Udemy
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
Risk Analytics, Financial Crime & Actuarial Analytics
Rating: 4.3 out of 5(35 ratings)
312 students

Risk Analytics, Financial Crime & Actuarial Analytics

Credit Risk, Financial Crime, Fraud Detection, Actuarial Models, IFRS 9, Basel, AML, Insurance Pricing & Python
Created byPius Dave
Last updated 10/2026
English

What you'll learn

  • Build credit risk models using PD, LGD, EAD, scorecards, WOE, IV, logistic regression, machine learning and model validation techniques.
  • Apply IFRS 9, Basel RWA, portfolio risk, concentration risk, stress testing and credit risk analytics to real-world financial problems.
  • Design fraud and AML analytics using transaction data, rules, machine learning, anomaly detection, graph analytics and entity resolution.
  • Apply actuarial analytics to mortality, survival, insurance pricing, reserving, risk theory, longevity, solvency and capital modelling.

Explore related topics

Course content

5 sections • 89 lectures • 16h 4m total length

  • Course Introduction4:25
  • Credit Risk Analytics1:39
  • Financial Crime & AML Analytics1:37
  • Actuarial Analytics1:32

Requirements

  • Basic knowledge of probability, statistics and financial concepts is recommended, but key concepts are explained throughout the course.
  • Basic Python knowledge is helpful for following the analytics and machine learning implementations.
  • A computer with Python and commonly used data science libraries installed is recommended for practical exercises.
  • No prior professional experience in credit risk, AML or actuarial science is required; the course progresses from foundations to advanced applications.

Description

Build an end-to-end understanding of modern Risk Analytics with Python across banking, financial crime, insurance and actuarial applications.

This comprehensive course brings together three major areas of quantitative risk analytics: Credit Risk Analytics, Financial Crime & AML Analytics, and Actuarial Analytics.

You will learn how financial institutions use statistical modelling, machine learning, probability, data analytics and risk frameworks to transform raw financial data into measurable risk indicators and actionable decisions.

What You Will Learn

Credit Risk Analytics

  • Expected Loss using PD, LGD and EAD

  • Credit data preparation and exploratory analysis

  • WOE and Information Value

  • Logistic regression and credit scorecards

  • Gini, KS, PSI and model validation

  • PD calibration and master scales

  • LGD and EAD modelling

  • IFRS 9 Expected Credit Loss

  • Portfolio risk and concentration

  • ASRF and Basel RWA

  • Credit stress testing

  • Machine learning, SHAP and model governance

Financial Crime & AML Analytics

  • Financial crime data and transaction analytics

  • Feature engineering and transaction graphs

  • Benford's Law and statistical red flags

  • Rule-based fraud detection

  • Supervised machine learning for fraud

  • Anomaly and unsupervised detection

  • Network and graph analytics

  • Behavioural and sequence modelling

  • Sanctions and PEP screening

  • Entity resolution and beneficial ownership

  • Explainability, compliance and model governance

  • End-to-end AML and fraud detection systems

Actuarial Analytics

  • Actuarial mathematics and probability foundations

  • Survival analysis and mortality modelling

  • Life insurance and annuities

  • Pension and retirement analytics

  • General insurance loss models

  • Pricing and ratemaking

  • Claims reserving

  • Risk theory and ruin models

  • Risk measures and dependence

  • Machine learning for actuarial applications

  • Mortality forecasting and longevity risk

  • Solvency, capital and regulatory reporting

A Practical Analytics Approach

The course follows a common framework throughout:

Data → Feature Engineering → Statistical Model → Machine Learning → Validation → Explainability → Risk Measurement → Decision

Rather than learning individual techniques in isolation, you will see how analytical models fit into complete risk-management systems.

Who Is This Course For?

This course is designed for:

  • Risk Analysts and Credit Risk Professionals

  • Quantitative Analysts

  • Data Scientists working in Financial Services

  • Banking and Finance Professionals

  • Fraud and AML Analysts

  • Financial Crime Professionals

  • Actuarial Students and Professionals

  • Insurance Analytics Professionals

  • Financial Modelling Professionals

  • Students interested in Risk Analytics

  • Python professionals moving into finance and insurance analytics

A basic understanding of Python, statistics and financial concepts is helpful but the relevant concepts are developed throughout the course.

What Makes This Course Different?

Instead of focusing on only one risk domain, this program connects three important areas of financial analytics:

Credit Risk + Financial Crime + Actuarial Risk

This gives you a broader perspective on how quantitative analytics is applied across banking, financial crime, insurance and risk management.

You will work with concepts used in real-world financial and insurance analytics, including credit scoring, PD/LGD/EAD, IFRS 9, Basel RWA, fraud detection, AML analytics, graph models, mortality modelling, pricing, reserving and solvency.

By the end of the course, you will have a structured understanding of how to design and evaluate analytics-driven risk systems from data preparation through model development, validation and decision-making.

Who this course is for:

  • Finance, banking, risk and data professionals who want to develop practical skills across credit risk, financial crime and actuarial analytics.
  • Students, analysts, quantitative professionals, fraud and AML specialists, actuarial learners and data scientists interested in financial risk analytics.

Report abuse