Neural network models for empirical finance
Neural network models for empirical finance
This paper presents an overview of the procedures involved in prediction with machine learning models with special emphasis on deep learning. We study suitable objective functions for prediction in high-dimensional settings and discuss the role of regularization methods to alleviate the problem of overfitting. We also review other features of machine learning methods such as the selection of hyperparameters, the role of the architecture of a deep neural network for model prediction or the importance of using different optimization routines for model selection. The review also considers the issue of model uncertainty and presents state-of-the-art methods for constructing prediction intervals using ensemble methods such as bootstrap and Monte Carlo dropout. These methods are illustrated in an out-of-sample empirical forecasting exercise that compares the performance of machine learning methods against conventional time series models for different financial indices. These results are confirmed in an asset allocation context.
1-22
Calvo-Pardo, Hector
07a586f0-48ec-4049-932e-fb9fc575f59f
Olmo, Jose
706f68c8-f991-4959-8245-6657a591056e
Mancini, Tullio
3e5a59a2-e184-4996-a7d6-7b4394bec08c
November 2020
Calvo-Pardo, Hector
07a586f0-48ec-4049-932e-fb9fc575f59f
Olmo, Jose
706f68c8-f991-4959-8245-6657a591056e
Mancini, Tullio
3e5a59a2-e184-4996-a7d6-7b4394bec08c
Calvo-Pardo, Hector, Olmo, Jose and Mancini, Tullio
(2020)
Neural network models for empirical finance.
Journal of Risk and Financial Management, 13 (11), .
(doi:10.3390/jrfm13110265).
Abstract
This paper presents an overview of the procedures involved in prediction with machine learning models with special emphasis on deep learning. We study suitable objective functions for prediction in high-dimensional settings and discuss the role of regularization methods to alleviate the problem of overfitting. We also review other features of machine learning methods such as the selection of hyperparameters, the role of the architecture of a deep neural network for model prediction or the importance of using different optimization routines for model selection. The review also considers the issue of model uncertainty and presents state-of-the-art methods for constructing prediction intervals using ensemble methods such as bootstrap and Monte Carlo dropout. These methods are illustrated in an out-of-sample empirical forecasting exercise that compares the performance of machine learning methods against conventional time series models for different financial indices. These results are confirmed in an asset allocation context.
Text
CPMO machine learning review final revised
- Accepted Manuscript
Text
jrfm-963015
- Version of Record
More information
Accepted/In Press date: 26 October 2020
e-pub ahead of print date: 29 October 2020
Published date: November 2020
Additional Information:
This article belongs to the Special Issue, Machine Learning for Empirical Finance
Identifiers
Local EPrints ID: 444610
URI: http://eprints.soton.ac.uk/id/eprint/444610
ISSN: 1911-8066
PURE UUID: 61a71413-1455-4275-b60e-774df2250398
Catalogue record
Date deposited: 27 Oct 2020 19:55
Last modified: 17 Mar 2024 03:32
Export record
Altmetrics
Contributors
Author:
Tullio Mancini
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
