Credit Risk Analytics Training Course

Duration 5 days 10 modules · 33 contact hours
Level Intermediate Certificate on completion
Who attends Credit Risk Analyst, Credit Risk Manager and others
Fee from USD 1,100 KSh 95,000 for Kenyan organisations
Where 52 cities + online See dates by city
Next start 7 Nov 2026 Course code SD-RM-039

Before you join: Participants should understand basic lending concepts, including loans, arrears, collateral, interest and credit approval.

Dates & prices

Two start dates a month in every city, and live online on weekdays or weekends. Fees are per participant; classroom fees include tuition, materials, lunch and refreshments, and the certificate.

Suggest a date or city

Showing the next six months. Later dates, other cities and private deliveries for your team are available on request.

Course overview

Credit risk teams need to turn loan, customer, collateral and repayment data into decisions that protect portfolio quality while supporting profitable lending. This requires more than reporting delinquency rates. Analysts must define default consistently, prepare reliable datasets, estimate probability of default (PD), loss given default (LGD) and exposure at default (EAD), test model performance, and explain results to credit committees, finance teams and regulators. Poor data definitions, untested assumptions and weak monitoring can lead to mispriced loans, inadequate impairment allowances, unexpected losses and delayed management action.

This course teaches the analytical methods used to measure, model and monitor credit risk across retail, SME and corporate lending portfolios. Participants work through credit risk data structures, cohort and vintage analysis, scorecard development, logistic regression, PD calibration, LGD and EAD estimation, IFRS 9 expected credit loss, Basel capital measures, stress testing and portfolio concentration analysis. The course also addresses model validation, fairness considerations, decision rules, risk-based pricing and management reporting.

Instruction combines practitioner briefings with case analysis, group work, simulations and guided use of credit risk datasets. Participants apply methods to realistic lending situations, including deteriorating arrears performance, changing economic scenarios and model-monitoring exceptions. They leave with a reusable credit risk analytics workbook structure, model-monitoring checklist, expected-loss calculation model and a 90-day application plan. The five-day instructor-led course is available in classrooms in 50+ cities or live online, with a certificate of completion issued to participants who complete the course.

The course is suited to professionals who already work with lending, risk, finance, collections or customer data and need stronger analytical capability for credit risk decisions.

What you will be able to do

  • Construct credit risk datasets using documented definitions, data lineage and quality controls
  • Analyse delinquency, vintage, migration and survival patterns within lending portfolios
  • Develop and assess logistic regression scorecards using discrimination and calibration measures
  • Estimate PD, LGD and EAD inputs for expected-loss and capital calculations
  • Calculate IFRS 9 expected credit losses using staging and scenario-weighted assumptions
  • Validate credit risk models through back-testing, stability testing and governance evidence
  • Evaluate portfolio concentration, migration and stress-test results for management action
  • Produce credit risk dashboards, exception reports and a practical analytics application plan

Benefits of attending

For you

  • Apply recognised PD, LGD and EAD concepts in lending and impairment work
  • Interpret scorecard performance using Gini, KS, calibration and stability measures
  • Build clearer evidence for credit policy and portfolio review discussions
  • Identify data quality weaknesses that can distort expected-loss estimates
  • Prepare for broader responsibilities in credit risk, model risk or portfolio management

For your organisation

  • More consistent credit risk analysis across underwriting, finance and collections teams
  • Earlier identification of deteriorating segments through vintage and migration monitoring
  • Better support for IFRS 9 impairment estimates and scenario documentation
  • Stronger model governance evidence for validation, audit and committee review
  • Clearer risk-based decisions on pricing, limits, referrals and collection priorities

Course modules

10 modules over 5 days

Participants can explain the principal credit risk measures and connect them to lending decisions, impairment and portfolio profitability.

  • Credit risk decisions linked to default, loss, exposure and profitability
  • Basel credit risk parameters: PD, LGD, EAD and maturity
  • IFRS 9 staging, significant increase tests and expected credit loss
  • Point-in-time versus through-the-cycle estimates for lending decisions
  • Retail, SME and corporate portfolios compared through risk drivers
  • Risk appetite metrics translated into portfolio limits and referral rules

Participants can prepare credit risk data for analysis using documented definitions, reconciliations and quality tests.

  • Data lineage from source systems to approved analytical datasets
  • Define observation windows, performance windows and target outcomes
  • Missing-value treatment documented using business rules and reason codes
  • Outlier detection with winsorisation, capping and investigation thresholds
  • Reconcile loan balances, delinquency status and customer identifiers
  • Population stability index identifies material shifts between development and monitoring samples

Participants can identify emerging credit deterioration through cohort, arrears, migration and default analysis.

  • Construct default definitions using 90-days-past-due and unlikeliness-to-pay criteria
  • Build vintage, roll-rate and migration analyses from monthly account histories
  • Calculate delinquency rates by origination cohort, segment and seasoning
  • Kaplan-Meier survival curves estimate time-to-default patterns for borrower segments
  • Identify cure, relapse and write-off transitions within arrears data
  • Compare observed defaults with policy thresholds and prior forecasts

Participants can develop, interpret and assess a probability of default scorecard.

  • Select predictive variables using business rationale, stability and availability
  • Transform continuous predictors through binning, weight of evidence and monotonicity
  • Fit logistic regression scorecards and interpret coefficient signs
  • Assess discrimination using ROC curves, Gini coefficient and KS statistic
  • Calibrate predicted probabilities to observed default rates by grade
  • Set cut-offs using approval, bad-rate and profitability trade-offs

Participants can estimate loss given default and exposure at default assumptions for expected-loss calculations.

  • Estimate downturn LGD from recoveries, costs, collateral and cure rates
  • Separate realised LGD, economic loss and regulatory downturn adjustments
  • Model credit conversion factors for undrawn commitments and utilisation
  • Segment EAD estimates by product, limit structure and borrower behaviour
  • Discount recovery cash flows using effective interest rate conventions
  • Reconcile PD, LGD and EAD assumptions within expected-loss calculations

Participants can calculate and explain expected credit loss estimates under IFRS 9 and relate them to Basel measures.

  • Calculate twelve-month and lifetime expected credit losses under IFRS 9
  • Assign Stage 1, Stage 2 and Stage 3 exposures using documented criteria
  • Translate macroeconomic scenarios into forward-looking PD and LGD adjustments
  • Probability-weight alternative scenarios within impairment allowance estimates
  • Contrast regulatory capital expected loss with accounting impairment measures
  • Trace Basel risk-weighted asset inputs to portfolio-level capital consumption

Participants can assess credit model performance and document validation evidence for model risk governance.

  • Design development, validation and approval roles under model risk governance
  • Test discrimination, calibration, stability and sensitivity against validation criteria
  • Back-test predicted default rates using binomial confidence intervals
  • Apply traffic-light thresholds to model performance monitoring results
  • Challenge overrides, expert judgement and data limitations through documented review
  • Maintain model inventory, change logs and validation evidence

Participants can assess portfolio risk drivers, concentration exposures and stress-test outcomes.

  • Measure concentration by obligor, sector, geography and rating grade
  • Calculate expected loss, unexpected loss and risk-adjusted return
  • Use migration matrices to project rating movements and portfolio quality
  • Stress unemployment, interest rates and property prices through scenario analysis
  • Compare segment performance using vintage curves, loss rates and yield
  • Prioritise collections strategies using arrears stage, propensity and exposure

Participants can translate credit analytics into controlled approval, pricing and account-management decisions.

  • Build scorecard decision matrices for approve, decline and refer outcomes
  • Set risk-based pricing using expected loss, costs and target return
  • Design challenger models and controlled tests for policy changes
  • Analyse fairness metrics and prohibited-basis risk in credit decisions
  • Document adverse-action reason codes from model inputs and decision rules
  • Link early-warning indicators to account management and collections actions

Participants can communicate credit risk results through decision-focused reporting and a prioritised improvement plan.

  • Create portfolio dashboards with risk appetite, losses, migration and concentration
  • Specify monthly monitoring packs for committees, finance and business leaders
  • Escalate breaches using thresholds, ownership, actions and closure dates
  • Present model limitations, uncertainty and scenario assumptions to non-specialists
  • Prioritise data, model and policy improvements using materiality assessment
  • Draft a 90-day credit analytics application plan with named actions

Exercises and examples are adapted to each cohort's sectors and roles.

What you take back to work

  1. Credit risk data dictionary template
  2. PD scorecard assessment model
  3. IFRS 9 expected-loss calculation template
  4. Credit model validation checklist
  5. Portfolio stress-testing analysis template
  6. 90-day credit analytics application plan

Who should attend

  • Credit Risk Analyst — needs stronger methods for portfolio analysis, modelling and monitoring
  • Credit Risk Manager — needs evidence for policy, limits, impairment and committee decisions
  • Financial Analyst — supports expected credit loss, provisioning and portfolio performance reporting
  • Credit Underwriter — needs data-led insight for approval, referral and pricing decisions
  • Collections Manager — needs arrears segmentation and early-warning analysis for treatment strategies
  • Internal Auditor — reviews model governance, data controls and credit risk reporting evidence

Skills and tools covered

Credit risk modellingExpected loss estimationPortfolio stress testingModel performance validationCredit data qualityRisk reporting

Tools and standards

IFRS 9, Basel III

How the course runs

Training methodology

The course uses short instructor briefings to introduce credit risk methods, followed by case work using realistic lending data. Participants interpret portfolio trends, review scorecard outputs, calculate expected losses and assess model-monitoring results in small groups. Simulations examine deteriorating arrears, macroeconomic shocks and credit policy changes. Facilitated discussions focus on assumptions, data limitations and management judgement. Each participant develops an application plan that identifies relevant data sources, reporting needs and priority improvements for their own role.

Requirements and prerequisites

Participants should understand basic lending concepts, including loans, arrears, collateral, interest and credit approval. Familiarity with spreadsheets and simple descriptive statistics, such as averages, percentages and trend analysis, is assumed. Experience working with credit, finance, collections or customer data is helpful. Participants do not need prior experience with Python, SQL, statistical programming, logistic regression or formal credit model development. The course explains the purpose and interpretation of these methods before applying them to credit risk cases.

A typical training day

08:30 – 10:30First session
10:30 – 10:45Refreshment break
10:45 – 12:30Second session
12:30 – 13:30Lunch and networking
13:30 – 15:00Third session
15:00 – 15:15Refreshment break
15:15 – 16:30Workshop and daily review

Live online deliveries follow the same structure in East Africa Time, with shorter screen blocks and longer breaks.

What the fee includes

  • Instruction by a practitioner facilitator
  • Full course workbook and materials
  • Exercise files, templates and case studies
  • Refreshments and lunch on classroom deliveries
  • Certificate of completion
  • Post-course application plan

Frequently asked questions

Participants should understand basic lending, arrears and spreadsheet concepts. Prior statistical modelling, Python, SQL or credit model development experience is not required.

Bring a laptop with spreadsheet software if attending in person, along with examples of credit risk questions from your role. No confidential customer data should be brought into the classroom or live online sessions.

The course is designed for credit risk, finance, underwriting, collections, portfolio management and internal audit professionals. It is particularly relevant to people who interpret lending data or contribute to credit decisions.

Credit underwriting courses focus mainly on individual borrower assessment and approval judgement. This course focuses on portfolio data, credit risk parameters, scorecards, expected loss, model validation and monitoring.

Participants can improve portfolio reporting, review data definitions, assess scorecard outputs and support impairment or policy discussions. The application plan helps them identify actions that fit their current data, systems and responsibilities.

Each day runs from 08:30 to 16:30 and provides about 6.5 contact hours. Time is divided between instructor input, analysis of lending cases, group exercises, simulations and application planning across the ten modules.

Questions about this course?

Ask about dates, fees, group bookings or running it for your team. Our training team replies by email.

Ask on WhatsApp info@skillsetdevelopment.com

Related courses in Risk Management