Are there techniques or models in finance that (unlike supervised learning where input data such as returns and volatility is estimated making the asset allocation data-driven) allow for portfolio optimization without using empirical data for an input?
$\begingroup$
$\endgroup$
1
-
$\begingroup$ Yes, the simplest is to use hierarchical clustering to split your capital down each branch. With some intuition, however, partitional clustering can be even used like a relative valuation tool. $\endgroup$– Lisa AnnCommented Jul 16, 2020 at 6:52
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
I quote a very famous paper from De Prado:
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2708678
In general, unsupervised learning is a very powerful tool in asset allocation especially with regards to exploring deep unsupervised relations among different assets (i.e. sort of correlations).
