期刊名称：International Journal of Advances in Engineering and Management
电子版ISSN：2395-5252
出版年度：2022
卷号：4
期号：1
页码：847-852
DOI：10.35629/5252-04016642654
语种：English
出版社：IJAEM JOURNAL
摘要：Bitcoin has become an investment due to its increasing popularity, and it operates on the Block chain technology, which has given rise to other crypto currencies.This makes predicting its value extremely challenging, thus this predictor is put to the test using a Machine Learning Algorithm and an Artificial Neural Network Model.We used Bitcoin data sets to test and train the machine learning and artificial intelligence models in this work.The data filtration process was completed with the help of python libraries.Python provides a fantastic capability for data visualisation and analysis.We reduce the data and employ the characteristics or attributes that are most suited for the model after we have a good knowledge of it. The model is put into action, and the results are recorded.When compared to other Machine Learning models from relevant studies, it was determined that the linear regression model's accuracy rate is extremely high; it was shown to be 99.87 percent correct.The LSTM model, on the other hand, has a 0.08 percent minor error rate.As a result, the neural network model is superior to the machine learning model in terms of optimization.The tkinter library was used to develop a tiny GUI that allows the user to input the High, Low, and Open features values and then anticipate the coin's future value.The results of a machine learning model and an artificial neural network model are compared in this research.We selected linear regression to compare it to the LSTM model because it delivered the highest accuracy compared to the other machine learning models.
