Many investors have been attracted by Crypto assets in the last few years. However, despite the possibility of gaining high returns, investors bear high risks in crypto markets. To help investors and make the markets more reliable, Robot advisory services are rapidly expanding in the field of crypto asset allocation. Robot advisors not only reduce costs but also improve the quality of the service by involving investors and make the market more transparent. However, the reason behind the given solutions is not clear and users face a black-box model that is complex. The aim of this paper is to improve trustworthiness of robot advisors, to facilitate their adoption. For this purpose, we apply Shapley values to the predictions generated by a machine learning model based on the results of a dynamic Markowitz portfolio optimization model and provide explanations for what is behind the selected portfolio weights.

Explainable artificial intelligence for crypto asset allocation

Babaei G.;Giudici P.;Raffinetti E.
2022-01-01

Abstract

Many investors have been attracted by Crypto assets in the last few years. However, despite the possibility of gaining high returns, investors bear high risks in crypto markets. To help investors and make the markets more reliable, Robot advisory services are rapidly expanding in the field of crypto asset allocation. Robot advisors not only reduce costs but also improve the quality of the service by involving investors and make the market more transparent. However, the reason behind the given solutions is not clear and users face a black-box model that is complex. The aim of this paper is to improve trustworthiness of robot advisors, to facilitate their adoption. For this purpose, we apply Shapley values to the predictions generated by a machine learning model based on the results of a dynamic Markowitz portfolio optimization model and provide explanations for what is behind the selected portfolio weights.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11571/1461546
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? ND
social impact