IFoA Workshop - AI for Actuaries · Dr Rohan Yashraj Gupta

Designed and led by Satya Sai Mudigonda, Rohan Yashraj Gupta and expert AI engineering mentors.

The Series

The series opened in Mumbai on 15 May 2026 at the Hilton near the airport, Gurugram on 10th July 2026 at Club 4, and continues in Bangalore on 24 and 25 July 2026 at Four Points by Sheraton, Whitefield.

Each edition runs as a day-long, hands-on programme — two live sessions of three hours each — followed by a mandatory two-week group case study with mentor-led online support. Attendance alone doesn't earn completion; building something does.

Why This Workshop Exists

AI is no longer adjacent to actuarial work — it is arriving inside it. Pricing teams are benchmarking GLMs against gradient-boosted trees. Reserving and reporting teams are experimenting with LLMs for documentation. Regulators — from the IFoA and the FRC to IRDAI, the NAIC, and the EU AI Act — are actively shaping how these models may be used in insurance.

Yet most actuaries face a practical gap: deep statistical training and strong GLM intuition, but limited hands-on exposure to Python, machine learning workflows, generative AI, and the emerging world of AI agents. Generic AI courses don't close this gap, because they aren't grounded in exposure, frequency–severity structures, fairness in pricing, or the professional duty to explain and sign off a model.

This workshop was built to close exactly that gap — by actuaries, for actuaries, with every example drawn from Life, Health, and General Insurance contexts. The response from the actuarial community made the case plainly: the Mumbai edition drew practicing actuaries from across insurers and consulting firms, and demand led directly to the Bangalore edition two months later.

What the Community Is Asking For

Practicing actuaries consistently raise the same needs, and the workshop is structured around them:

"I know GLMs — how do tree models actually compare?" Not in theory, but on a real pricing dataset, with an honest leaderboard.
"How do I explain a machine learning price to my chief actuary, my regulator, and my customer?"Interpretability (SHAP), fairness, and governance are treated as first-class topics, not afterthoughts.
"Can GenAI actually help with documentation and reporting — safely?" Hands-on prompt engineering with clear guardrails on confidentiality and validation.
"What is an AI agent, really — and could I build one?" Every participant watches one built live, then builds their own in the case study.

Session 1 — AI Foundations & Predictive Modeling

Lectures + guided Python walkthroughs + discussion (3 hours)

AI in actuarial work — where actuaries and AI meet across pricing, claims, fraud, and operations, illustrated with documented industry case studies (Lemonade's AI-driven quoting and claims, John Hancock's Vitality programme, Tractable's photo-based motor damage assessment)
Tools and data foundations — Python via Google Colab (no local installs), NumPy, pandas, scikit-learn; the anatomy of insurance data: policies, exposure, frequency and severity
Predictive modelling — GLMs implemented in statsmodels, then Random Forests and XGBoost on the same book; evaluation with MAE, RMSE, AUC, and actuarial lift charts
Interpretation and fairness — SHAP values for global and local explanation, proxy discrimination, and the regulatory landscape: IFoA professional standards, IRDAI, NAIC's AI Model Bulletin, Colorado SB21-169, and the EU AI Act

All modelling runs on a purpose-built hypothetical insurer — ABC Insurer, with motor, health, and life datasets in INR — so every participant works with data that looks like their day job.

Session 2 — GenAI & AI Agents

Conceptual overviews + guided demos + live coding (3 hours)

Generative AI for actuaries — what LLMs can and cannot do, hallucinations and why actuaries must care, confidentiality discipline, and structured prompt engineering
GenAI tools in daily work — live demos producing risk-factor tables, underwriting guideline drafts, and board-pack summaries; a tour of copilots, chatbots, and AI IDEs
Introduction to AI agents — the difference between a chatbot and an agent; the ReAct pattern; tools, memory, and function calling; the framework landscape
Live "VIBE coding" showcase — an actuarial AI agent (a Pricing Logic Explainer) built live on stage: it takes rating logic as input, explains it in plain English, fails visibly when it hallucinates, and is fixed with a guardrail — because watching an agent break and get repaired teaches more than a polished demo ever could
Case study briefing — tracks, teams, deliverables, and evaluation

The Two-Week Case Study

Participants form teams of ~5 and choose one track:

Model Build & Interpretation — build and interpret statistical or ML models with illustrative factor tables or projections
Documentation with GenAI — produce model documentation, assumption summaries, and structured actuarial reports with LLM tooling
Build a Simple AI Agent — create a working agent that automates an actuarial task, such as a rating logic interpreter

Final submissions include a Python notebook, documentation, and an executive summary — with mentor support available throughout the fortnight.

What Participants Leave With

The ability to apply AI techniques inside actuarial workflows, not alongside them
Confidence to interpret and validate predictive models — and to defend that interpretation to a signing actuary or a regulator
Practical fluency in using GenAI for reporting and documentation with appropriate professional scepticism
A working understanding of AI agents — and the experience of having built one
A complete take-home kit: Colab notebooks that run end-to-end, prompt templates, agent design templates, and recordings

Design Principles Behind the Programme

A few things distinguish this workshop from a generic AI course:

Practitioner-first. Every concept answers "what does an actuary do with this on Monday morning?"
Honest over impressive. Model comparisons report what the data shows — including where the humble GLM holds its own against XGBoost.
Rigorous sourcing. Every industry claim traces to public filings, peer-reviewed papers, or regulator publications. No recycled AI hype.
All three lines of business. Worked examples rotate deliberately across Life, Health, and General Insurance so no participant feels the material was written for someone else.
Zero setup friction. Everything runs in Google Colab on free tiers — participants code within minutes, not after an afternoon of installs.

Faculty

Satya Sai Mudigonda — Chairman, Sri Sathya Sai Institute of Actuaries. Tech-actuarial consultant with over three decades of experience across the US and India in AI/ML applications, analytics, and actuarial modelling.

Dr Rohan Yashraj Gupta, FIA, FIAI — GI Actuary at Accenture and Adjunct Faculty. Qualified General Insurance actuary with over eight years of experience, specialising in agentic AI, InsurTech, and actuarial automation. Workshop designer and lead presenter.

Expert AI engineering mentors — each edition is supported by a lead AI engineer as co-faculty and case-study mentor, bringing production AI systems expertise to complement the actuarial perspective.

Offered by the Institute and Faculty of Actuaries (IFoA) · actuaries.org.uk