A conceptual alternative forecasting model for alternative investments

Dimitrios Stafylas, Konstantina Mari

Research output: Contribution to journalArticle

Abstract

In this article we present a conceptual model for forecasting purposes that can be used from fund managers or investors. Our conceptual model is a hybrid model and borrows concepts from machine learning; more specifically, from artificial neural networks (ANN) and fuzzy logic (FL). We propose the use of the nonlinear autoregressive network with exogenous inputs (NARX) which is a recurrent dynamic network, with feedback connections enclosing several layers of the network. This ANN is combined with a FL component to deal with uncertainties when considering various market conditions. The proposed conceptual forecasting model has an open architecture design so as to be extended and optimized based on investors’ needs.
Original languageEnglish
Pages (from-to)1-25
JournalJOURNAL OF PREDICTION MARKETS
Volume12
Issue number2
DOIs
Publication statusPublished - 30 Jun 2018

Fingerprint

Conceptual model
Fuzzy logic
Alternative investments
Artificial neural network
Investors
Market conditions
Machine learning
Hybrid model
Uncertainty
Network dynamics
Fund managers

Cite this

Stafylas, Dimitrios ; Mari, Konstantina. / A conceptual alternative forecasting model for alternative investments. In: JOURNAL OF PREDICTION MARKETS. 2018 ; Vol. 12, No. 2. pp. 1-25.
@article{dfa7ec5c396d47d7a34208fd06a66ec0,
title = "A conceptual alternative forecasting model for alternative investments",
abstract = "In this article we present a conceptual model for forecasting purposes that can be used from fund managers or investors. Our conceptual model is a hybrid model and borrows concepts from machine learning; more specifically, from artificial neural networks (ANN) and fuzzy logic (FL). We propose the use of the nonlinear autoregressive network with exogenous inputs (NARX) which is a recurrent dynamic network, with feedback connections enclosing several layers of the network. This ANN is combined with a FL component to deal with uncertainties when considering various market conditions. The proposed conceptual forecasting model has an open architecture design so as to be extended and optimized based on investors’ needs.",
author = "Dimitrios Stafylas and Konstantina Mari",
year = "2018",
month = "6",
day = "30",
doi = "10.5750/jpm.v12i2.1541",
language = "English",
volume = "12",
pages = "1--25",
number = "2",

}

A conceptual alternative forecasting model for alternative investments. / Stafylas, Dimitrios; Mari, Konstantina.

In: JOURNAL OF PREDICTION MARKETS, Vol. 12, No. 2, 30.06.2018, p. 1-25.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A conceptual alternative forecasting model for alternative investments

AU - Stafylas, Dimitrios

AU - Mari, Konstantina

PY - 2018/6/30

Y1 - 2018/6/30

N2 - In this article we present a conceptual model for forecasting purposes that can be used from fund managers or investors. Our conceptual model is a hybrid model and borrows concepts from machine learning; more specifically, from artificial neural networks (ANN) and fuzzy logic (FL). We propose the use of the nonlinear autoregressive network with exogenous inputs (NARX) which is a recurrent dynamic network, with feedback connections enclosing several layers of the network. This ANN is combined with a FL component to deal with uncertainties when considering various market conditions. The proposed conceptual forecasting model has an open architecture design so as to be extended and optimized based on investors’ needs.

AB - In this article we present a conceptual model for forecasting purposes that can be used from fund managers or investors. Our conceptual model is a hybrid model and borrows concepts from machine learning; more specifically, from artificial neural networks (ANN) and fuzzy logic (FL). We propose the use of the nonlinear autoregressive network with exogenous inputs (NARX) which is a recurrent dynamic network, with feedback connections enclosing several layers of the network. This ANN is combined with a FL component to deal with uncertainties when considering various market conditions. The proposed conceptual forecasting model has an open architecture design so as to be extended and optimized based on investors’ needs.

UR - http://ubplj.org/index.php/jpm/article/view/1541

U2 - 10.5750/jpm.v12i2.1541

DO - 10.5750/jpm.v12i2.1541

M3 - Article

VL - 12

SP - 1

EP - 25

IS - 2

ER -