Stock Price Analysis and Prediction Using Seq2Seq LSTM

Lecture notes in networks and systems, Journal Year: 2023, Volume and Issue: unknown, P. 655 - 666

Published: Jan. 1, 2023

Language: Английский

---

Unveling the Precision of Deep Learning Models for Stock Price Prediction: A Comparative Analysis of Bi-LSTM, LSTM, and GRU

Published: Oct. 25, 2023

Due to the unpredictability of stock market, accurate prognostic models are necessary for investing. In recent years, machine learning techniques, specifically deep algorithms, have grown in popularity predicting prices. This paper seeks compare stock-price forecasting abilities several models, including LSTM, Bi-LSTM, and GRU. The algorithms make use capabilities Recurrent Neural Networks (RNNs), with a particular emphasis on Long-Short Term Memory (LSTM) model. primary objective is evaluate accuracy these at market values determine how number training epochs affects model performance. Through comparative analysis, we intend identify most Using historical data, research involves evaluating various models. Common evaluation metrics, such as Root Mean Square Error (RMSE), Squared (MSE), Absolute (MAE), used performance each terms RMSE, MSE, MAE, bi-LSTM outperforms other obtaining 0.00029, 0.01 respectively.

Language: Английский

---

ANFIS-Based Investment Recommendations for Government Bonds: Personalized Approach

Lecture notes in computer science, Journal Year: 2024, Volume and Issue: unknown, P. 3 - 20

Published: Jan. 1, 2024

Language: Английский

---

A multi-scale multi-head attention network for stock trend prediction considering textual factors

Applied Soft Computing, Journal Year: 2024, Volume and Issue: unknown, P. 112388 - 112388

Published: Oct. 1, 2024

Language: Английский

---

Prediction of the Price of Advanced Global Stock Markets Using Machine Learning: Comparative Analysis

Journal of Financial Risk Management, Journal Year: 2024, Volume and Issue: 13(04), P. 689 - 702

Published: Jan. 1, 2024

Language: Английский

---

Stock Market Forecasting using ANN

2021 5th International Conference on Information Systems and Computer Networks (ISCON), Journal Year: 2023, Volume and Issue: unknown, P. 1 - 5

Published: March 3, 2023

Due to the unpredictable nature of share market, prediction market is an assignment. However, as a way recognize or make earnings, numerous marketplace contributors researchers try forecast percentage price by use diverse numerical, related finance even neural community approaches. Herein paper, effort made approximately proportion using Artificial Neural Network (ANN) this approach strong and consistent.

Language: Английский

---

Neural Network and Sentimental Model for Prediction of Stock Trade Value

Revue d intelligence artificielle, Journal Year: 2023, Volume and Issue: 37(2), P. 315 - 321

Published: April 30, 2023

Forecasting and pattern recognition are increasingly important in unpredictable of the stock market.No system can consistently deliver correct predictions; complex machine learning approaches required.Many research initiatives from numerous disciplines have been carried out to address difficulties market forecasting.In order predict values, a significant amount has conducted.Many techniques applied this form forecasting, results were satisfactory.In study, we'll utilize web scraping get all actual data National Stock Exchange (NSE) Long Short Term Memory (LSTM) Networks with prior mining try forecast value on certain day.The study show potential LSTM for examining historical price obtaining useful guidance through trend forecasting appropriate economic parameters.To determine if company's is heading upward or lower, should also gather most recent commentary pertinent websites apply noise reduction, classifier, an algorithm analyze sentiment polarity.Using method, proposed represents current condition specific information.

Language: Английский

---

An Aggregator Framework for Transforming Big Data in Real-Time using PT-INDRNN

International Journal of Engineering and Advanced Technology, Journal Year: 2023, Volume and Issue: 12(5), P. 12 - 24

Published: June 20, 2023

The prediction of stock market prices based on the financial text sentiment classification using Machine Learning (ML) and Deep (DL) models is becoming popular among researchers in era Big Data (BD). Nevertheless, owing to lack extensive analysis, most developed ML DL failed achieve better results. Thus, for real-time polarity price, a Probability Tanh-Independently Recurrent Neural Network (PT-IndRNN)-based data Twitter proposed solve this problem. Primarily, by employing corresponding API, are extracted stored MongoDB database Apache Flume. This with historical big datasets taken pre-processed. Next, deploying Hadoop Distributed File System (HDFS) clustering, pre-processed real-time, as well dataset, combined separately. After that, features from clustered sentences. Then, utilizing Senti Word Net, sentences chosen Linear Scaling-Dwarf Mongoose Optimization Algorithm (LS-DMOA) converted negative positive scores. In end, texts classified PTh-Ind RNN, which proved obtaining reliable result values.

Language: Английский

---

Modified Extreme Learning Machine Algorithm with Deterministic Weight Modification for Investment Decisions based on Sentiment Analysis

Recent Advances in Computer Science and Communications, Journal Year: 2023, Volume and Issue: 16(8)

Published: Aug. 23, 2023

Background: A significant problem in economics is stock market prediction. Due to the noise and volatility, however, timely prediction typically regarded as one of most difficult challenges. sentiment-based price that takes investors' emotional trends into account overcome these difficulties essential. Objective: This study aims enhance ELM's generalization performance accuracy. Methods: article presents a new sentiment analysis based-stock method using modified extreme learning machine (ELM) with deterministic weight modification (DWM) called S-DELM. First, investor used prediction, which can considerably increase model's predictive power. Hence, convolutional neural network (CNN) classify user comments. Second, DWM applied optimize weights biases ELM. Results: The results experiments demonstrate S-DELM may not only accuracy but also shorten time, tendencies are proven help them achieve expected Conclusion: compared different variants ELM some conventional

Language: Английский

---

Deep Learning Model for Fusing Spatial and Temporal Data for Stock Market Prediction

Computational Economics, Journal Year: 2023, Volume and Issue: 64(3), P. 1639 - 1662

Published: Oct. 24, 2023

Language: Английский

---