Abstract

A Comparative Analysis of Stock Series Prediction using Deep Learning" is a research journal that focuses on the application of deep learning techniques to predict stock market trends. The work presents a comparative study of several deep learning algorithms, including Long Short-Term Memory (LSTM), Support Vector Machines (SVM), Random Forests (RF), Convolutional Neural Networks (CNN), Deep Neural Networks (DAN), Artificial Neural Network (ANN), and Recurrent Neural Network (RNN) to analyze their effectiveness in predicting stock prices. This research provides insights into the potential of deep learning techniques for predicting stock market trends and helps investors and financial analysts make informed decisions. The experimental results indicated that the RNN model outperformed other models based on its strong predictive capabilities and suitability for predicting Google stock, with an accuracy of 87.32% and the top-performing models for Apple stock was the hybridization of Convolutional Neural Network and Long Short-Term Memory (C-LSTM) with an outstanding accuracy of 99.73%.