Skip to main content
Blog home
Newsletter
News
Video
Podcast
Reading list
Wright Brief
Sign In

What is Cross-Validation in Finance (Purged K-Fold)?

A plain-language explanation of Cross-Validation in Finance (Purged K-Fold), with a worked example, common pitfalls and the questions people ask most.

Listen to this article
Audio · ~2 min
Add as a preferred source on Google

Cross-validation tests a model by repeatedly training it on part of the data and scoring it on the rest. In finance, ordinary k-fold cross-validation leaks information because returns overlap in time, so researchers use purged and embargoed versions.

Why ordinary k-fold fails

  • Data is ordered. Shuffling rows lets the model train on the future to predict the past.
  • Labels overlap. If each label is the return over the next 5 days, observations on Monday and Tuesday share four days of the same return, so a training row can contain nearly the same information as a test row.

An illustrative example

Suppose labels are 5-day forward returns and the test fold covers days 100 to 120. A training observation from day 97 has a label that runs to day 102, inside the test period.

TechniqueWhat it does
PurgingRemoves training observations whose labels overlap the test period, here days 96 to 99 and any after the fold's start
EmbargoAlso drops a short period after the test fold, since serial correlation links it to the test data
Combinatorial purged CVTests many train/test combinations to get a distribution of backtest paths, not just one

These techniques are described in Lopez de Prado (2018).

Where it fits

Cautions

Even with purging, repeated use of the same data to choose models leads to data snooping. A final untouched hold-out period is still needed.

Frequently asked questions

Why can't normal k-fold cross-validation be used for financial data?

Because returns are time-ordered and labels overlap, so training data can contain information from the test period, inflating results.

What is purging in cross-validation?

Removing training observations whose labels overlap in time with the test set.

What is an embargo?

A gap after the test set during which observations are excluded from training to avoid leakage through serial correlation.

Is cross-validation better than walk-forward testing?

They serve different needs. Walk-forward respects time strictly and mimics live use, while purged cross-validation uses data more efficiently.

Further reading

  1. Lopez de Prado, M. (2018). Advances in Financial Machine Learning. Wiley.
Browse the full Quant Glossary →

Disclaimer: Investment in securities market are subject to market risks. Read all the related documents carefully before investing. Registration granted by SEBI, membership of a SEBI recognized supervisory body (if any) and certification from NISM in no way guarantee performance of the intermediary or provide any assurance of returns to investors.

The content in these posts/articles is for informational and educational purposes only and should not be construed as professional financial advice and nor to be construed as an offer to buy/sell or the solicitation of an offer to buy/sell any security or financial products. Users must make their own investment decisions based on their specific investment objective and financial position and using such independent advisors as they believe necessary.

Wryght Research & Capital Pvt (Brand name: Wright Research) is a SEBI Registered Portfolio Manager Reg No: INP000007979 (Validity: Apr 03, 2023 – Perpetual) and a SEBI Registered Research Analyst No: INH000017295 (Validity: Jul 03, 2024 – Perpetual), with its registered office at 103, Shagun Vatika Prag Narayan Road, Lucknow, UP, 226001 India and CIN: U67100UP2019PTC123244. Past performance may or may not be sustained in future. Performance provided there in is not verified by SEBI. Investment in securities is subject to market and other risks, and there is no assurance or guarantee that the objectives of any of the strategies of the Portfolio Management Services will be achieved. Registration granted by SEBI, enlistment as RA with Exchange and certification from National Institute of Securities Markets (NISM) in no way guarantee performance of the intermediary or provide any assurance of returns to investors. Please read the Disclosure document carefully before investing. Securities quoted are for illustration only and are not recommendatory. Charts shown are for illustration only. For more information and disclosures, visit our disclosures page here.

Found this useful? Share it.
Wright PMS · Portfolio Management Service

Put this research to work

The same 300+ factor research engine behind this article — applied to a professionally managed portfolio, end to end.

300+
Factors tracked
2L+
Investors
₹1,200+ Cr
Invested
SEBI
Registered PMS