A New Investment Method with Autoencoder: Applications to Cryptocurrencies

Expert Systems with Applications, Volume 162, 2020, 113730

Posted: 29 Oct 2019 Last revised: 10 Aug 2020

See all articles by Masafumi Nakano

Masafumi Nakano

University of Tokyo, Graduate School of Economics, Students

Akihiko Takahashi

University of Tokyo - Faculty of Economics

Date Written: October 11, 2019

Abstract

This paper proposes a novel approach to the portfolio management using an AutoEncoder.
In particular, the features learned by an AutoEncoder with ReLU are directly exploited to the portfolio construction.

Since the AutoEncoder extracts the characteristics of the data through the 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 the ReLU and the option payoff.

Especially, this paper shows that the features are successfully replicated by applying so-called the dynamic delta hedging strategy.

An out of sample simulation with crypto currency dataset shows the effectiveness of our proposed strategy.

Furthermore, we investigate the background of our proposed methodology, which suggests that the first principal component is quite important.

Keywords: AutoEncoder, Cryptocurrency, Delta hedging, Artificial neural network

JEL Classification: C45, C63, G11

Suggested Citation

Nakano, Masafumi and Takahashi, Akihiko, A New Investment Method with Autoencoder: Applications to Cryptocurrencies (October 11, 2019). Expert Systems with Applications, Volume 162, 2020, 113730, Available at SSRN: https://ssrn.com/abstract=3473684 or http://dx.doi.org/10.2139/ssrn.3473684

Masafumi Nakano (Contact Author)

University of Tokyo, Graduate School of Economics, Students ( email )

Tokyo
Japan

Akihiko Takahashi

University of Tokyo - Faculty of Economics ( email )

7-3-1 Hongo, Bunkyo-ku
Tokyo 113-0033
Japan

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Abstract Views
505
PlumX Metrics