Home › Hard problems › India

India: hard problems at India's scale

Credit for people with no credit history

Solo: possibleOne person can test a narrow slice of it.

Sunita runs asmall stallcreditrecordemptyOther data, say,phone bills, UPI paymentsA lending modelguesses if shewill repayNoUnfair?may turn down wholegroups more often"Why me?"hard to explain to heror to the regulator
With no credit record, a model has to judge from other data, and its answers can be unfair and hard to explain.

Why it is still open

Millions have no credit record. Models using other data can be unfair and hard to explain to a regulator.

An experiment one person can run in 8 weeks

On a public lending dataset, compare accuracy against fairness gaps for 3 models, plus the explanation each gives a rejected applicant.

Verdict: Solo: possible

Measurable, and lenders and regulators care.

The solo test behind the verdict

  1. Can it be measured? There is a number that shows you did better, such as an error rate, a catch rate or a cost per answer.
  2. Is it cheap to try? It runs on a laptop, free open models and open data, or under about ₹50,000 of rented GPU time.
  3. Is there a public yardstick? A benchmark or dataset others use, so your result can be compared and believed.
  4. Would a small win get noticed? A lab, a funder or a customer would care about a 10% improvement, not only a full solution.

Four yeses means Solo: strong. Two or three means Solo: possible. Fewer means Follow, don't build.

PreviousCourt case backlogNextMatching informal workers to jobs

All 79 hard problems · Working on this, or know of a result we missed? basant@cleandataengineering.ai