability status. Consumer Duty still requires evidence of fair outcomes. PrivatizedFairnessAudit solves this with local dif...
20 Mar 2026

Fairlearn vs insurance-fairness: Why Generic ML Fairness Tools Miss What the FCA Cares About

Fairlearn is excellent for classification fairness. It was not built for insurance pricing, the Equality Act 2010, or the FCA's specific concern: proxy discrimination in a multi...
19 Mar 2026

The FCA Is Investigating Home and Travel Insurers: Is Your Pricing Model Defensible?

Active Consumer Duty investigations in home and travel insurance. What a defensible pricing model actually requires under PRIN 2A, and what the FCA thematic review said about mo...
19 Mar 2026

EquiPy vs insurance-fairness: Two Different Questions About Fairness in Insurance Pricing

EquiPy is a technically excellent fairness correction tool built on optimal transport theory, from Arthur Charpentier's group at UQAM. insurance-fairness is an FCA-focused proxy...
18 Mar 2026

Alibi Detect vs insurance-monitoring: Drift Detection for Insurance Pricing Models

Alibi Detect is a solid general-purpose drift detection library. It doesn't do exposure-weighted PSI, segmented A/E ratios, Gini discrimination drift, or Lloyd's MRM framework r...
17 Mar 2026

Champion/Challenger Testing That Satisfies the SMF Holder: Routing, Logging, and Bootstrap Power Analysis

Champion/challenger testing is the right way to evaluate pricing model changes. Most teams do it badly or not at all - ad-hoc scripts, no audit trail, no...
16 Mar 2026

Importance-Weighted Evaluation for Portfolio Composition Shift: Diagnosing the Mismatch Before It Shows in Loss Ratios

Density ratio correction for portfolio composition shift - CatBoost classifier, importance-weighted evaluation, insurance-covariate-shift library
16 Mar 2026

The EBM Is Sitting in Your Notebook Because You Can't Show It to the Committee

GLMComparison and MonotonicityEditor in insurance-gam close the governance gap between EBM shape functions and the GLM factor table your pricing committee...
15 Mar 2026

BYM2 Territory Modelling: Posterior Uncertainty Intervals and Year-on-Year Stability from Spatial Smoothing

Two things independent credibility cannot give you: a quantified uncertainty per sector, and stable factors year-on-year.
15 Mar 2026

Monthly Covariate Shift Monitoring: When to Reweight and When to Retrain

How to run covariate shift detection as a recurring monthly check: monitoring cadence, ESS ratio trends, and the thresholds that trigger a retraining...
15 Mar 2026

Debiasing Price Elasticity Estimates with Double Machine Learning: Removing the Risk Model's Fingerprint

OLS elasticity in formula-rated books is contaminated by your own risk model. insurance-causal fixes this with CausalForestDML and CatBoost nuisance.
14 Mar 2026

One Package, One Install: PRA SS1/23 Validation and MRM Governance Unified

insurance-governance merges insurance-validation and insurance-mrm. PRA SS1/23 statistical validation and MRM governance in one install - no version conflicts.
14 Mar 2026

OLS Elasticity in a Formula-Rated Book Measures the Wrong Thing

CausalForestDML separates causal price effect from risk-lapse correlation in UK motor renewal. insurance-elasticity - per-customer CATE and ENBP optimiser.
13 Mar 2026

Synthetic Difference-in-Differences for Rate Change Evaluation

DiD and Callaway-Sant'Anna for rate change attribution. insurance-causal-policy quantifies what your rate change actually achieved, with FCA Consumer Duty-aligned evidence output.
13 Mar 2026

Model Risk Governance for UK Insurers: Beyond the Excel Register

Model risk governance for UK insurers: model inventory, risk tier scoring, exec committee reports. Built on SS1/23 principles (formally a banking standard, widely adopted by ins...
13 Mar 2026

Actuarial Neural Additive Models: Exact Interpretability with Tweedie Loss

Actuarial Neural Additive Models for UK pricing: exact interpretability, Tweedie loss, guaranteed monotonicity. insurance-gam - beyond SHAP and EBM limitations.
13 Mar 2026

Champion/Challenger Testing with ICOBS 6B.2.51R Compliance

Champion/challenger with ICOBS 6B.2.51R compliance for UK insurers. SHA-256 routing, SQLite logging, bootstrap LR tests, SMF-signable report - insurance-deploy.
13 Mar 2026

Pairwise Interaction Networks: The Model That Beats GBMs and Prints as a Relativities Table

Pairwise Interaction Networks produce exact tabulatable 2D rating factor surfaces, not SHAP approximations. Beats GBMs on French MTPL benchmark. Python.
13 Mar 2026

Frequency and Severity Are Two Outputs. You Have One Prediction Interval.

Joint conformal prediction sets for frequency and severity in UK insurance. Fan and Sesia coordinate-wise standardization - simultaneous coverage across both.
13 Mar 2026

Robust Rate Optimisation: Pricing Against Demand Model Misspecification

Distributionally robust rate optimisation: worst-case demand within a Wasserstein ball. Price-of-robustness curve for UK pricing committee papers - Python.
13 Mar 2026

When Did Your Loss Ratio Actually Change?

Bayesian Online Changepoint Detection for UK insurance loss ratios. Poisson-Gamma conjugates, regulatory event priors, Consumer Duty evidence pack - Python.
13 Mar 2026

Mixture Cure Models for Retention Pricing: Separating Structural Non-Lapsers from the At-Risk Book

Logistic regression treats all non-lapsers the same. Mixture cure models split them into two groups: structural non-lapsers who will never leave, and...
12 Mar 2026

Bandit Algorithms for GIPP-Compliant Price Experimentation

Bandit algorithms for FCA GIPP-compliant price experimentation in UK general insurance. ENBP constraints and compliance reporting built in - insurance-online.
12 Mar 2026

Heterogeneous Lapse Effects with Bayesian Causal Forests: Beyond the Average Elasticity

Bayesian Causal Forests for heterogeneous lapse effects in UK insurance pricing. Segment-level elasticity with posteriors - insurance-bcf wrapping stochtree.
12 Mar 2026

Continuous Treatment Causal Inference for Insurance Pricing: insurance-causal

Automatic Debiased ML via Riesz Representers for continuous price elasticity. insurance-causal - no GPS density blow-up at tails. UK personal lines Python.
11 Mar 2026

Survival Models for Insurance Retention

Survival models for UK personal lines retention: cure models, survival-adjusted CLV, actuarial lapse tables, MLflow deployment. What lifelines does not do.
11 Mar 2026

Does the Risk Actually Drop at 25? Using Regression Discontinuity to Test Your Age Threshold

Regression Discontinuity Design tests if UK motor risk drops at age 25. Exposure-weighted Poisson outcomes, geographic boundaries, Consumer Duty output.
10 Mar 2026

Rate Change Evaluation: Did the Premium Increase Cause the Lapses?

A 12% rate increase on young motor drivers. An 8% lapse spike three months later. Here is how to tell whether the rate change caused it — using synthetic difference-in-differences.
10 Mar 2026

Discrimination-Free Pricing in Python: Causal Paths, Optimal Transport, and the FCA

Discrimination-free UK insurance pricing via Wasserstein barycenter and causal path decomposition. Satisfies FCA Consumer Duty proxy discrimination rules.
09 Mar 2026

Why Generic Synthetic Data Fails Actuarial Fidelity Tests

Actuarially faithful synthetic data via vine copulas and AIC-selected marginals. insurance-synthetic fixes Poisson semantics and tail behaviour SDV gets wrong.
07 Mar 2026

Constrained Portfolio Rate Optimisation with FCA ENBP Enforcement

Constrained portfolio rate optimiser for UK personal lines: SLSQP, analytical Jacobians, FCA ENBP enforcement, shadow prices. Python - insurance-optimise.
06 Mar 2026

Density Ratio Detection for Channel Mix Drift: Correcting Predictions Before the Loss Ratio Reacts

When a new aggregator partnership or competitor exit changes your new business mix, models trained on the old distribution misprice silently.
04 Mar 2026

GLM Interaction Detection: A Six-Step Walkthrough with CANN, NID, and SHAP

Step-by-step tutorial: plant two interactions in synthetic motor data, detect them with CANN + NID, validate with SHAP, confirm with A/E surfaces, and...
03 Mar 2026

Proxy Discrimination in UK Motor Pricing: Detection and Correction

Detect and correct proxy discrimination in UK insurance using SHAP and insurance-fairness. Protected characteristic leakage detection under FCA Consumer Duty.
02 Mar 2026

How to Extract GLM-Style Rating Factors from a CatBoost Model

Step-by-step: extract multiplicative CatBoost rating factors using shap-relativities. SHAP decomposition to GLM-format exp(beta) tables with CI and...
01 Mar 2026

Double Machine Learning for Insurance Price Elasticity

Double Machine Learning fixes biased price elasticity in insurance quote data. insurance-optimise: conversion, retention, elasticity, demand curves, FCA GIPP.
28 Feb 2026

Blending GLMs and GBMs for UK Pricing: Cross-Validated Weights, Not a Choice Between Them

How to combine GLM and GBM predictions for production pricing: cross-validated blend weights, PRA interpretability, and when blending actually helps. Once the blended model is v...
28 Feb 2026

Recalibrate or Refit? The Murphy Decomposition Makes it a Data Question

Assumes familiarity with the Murphy decomposition framework. Focuses on the operational question: given a monitoring alert, how do you read GMCB vs LMCB...
13 Jul 2025

Your Model Validation Is a Checklist, Not a Test

PRA SS1/23 requires quantitative pass/fail tests, not narrative. insurance-governance automates the full validation suite and generates auditable HTML reports.