A new investment method with AutoEncoder: Applications to crypto currencies

•We propose a new investment strategy free from the estimation of expected returns.•AutoEncoder extracts the factors which enable to prevent the large drawdown.•The extracted non-linear factors are implemented by the dynamic delta hedging.•Backtesting with multiple cryptocurrencies shows the effecti...

Full description

Saved in:
Bibliographic Details
Published in:Expert systems with applications Vol. 162; p. 113730
Main Authors: Nakano, Masafumi, Takahashi, Akihiko
Format: Journal Article
Language:English
Published: New York Elsevier Ltd 30.12.2020
Elsevier BV
Subjects:
Artificial neural network
AutoEncoder
Crypto currency
Delta hedging
Digital currencies
Linear transformations
Portfolio management
Crypto currency
Artificial neural network
AutoEncoder
Delta hedging
ISSN:0957-4174, 1873-6793
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•We propose a new investment strategy free from the estimation of expected returns.•AutoEncoder extracts the factors which enable to prevent the large drawdown.•The extracted non-linear factors are implemented by the dynamic delta hedging.•Backtesting with multiple cryptocurrencies shows the effectiveness of our strategy. This paper proposes a novel approach to the portfolio management using an AutoEncoder. In particular, features learned by an AutoEncoder with ReLU are directly exploited to portfolio constructions. Since the AutoEncoder extracts characteristics of data through a non-linear activation function ReLU, its realization is generally difficult due to the non-linear transformation procedure. In the current paper, we solve this problem by taking full advantage of the similarity of ReLU and an option payoff. Especially, this paper shows that the features are successfully replicated by applying so-called dynamic delta hedging strategy. An out of sample simulation with crypto currency dataset shows the effectiveness of our proposed strategy.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0957-4174
1873-6793
DOI:10.1016/j.eswa.2020.113730