PracHub
QuestionsCoachesLearningGuidesInterview Prep
|Home/Machine Learning/Citibank

Identify top exposures and mitigate

Last updated: Mar 29, 2026

Quick Overview

Identify top exposures and mitigate 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.

  • medium
  • Citibank
  • Machine Learning
  • Data Scientist

Identify top exposures and mitigate

Company: Citibank

Role: Data Scientist

Category: Machine Learning

Difficulty: medium

Interview Round: Technical Screen

Identify the top five risk exposures in the portfolio and propose specific mitigation actions (e.g., collateral adjustments, covenants, limits, hedging, pricing changes). Justify each recommendation with quantitative and qualitative evidence.

Quick Answer: Identify top exposures and mitigate 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.

Related Interview Questions

  • Diagnose and fix linear regression assumption breaks - Citibank (medium)
  • Handle missing values for LGD modeling - Citibank (medium)
  • Discuss logistic regression limitations for PD - Citibank (medium)
  • Compute EL and RWA from loan data - Citibank (medium)
  • Explain PD model validation steps - Citibank (medium)
|Home/Machine Learning/Citibank

Identify top exposures and mitigate

Citibank logo
Citibank
Jul 26, 2025, 12:00 AM
mediumData ScientistTechnical ScreenMachine Learning
2
0

Identify top exposures and mitigate

Portfolio Risk Identification and Mitigation Proposal

Context

You are evaluating a commercial/corporate lending portfolio. Assume you have loan-level data with: obligor ID, sector/industry, region, facility type, exposure at default (EAD), probability of default (PD, 12m), loss given default (LGD, downturn), maturity, collateral type and loan-to-value (LTV), rate type (fixed/floating), coupon/spread, covenant quality score, rating, and historical performance. You can run simple stress scenarios (e.g., GDP −2%, rates +300 bps, CRE prices −20%).

No raw dataset is provided; make reasonable, clearly stated assumptions. Use small numeric examples to justify your decisions.

Task

  1. Identify the top five risk exposures in the portfolio (e.g., single-name concentration, sector/geography, collateral/LTV risk, covenant risk, interest-rate sensitivity, refinancing walls, FX mismatch, etc.).
  2. For each exposure, propose specific mitigation actions (e.g., collateral adjustments, covenants, limits, hedging, pricing changes, sell-down/participations, risk transfer).
  3. Justify each recommendation with quantitative and qualitative evidence (e.g., EL/UL/EC contributions, stress impacts, concentration indices, industry outlook), including formulas or small numeric examples where helpful.
  4. State any assumptions and describe how you would validate the effect of your mitigations (monitoring, backtests, scenario 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?
Loading comments...

Browse More Questions

More Machine Learning•More Citibank•More Data Scientist•Citibank Data Scientist•Citibank Machine Learning•Data Scientist Machine Learning

Write your answer

Your first approved answer each day earns 20 XP.

Sign in to write your answer.
PracHub

Master your tech interviews with 8,500+ real questions from top companies.

Product

  • Questions
  • Learning Tracks
  • Interview Guides
  • Resources
  • Premium
  • For Universities

Browse

  • By Company
  • By Role
  • By Category
  • Topic Hubs
  • SQL Questions
  • AI Coding Questions
  • Compare Platforms
  • Discord Community

Support

  • support@prachub.com
  • (916) 541-4762

Legal

  • Privacy Policy
  • Terms of Service
  • About Us

© 2026 PracHub. All rights reserved.