การพยากรณ์ราคาสกุลเงินดิจิทัลและการจัดพอร์ตการลงทุนโดยใช้อนุกรมเวลาฟัซซี่นิวโทรโซฟิกแบบลังเลที่มีค่าเดียว

Abstract

The purpose of this paper is to modified model for a single-valued neutrosophic hesitant fuzzy time series forecasting of the time series data, called Gaussian and bell-shaped membership functions based on single-valued neutrosophic hesitant fuzzy time series (GBMF-SVNHFTS). We also test the approximation accuracy and reliability of the studied models, and compared to Classical Fuzzy Time Series Models in forecasting University of Alabama student enrollment data. Moreover, we will forecast the daily closing prices of ten major cryptocurrencies using the proposed GBMF-SVNHFTS model and compared to the S-ANFIS, ARIMA, and LSTM methods. to analyze the appropriate investment’s proportion and risk of cryptocurrencies portfolio. Then, we applied our method to predict the ten major cryptocurrencies consisting of Bitcoin (BTC), Ethereum (ETH), Cardano (ADA), Binance Coin (BNB), Dogecoin (DOGE), Solana (SOL), Ripple (XRP), Polygon (MATIC), Polkadot (DOT), and Litecoin (LTC). The data from 17 August 2017 to 30 June 2022 were retrieved from www.yahoo.finance.com (accessed on 11 July 2022). To achieve this purpose, we improve the previously presented single-valued neutrosophic hesitant fuzzy time series (SVNHFTS) model by including several degrees of hesitancy to increase forecasting accuracy. The Gaussian fuzzy number (GFN) and the bell-shaped fuzzy number (BSFN) were used to incorporate the degree of hesitancy. The cosine measure and the single-valued neutrosophic hesitant fuzzy weighted geometric (SVNHFWG) operator were applied to analyze the possibilities and pick the best one based on the neutrosophic value. The result of improve the previously presented single-valued neutrosophic hesitant fuzzy time series (SVNHFTS) model revealed that the proposed GBMF-SVNHFTS model outperforms all other Classical Fuzzy Time Series Models in terms of RMSE, MAE and MAPE. The suggested GBMF-SVNHFTS model offers superior efficiency and accuracy evaluated in this study compared to the S-ANFIS, ARIMA, and LSTM approaches accordingly in terms of RMSE, MAE, and MAPE, according to the results of predicting the 10 biggest cryptocurrencies. The lowest variance strategy, which is based on bitcoin forecasting data from the most efficient model, gives a higher rate of return than the equal weighting strategy, according to risk analysis and portfolio management. The risk value calculated using the Value at Risk and Expected Shortfall is also lower than the risk value calculated using the same equal weighting technique.