<![CDATA[The current rapid development of technology can facilitate all human activities, so that all aspects cannot be separated from technology, including the financial sector. With the development of technology, it is also accompanied by the introduction of various investment instruments. Every time you make an investment, of course there will always be various risks that come with it, including investing in cryptocurrencies, one of which is bitcoin. Unlike conventional currencies, bitcoin is not decentralized so that its price development is not under the supervision or control of any party, where as conventional money there is a certain institution that oversees and controls its movements. This causes the price of the exchange rate of bitcoin to be inconsistent or unstable. With the prediction method, bitcoin users can determine the right time to carry out transactions. This study aims to predict bitcoin prices using the LSTM and Bi-LSTM methods. Based on the research results, the best prediction results were obtained using the Bi-LSTM method with an RMSE of 1482.73 whereas with LSTM it produces an RMSE of 1768.69 so that it can be concluded from an accuracy perspective that Bi-LSTM gives more accurate results but with Bi-LSTM it requires more resources.]]>
Copyrights © 2023
