– The paper develops a hybrid ANN through Rao algorithm (RA + ANN) for predicting cryptocurrencies.
– Six comparative models are evaluated and the RA + ANN model outperforms them.
– The proposed model has the lowest mean absolute percentage of error (MAPE) and average relative variance (ARV) values.
– The RA + ANN model can be recommended as a potential financial instrument for predicting cryptocurrencies.

– “Predicting Cryptocurrency Prices: A Machine Learning Approach”
– “Using Rao Algorithm-Based ANN for Cryptocurrency Price Forecasting”
– “Comparative Analysis of ANN Models for Cryptocurrency Prediction”
– “RA + ANN: The Optimal Hybrid Model for Cryptocurrency Forecasting”
– “Improving Accuracy in Cryptocurrency Price Prediction with RA + ANN”
– “RA + ANN: A Potential Financial Instrument for Cryptocurrency Prediction”

– Paper focuses on predicting cryptocurrency closing prices using artificial neural networks (ANNs).
– ANNs are suitable for predicting financial time series (FTS).
– Conventional methods struggle with capturing uncertainties in cryptocurrency FTS.
– Proposed hybrid ANN with Rao algorithm (RA + ANN) outperforms other models.
– RA + ANN generates lowest mean absolute percentage of error (MAPE) and average relative variance (ARV) values.
– Recommended as a potential financial instrument for predicting cryptocurrencies.

– Paper develops a hybrid ANN through Rao algorithm (RA + ANN)
– Six popular cryptocurrencies are predicted using the proposed model
– Proposed model outperforms existing methods in terms of prediction accuracy

– This article focuses on predicting cryptocurrency closing prices using artificial neural networks.
– The objective is to develop an efficient ANN forecast for accurate cryptocurrency prediction.
– The article provides a concise description of ANNs and their capabilities.
– Experimental data and summarized results are presented in the article.
– The proposed hybrid ANN with Rao algorithm (RA + ANN) outperforms other models.
– The RA + ANN model has the lowest mean absolute percentage of error (MAPE) and average relative variance (ARV) values.
– The model can be recommended as a potential financial instrument for predicting cryptocurrencies.

– Study of trading opportunities and profitability in the cryptocurrency market.
– Use of evolutionary optimization techniques to train ANNs.
– Testing the appropriateness of Rao algorithms for finding optimal parameters of ANNs.
– Application of the resultant method for stock closing price prediction.
– Suggestion of different soft computing methods for predicting cryptocurrencies indices.

– Hybrid ANN through Rao algorithm (RA + ANN)
– GA + ANN
– PSO + ANN
– MLP
– SVM
– LSE
– ARIMA

– Hybrid ANN through Rao algorithm-based optimization (RA ANN) is developed.
– RA ANN has faster convergence rate and better generalization ability.
– RA ANN-based forecasting is good enough to follow dynamic trend of cryptocurrencies.
– RA ANN achieved improved forecasting accuracy compared to other methods.

– Developed a hybrid ANN through Rao algorithm (RA + ANN) for cryptocurrency prediction.
– Compared the RA + ANN model with GA + ANN, PSO + ANN, MLP, SVM, LSE, and ARIMA models.
– RA + ANN generated the lowest mean absolute percentage of error (MAPE) and average relative variance (ARV) values.
– RA + ANN outperformed existing methods and can be recommended for cryptocurrency prediction.

– The researchers created a computer program to predict the prices of cryptocurrencies.
– They used a type of artificial intelligence called artificial neural networks (ANNs).
– The program was trained to predict the prices of six popular cryptocurrencies: Bitcoin, Litecoin, Ethereum, CMC 200, Tether, and Ripple.
– The program uses hidden layers to capture the relationships between different variables.
– The predictions made by the program were more accurate than other methods tested.
– The program can be used as a tool to help predict cryptocurrency prices.

– Hybrid ANN through Rao algorithm-based optimization (RA ANN) is developed.
– RA ANN has faster convergence rate and better generalization ability.
– RA ANN-based forecasting is good enough to follow the dynamic trend of cryptocurrencies.
– RA ANN achieved improved forecasting accuracy compared to other models.

Comments

No comments yet. Why don’t you start the discussion?

    Leave a Reply