Cryptocurrencies transactions advisor using a genetic Mamdani-type fuzzy rules based system
Carregando...
Data
Título da Revista
ISSN da Revista
Título de Volume
Editor
Universidade Federal de Minas Gerais
Descrição
Tipo
Artigo de evento
Título alternativo
Primeiro orientador
Membros da banca
Resumo
Cryptocurrencies prices forecasting is a complex theme due to the chaotic market behavior and the influence of external events. Therefore, inference models should offer, in addition to a satisfying accuracy, reasonable interpretability, so that investors can decide based on their own knowledge. However, many studies in this subject focus on model accuracy and leave much to be desired in terms of simplicity and interpretability. This work proposes the use of Mamdani interpretable fuzzy inference models for forecasting cryptocurrency price variation. For that, a genetic algorithm to optimize models accuracy is employed, limiting the quantity of rules and antecedents arbitrarily. A set of infeasible rules had to be discarded, in order to generate interesting models, that produce a relevant amount of trades. Data from Kraken exchange were utilized for training, validation and results assessment. Results have shown that, for the cryptocurrencies with the highest validation performances, there are gains in comparison to the simple currency appreciation. Using the interpretable aspect of the models, it should be possible to obtain even higher profits.
Abstract
Assunto
Sistemas difusos, Engenharia econômica
Palavras-chave
Genetic algorithms , Bitcoin , Sociology , Statistics , Linguistics , Forecasting, Fuzzy Rules , Forecasting , Set Of Rules , Model Interpretation , Fuzzy Logic , Model Inference , Fuzzy Model , Currency Appreciation , Membership Function , Individual Fitness , Market Volatility , Tournament , Fuzzy System , Market Growth , Solution Representation , Individuals In Generation , Portfolio Investment , Output Prices , Transaction Fees , Final Balance, inference models for the forecasting of cryptocurrency prices variation. The number of rules per model and antecedents per rule were limited, so that the investor could understand the designed system. To deal with the accuracy-interpretability trade off, a genetic algorithm was employed to each cryptocurrency evaluated. When tested in a real case scenario, the five best models obtained better profits than the currency appreciation itself, in average
Citação
Departamento
Curso
Endereço externo
https://ieeexplore.ieee.org/document/8491619