How do I approach Machine Learning interview questions?

Machine Learning questions require understanding of core concepts and practice. PracHub provides solutions with explanations to help you master machine learning interviews.

What difficulty level is this interview question?

This is a medium difficulty Machine Learning question, commonly asked during Technical Screen rounds at Citibank.

What role is this question designed for?

This question is commonly asked for Data Scientist candidates at Citibank during technical interviews.

Compute EL and RWA from loan data | Citibank Interview Question

Quick Overview

Compute EL and RWA from loan data evaluates core ML concepts, assumptions, math intuition, training/evaluation trade-offs, and practical failure modes in a realistic interview setting. A strong answer states assumptions, handles edge cases, explains trade-offs, and shows how to validate the result clearly.

Compute EL and RWA from loan data

Task: Compute Portfolio EL and RWA from Loan-Level PD, LGD, EAD

Context

You are given an anonymized, loan-level dataset with at least the following fields per exposure:

PD: one-year probability of default (as a decimal, e.g., 0.01 for 1%)
LGD: loss given default under downturn conditions (decimal between 0 and 1)
EAD: exposure at default (currency units). For off-balance-sheet items, EAD should reflect credit conversion factors (CCFs), or you must compute EAD from committed/undrawn amounts and CCFs.

Compute:

Portfolio expected loss (EL)
Risk-weighted assets (RWA)

Also state:

Assumptions (regulatory approach, asset class, maturity, parameter floors)
Formulas used
Aggregation approach across loans
Treatment of off-balance-sheet exposures
Sensitivity and validation checks

Constraints & Assumptions

Preserve the scope, facts, inputs, and requested outputs from the prompt above.
If the prompt leaves a detail unspecified, state a reasonable assumption before relying on it.
Keep the answer interview-ready: concise enough to present, but concrete enough to implement or evaluate.

Clarifying Questions to Ask

Clarify the task, data shape, labels, constraints, and evaluation metric.
State assumptions behind the math or modeling technique you choose.
Connect theory to practical training, debugging, and deployment implications.

What a Strong Answer Covers

Correct definitions and formulas where the prompt requires them.
A practical explanation of how the method behaves on real data.
Trade-offs, failure modes, diagnostics, and mitigation strategies.
Evaluation choices that match the product or modeling objective.

Follow-up Questions

How would noisy labels, class imbalance, or distribution shift affect the answer?
What would you monitor after deployment?
Which baseline would you compare against first?

Quick Overview

Context

You are given an anonymized, loan-level dataset with at least the following fields per exposure:

PD: one-year probability of default (as a decimal, e.g., 0.01 for 1%)

LGD: loss given default under downturn conditions (decimal between 0 and 1)

EAD: exposure at default (currency units). For off-balance-sheet items, EAD should reflect credit conversion factors (CCFs), or you must compute EAD from committed/undrawn amounts and CCFs.

Compute:

Portfolio expected loss (EL)

Risk-weighted assets (RWA)

Also state:

Assumptions (regulatory approach, asset class, maturity, parameter floors)

Formulas used

Aggregation approach across loans

Treatment of off-balance-sheet exposures

Sensitivity and validation checks

Constraints & Assumptions

Preserve the scope, facts, inputs, and requested outputs from the prompt above.

If the prompt leaves a detail unspecified, state a reasonable assumption before relying on it.

Keep the answer interview-ready: concise enough to present, but concrete enough to implement or evaluate.

Clarifying Questions to Ask

Clarify the task, data shape, labels, constraints, and evaluation metric.

State assumptions behind the math or modeling technique you choose.

Connect theory to practical training, debugging, and deployment implications.

What a Strong Answer Covers

Correct definitions and formulas where the prompt requires them.

A practical explanation of how the method behaves on real data.

Trade-offs, failure modes, diagnostics, and mitigation strategies.

Evaluation choices that match the product or modeling objective.

Follow-up Questions

How would noisy labels, class imbalance, or distribution shift affect the answer?

What would you monitor after deployment?

Which baseline would you compare against first?

Compute EL and RWA from loan data

Quick Overview

Compute EL and RWA from loan data

Compute EL and RWA from loan data

Task: Compute Portfolio EL and RWA from Loan-Level PD, LGD, EAD

Context

Constraints & Assumptions

Clarifying Questions to Ask

What a Strong Answer Covers

Follow-up Questions

Write your answer

Compute EL and RWA from loan data

Quick Overview

Compute EL and RWA from loan data

Compute EL and RWA from loan data

Task: Compute Portfolio EL and RWA from Loan-Level PD, LGD, EAD

Context

Constraints & Assumptions

Clarifying Questions to Ask

What a Strong Answer Covers

Follow-up Questions

Write your answer