Stock Price Prediction Using LSTM and GRU

Procedia Computer Science, 2020

It has never been easy to invest in a set of assets, the abnormally of financial market does not allow simple models to predict future asset values with higher accuracy. Machine learning, which consist of making computers perform tasks that normally requiring human intelligence is currently the dominant trend in scientific research. This article aims to build a model using Recurrent Neural Networks (RNN) and especially Long-Short Term Memory model (LSTM) to predict future stock market values. The main objective of this paper is to see in which precision a Machine learning algorithm can predict and how much the epochs can improve our model.

International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2023

This study investigates the widespread use of machine learning techniques, including recurrent neural networks (RNNs) and long short-term memory (LSTM) models to the analysis of stock market data. By utilizing RNN and LSTM model capabilities to identify temporal relationships and patterns in stock market data, it seeks to overcome conventional techniques' constraints. The research provides empirical proof of the efficiency of RNNs and LSTM models in enhancing investment decision-making by analyzing the project outcomes using real-world stock market data. The inclusion of RNNs and LSTM models in this research paper strengthens the exploration of machine learning techniques in stock market analysis.

TechRxiv, 2022

Prediction of financial markets is a challenging task due to its volatility, presence of noise and involvement of human sentiments. This work comparatively analyses the implementations of LSTM (Long Short Term Memory) and three kernels of SVR (Support Vector Regressor), namely linear kernel, RBF (Radial Basis Function) kernel and polynomial kernel. A series of experiments have been conducted, and results of the two algorithm have been compared based on the accuracy of the market forecast. The results indicate that a single kernel of SVR is not sufficient to predict the prices of the stocks, although if all three kernels are considered, the results are comparatively better. But, LSTM exhibits the best accuracy compared to SVR with linear activation function and four layers.

Hradec Economic Days, 2021

We employ a recurrent neural network with Long short-term memory for the task of stock price forecasting. We chose three stocks from the same sub-industry: Visa, Mastercard, and PayPal. This paper aims to test the LSTM network's prediction on stock prices and propose the best settings for selected stock price forecasting. The secondary goal is to assess how the settings differed in the case of two highly correlated stocks (Visa-Mastercard year correlation coefficient average: 0.97) and the case of only weak correlated stock (Visa-PayPal correlation coefficient average: 0.39). We tested 117 different settings of LSTM neural networks. The settings differed by the number of epochs/splits (from ten to fifty-eight by the step of four) and the range (minute, hour, and day). Our dataset was the stock price from 1.6.2020 to 15.1.2021. The best performing network has been trained on a 10day period for Visa and 10-minute for Mastercard and PYPL. However, the differences were negligible, so we did not find the number of epochs as a key setting, unlike in the case of FOREX.

2021

This research paper specifically targets the Indian Stock Market, The National Stock Exchange. Stock Market Prediction refers to understanding various aspects of the stock market that can influence the price of the stocks and based on these potential factors we built a Website/Application to predict the stock’s price. We’ll be using Python as a programming language to predict the prices, and in this paper, we propose a Machine Learning (ML) approach that will be trained from the available top 50 stocks of the NSE and gain intelligence and then use the acquired knowledge for an accurate prediction. This application with help the user to speculate the stock price trend and help him decide whether to buy or short the stock price to maximize their profit. You can expect to have a decent level of understanding of all the phenomenon and processes of stock market predictions and the associated technologies. This article will cover up topics such as how we created our predictive model and t...

International Journal for Research in Applied Science and Engineering Technology, 2023

International Journal of Advanced Research in Science, Communication and Technology

This paper aims to develop an innovative neural network approach to achieve better stock market predictions. Data were obtained from the live stock market for real-time and off-line analysis and results of visualizations and analytics to demonstrate Internet of Multimedia of Things for stock analysis. To study the influence of market characteristics on stock prices, traditional neural network algorithms may incorrectly predict the stock market, since the initial weight of the random selection problem can be easily prone to incorrect predictions. Based on the development of word vector in deep learning, we demonstrate the concept of “stock vector.” The input is no longer a single index or single stock index, but multi-stock high-dimensional historical data. We propose the deep long short-term memory neural network (LSTM) with embedded layer and the long short-term memory neural network with automatic encoder to predict the stock market. In these two models, we use the embedded layer ...

IJRASET, 2021

Stock Market is referred to as a trading platform where trading of listed companies share price is exchanged. It is a place where individuals can buy or sell shares of the publicly listed companies. The prediction of stock market that how it will perform, its movement is one of the challenging tasks to do. Stock market prediction involves determining the future movement of the stock value of a financial exchange. In this paper the prediction of the stock prices using deep learning's LSTM (Long Short-Term Memory) which is the extension of Recurrent Neural Network is done. The previous two years historical dataset from 31/7/2019 to 13/8/2021 is taken for the prediction purpose. The prediction is based on the time series analysis of data, since it can help us to get an idea of the stock price pattern and also it is considered to be the best tool for understanding the pattern of the previously observed values and make the predictions based on it. For a greater accuracy of the predictions, we should consider past happenings or events as the past affects the future. Since for stock market prediction the data will be in time series and LSTM performs well when the information or the data is of the past and the prediction is to be made for the future then we can say that LSTMs are quite capable of doing the prediction for the stock market values.

Stock market is carrying highly dynamic as well as time-varying characteristics, this field is drawing enormous amount of attention in financial sector. Prediction of stock prices are often challenging as it is involves current socioeconomic condition, company profiles and many more. This paper attempts to predict Tesla stock market price using two-layer LSTM model. Close price, high price, low price, and open price are forecasted using this proposed two-layer LSTM model. Experimental results exhibited an accuracy of 86.67%, 86.48%, 89.82%, 88.81% respectively for close, open, high and low prices respectively.

International Journal of Computational Intelligence Studies, 2019

Stock market is an immensely complex, chaotic and dynamic environment. Thus, the task of predicting changes in such an environment becomes challenging with regards to its accuracy. A number of approaches have been adopted to take on that challenge and machine learning has been at the crux in many of them. There are plenty of examples of algorithms based on machine learning yielding satisfactory results for such type of prediction. This paper presents the usage of long short-term memory (LSTM) networks in this scenario, to predict future trends of stock market prices based on the patterns from price history, paired with technical analysis indicators. To achieve this, a model has been built, and a series of experiments have been conducted through a number of parameters and the results were analysed against predefined metrics to assess if this algorithm presents any improvements in front of other machine learning methods and strategies. Also, a comparative study is presented which analyses popularly used optimisers and error schemes to check which given optimiser yields the best results. The results obtained are promising and presented a reasonably accurate prediction for the rise or fall of a particular stock in the near future.