Fin Maverick
QuarksCourses
PartnershipsShowdown
Log inSign up
Interview tracksAll
1Investment Banking
Question bankPuzzlesCase studies
2Equity Research
Question bankPuzzlesCase studies
3Venture Capital
Question bankPuzzlesCase studies
4Private Equity
Question bankPuzzlesCase studies
5Hedge Funds
Question bankPuzzlesCase studies
6Quant
Question bankPuzzlesCase studies
7Financial Analysis
Question bankPuzzlesCase studies
8Private Wealth Management
Question bankPuzzlesCase studies
9Debt Capital Markets
Question bankPuzzlesCase studies
10Risk Management
Question bankPuzzlesCase studies
11Derivatives Foundation
Question bankPuzzlesCase studies
12Portfolio Management
Question bankPuzzlesCase studies
13Mutual Fund Mastery
Question bankPuzzlesCase studies
055

Case 055Fixed income and creditCore

A lender's 12,000 personal loans sit in four score buckets with 30 defaults of 4,000, 60 of 4,000, 90 of 2,500 and 150 of 1,500. Compute default rates, 95% intervals and expected loss at 60% loss given default, and say whether the buckets are well ordered.

Jane StreetLondon · 2025

1The situation

Lakshyavar Finance, a consumer lender, sends you a take-home file of 12,000 personal loans made two years ago, each tagged with the application score bucket it fell into, A the best and D the worst, and whether it defaulted within a year.

Bucket A: 30 defaults out of 4,000 loans. Bucket B: 60 of 4,000. Bucket C: 90 of 2,500. Bucket D: 150 of 1,500. The average loan is Rs 2 lakh, and the credit team assumes 60% of a defaulted loan is lost after recoveries.

2Your task

Compute each bucket's default rate with a 95% confidence interval and its expected loss, and tell the credit team whether the score ranks risk reliably.

Quick check

Which pair of buckets is the hardest to tell apart statistically?

Worked solution

Try it on paper, then open one step at a time.

30-second answerThe answer to give first

The buckets are well ordered: default rates of 0.75%, 1.50%, 3.60% and 10.0% with 95% intervals that do not overlap. Expected loss is Rs 3.96 crore on Rs 240 crore of loans, 1.65%. Bucket D is one loan in eight but carries 45% of that loss. The smallest buckets have the widest intervals, and A against B is the closest call, still about 3.2 standard errors apart.

Step 1Why does a default rate need an interval at all?

Toss a fair coin 20 times and you might see 13 heads; nobody concludes the coin is biased. A default rate from a finite book is an estimate of a proportion, and its error shrinks only with the square root of the number of loans. The standard error is the square root of p times (1 - p) divided by n, and a 95% interval is the rate plus or minus 1.96 of those. Each bucket here has at least 30 defaults, enough for this normal approximation to be reasonable; with only a handful of defaults you would use an exact or Wilson interval instead.

BucketDefaults / loansDefault rateStd error95% intervalExposure, Rs croreExpected loss, Rs crore
A30 / 4,0000.75%0.14%0.48% to 1.02%800.36
B60 / 4,0001.50%0.19%1.12% to 1.88%800.72
C90 / 2,5003.60%0.37%2.87% to 4.33%501.08
D150 / 1,50010.00%0.77%8.48% to 11.52%301.80
All330 / 12,0002.75%2403.96
Default rates rise from 0.75% in bucket A to 10.0% in bucket D with no overlap between 95% intervals, and expected loss at 60% loss given default totals Rs 3.96 crore on Rs 240 crore of loans.
Step 2Are the buckets well ordered once you allow for the error?

Read the intervals, not the point estimates. No two intervals overlap, so each bucket's default rate is distinguishable from its neighbour's, and the score ranks risk in the right order. The closest pair is A and B: 0.48% to 1.02% against 1.12% to 1.88%. A direct test of the difference gives about 3.2 standard errors, comfortably significant. Bucket D has the widest interval, plus or minus 1.5 points, because it is both the smallest bucket and the one with the highest rate, but its whole interval sits far above C's.

Default rate by score bucket, with 95% confidence intervals3%6%9%12%0%0.75%0.48 to 1.02%Bucket A30 of 4,0001.50%1.12 to 1.88%Bucket B60 of 4,0003.60%2.87 to 4.33%Bucket C90 of 2,50010.00%8.48 to 11.52%Bucket D150 of 1,500
Lakshyavar's default rates rise from 0.75% in bucket A to 10.0% in bucket D, and because no two 95% intervals overlap the score ranks risk reliably, even though the small buckets' rates are estimated less precisely.
Step 3Where does the expected loss actually sit?

Expected loss is exposure times default rate times loss given default. Loss given defaultThe share of a loan that is lost once a borrower defaults, after collections and recoveries. of 60% turns bucket D's 10% default rate into a 6% expected loss rate, against 0.45% for bucket A. Bucket D is 12.5% of the loans but about 45% of the Rs 3.96 crore of expected loss. That is the number the credit team will care about: pricing or cutting bucket D moves the book's losses far more than any change in A or B.

One loan in eight carries almost half the expected lossShare of loansA 33.3%B 33.3%C 20.8%D 12.5%Share of expected lossA 9%B 18%C 27%D 45%Rs 240 crore of loans at Rs 2 lakh each; expected loss Rs 3.96 crore, 1.65% at 60% loss given default
Bucket D holds one loan in eight but about 45% of Lakshyavar's Rs 3.96 crore of expected loss, while bucket A holds a third of the loans and under a tenth of the loss.

Finish with what the file cannot tell you. These are one-year defaults from a single two-year-old cohort, so the rates carry that year's economy. A 60% loss given default is an assumption, not an estimate from this file. And an interval measures sampling error only; if applicants have changed since, the true rate can move outside it.

Where candidates lose it

The common miss is reporting four default rates and declaring the buckets ordered because the numbers rise. Without intervals you have not shown the ranking is more than noise, which is exactly what a credit risk case is testing.

The second is stopping at default rates. The credit team manages rupees of loss, and the interesting finding is that a small bucket carries nearly half of it.

What the interviewer asks next

  • Bucket A had only 5 defaults in 400 loans. How would you build its interval?
  • How many loans would bucket D need for an interval of plus or minus half a point?
  • The credit team wants to merge A and B. What evidence would you ask for first?

Asked at Jane Street, Credit Risk, London, 2025 (Wall Street Oasis): The case study consisted of credit risk data that I had to analyse using Excel or Python

← Case 054Your model of daily stock returns has an out-of-sample R-squared of 0.4%. A senior researcher asks whether that is useless. Convert it to a correlation and to a rough annual Sharpe ratio for a strategy trading it across 300 stocks.Case 056 →A stock's one-month at-the-money implied volatility is 32% and its three-month is 24%, with results due in two weeks. Back out the move the options imply for the results day, and decide whether the event is priced rich.

Company names and figures are illustrative.

Fin Maverick

Finance education that ends in a job, not a certificate that gathers dust. Built for young India.

LEARN
CalculatorsFrameworksComparisonsInterview RoadmapsShowdown
RESOURCES
All CoursesFree CoursesBootcampsNISMQuarksAI for Finance
COMPANY
AboutJob openingPartnership
LEGAL
Privacy PolicyTerms & ConditionsContent LicenseReturn & Refund Policy
© 2026 FIN MAVERICK / BUILT FOR INDIA.DO FINANCE, DO NOT JUST READ ABOUT IT.