IFoA SA10 case studies
IFoA SA10 · Put your knowledge to work in context.
SA10 Data Science is a Specialist Advanced subject in the Institute and Faculty of Actuaries (IFoA) qualification pathway. The IFoA describes itself as the professional body whose curriculum pages hold "All the information you need under our current curriculum", with exams pages holding "Key info for exams including dates and essential resources". SA10 sits within the Specialist Advanced stage, which candidates typically reach after the Core Principles and Core Practice subjects, and it is aimed at actuaries who want to apply data science techniques to insurance, pensions and wider financial work rather than treat modelling as a purely technical exercise. Study should combine statistical and machine learning theory with applied judgement: model selection and validation, data quality and governance, communicating uncertainty to non-technical stakeholders, and the professional and ethical questions that arise when models influence decisions about individuals. The IFoA SA10 case studies are 5 cases and about 2,667 words.
1Motor renewal pricing: GLM versus gradient boosting
A UK motor insurer has 750,000 policy-years of private car exposure and 12,000 claims. The pricing team fits a Poisson GLM with 18 factors and 6 interactions; the current GLM has a scaled deviance of 0.83 and is used for renewal quotes.
572 words, about 3 min2NLP claims triage and vulnerable customers
An insurer's claims operations receive about 45,000 motor claim narratives each month. A vendor's NLP model assigns each notification a severity score and routes the top 15% to specialist handlers.
537 words, about 3 min3Non-disclosure scoring using commercial bureau data
A life insurer is developing a non-disclosure risk model for new protection applications. The model combines application data with a commercial data bureau that aggregates social-media activity, address stability and online retail behaviour.
551 words, about 3 min4Feature leakage and reproducibility in a claims severity model
An actuarial data science team is building a feature pipeline for a household claims severity model. The repository contains 14 Jupyter notebooks, 320 engineered features and no versioned training data.
505 words, about 3 min5Neural network reserving for bodily injury claims
A general insurer is replacing its chain-ladder reserving process for bodily injury with a neural network. The dataset has 18,000 claims, 60 development months and 1.2% of claims above £1m.
502 words, about 3 min