Tokenisation
Splitting text into units, usually words, called tokens: the first step in preparing text for a model. With digital assets the same word means representing ownership of an asset as a token on a ledger.
Where you will meet it
Tokenisation appears in 2 learning outcomes on the CFA syllabus. A few of them:
- Explain distributed ledger technology and where it is used
“The credible applications in finance are settlement, tokenisation of illiquid assets and smart contracts that execute automatically.”
- Explain techniques for extracting, choosing and engineering features from text data
“Tokenisation splits it into words; normalisation lowercases, removes stop words, and applies stemming or lemmatisation.”
See also
Practise it
Practise tokenisation until it is automatic: questions that explain every wrong option.
Take the free diagnostic →