Bitcoin Price Prediction using the Hybrid Convolutional Recurrent Model Architecture

Abstract

The field of finance makes extensive use of real-time prediction of stock price tools, which are instruments that are put to use in the process of creating predictions. In this article, we attempt to predict the price of Bitcoin in a manner that is both accurate and reliable. Deep learning models, as opposed to more traditional methods, are used to manage enormous volumes of data and to generate predictions. The purpose of this research is to develop a method for predicting stock prices using the Hybrid Convolutional Recurrent Model (HCRM) architecture. This model architecture integrates the advantages of two separate deep learning models: The 1-Dimensional-Convolusional Neural Network (1D-CNN) and the Long-Short Term Memory (LSTM). The 1D-CNN is responsible for the feature extraction, while the LSTM is in charge of the temporal regression. The developed 1D-CNN-LSTM model has an outstanding performance in predicting stock values.

A Survey on the Latest Intrusion Detection Datasets for Software Defined Networking Environments

“…Various classifiers have been used in the literature and it has been shown that RF was the most optimal. Moreover, LSTM and CNN were often utilized in hybrid classifiers, in combination with CNN achieving good results in image processing due to its power of learning from spatial features, while the power of LSTM resides in its ability to learn from temporal correlations of network traffic that generate times series data [32]. Additionally, LSTM performs better with large datasets [33].…”

Advanced Fraud Detection in Blockchain Transactions: An Ensemble Learning and Explainable AI Approach

“…In the realm of data cleansing, we judiciously excised three variables from our dataset deemed non-essential for the task of EFD. These excluded features-specifically the "Address," "ERC20 most sent token type," and "ERC20 most received token type" were identified as extraneous in the context of our analytical objectives, thereby streamlining the feature space to those of greater pertinence [43]. Addressing the prevalence of incomplete records, we invoked the capabilities of the datasets library, a Python toolkit tailored for facile data operations and exploration.…”