Work detail

On the Utilization of Machine Learning in Asset Return Prediction on Limited Datasets

Author: Mgr. Lukáš Petrásek,
Year: 2019 - summer
Leaders: doc. PhDr. Jozef Baruník Ph.D.
Consultants:
Work type: Finance, Financial Markets and Banking
Masters
Language: English
Pages: 74
Awards and prizes:
Link:
Abstract: In this thesis, we conduct a comparative analysis of how various modern machine learning techniques perform when employed to asset return prediction
on a relatively small sample. We consider a broad selection of machine learning methods, including e.g. elastic nets, random forests or recently highly
popularized neural networks. We find that these methods fail to outperform
a simple linear model containing only 5 factors and estimated via ordinary
least squares. Our conclusion is that applications of machine learning in finance should be conducted carefully, because the techniques may not actually
be as powerful as one might think when they are applied under unfavorable
circumstances.

Partners

Deloitte

Sponsors

CRIF
McKinsey
Patria Finance