LSTMSA: A Novel Approach for Stock Market Prediction Using LSTM and Sentiment Analysis

Sarkar, Abhijoy; Sahoo, Abhaya Kumar; Sah, Sourav; Pradhan, Chittaranjan

doi:10.1109/iccsea49143.2020.9132928

Cited by 16 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GRU is a variant of RNN. The authors [ 10 ], utilized stock price with a news sentiment score. They showed that analyzing the lengthy input sequences can significantly improve the accuracy of the LSTM based model.…”

Section: Related Workmentioning

confidence: 99%

“…Most of the earlier work rely only on the input data at time point t to predict stock trend at time point t+1. Recently, many studies adopted the stock prediction problem as a sequence learning problem where the input to the prediction model is a sequence of input at successive time points [8][9][10]. But there is little work that investigates the effectiveness of multiple input sequence length in quest of enhancing prediction performance.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

LSTM based stock prediction using weighted and categorized financial news

Usmani

Shamsi²

2023

PLoS ONE

View full text Add to dashboard Cite

A significant correlation between financial news with stock market trends has been explored extensively. However, very little research has been conducted for stock prediction models that utilize news categories, weighted according to their relevance with the target stock. In this paper, we show that prediction accuracy can be enhanced by incorporating weighted news categories simultaneously into the prediction model. We suggest utilizing news categories associated with the structural hierarchy of the stock market: that is, news categories for the market, sector, and stock-related news. In this context, Long Short-Term Memory (LSTM) based Weighted and Categorized News Stock prediction model (WCN-LSTM) is proposed. The model incorporates news categories with their learned weights simultaneously. To enhance the effectiveness, sophisticated features are integrated into WCN-LSTM. These include, hybrid input, lexicon-based sentiment analysis, and deep learning to impose sequential learning. Experiments have been performed for the case of the Pakistan Stock Exchange (PSX) using different sentiment dictionaries and time steps. Accuracy and F1-score are used to evaluate the prediction model. We have analyzed the WCN-LSTM results thoroughly and identified that WCN-LSTM performs better than the baseline model. Moreover, the sentiment lexicon HIV4 along with time steps 3 and 7, optimized the prediction accuracy. We have conducted statistical analysis to quantitatively assess our findings. A qualitative comparison of WCN-LSTM with existing prediction models is also presented to highlight its superiority and novelty over its counterparts.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

LSTM based stock prediction using weighted and categorized financial news

Usmani

Shamsi²

2023

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Likewise for a specific trading day, they recorded the open, close, high, and low prices of a specific stock for each organization. Dogra et al [7] performed a detailed study on many classifiers such as KNN, Random Forest, SVM (Support Vector Machine), and Naive Bayes [4][8] [11] on their efficacy in predicting stock trends. We can hence state that although the Naive Bayes model has substantially greater accuracy, the SVM [9] and f-measures of certain different algorithms such as Random Forest which states that they are overall better in performance.…”

Section: Literature Surveymentioning

confidence: 99%

Stock Prediction Application using Machine Learning

Gudekar¹

2022

IJSREM

View full text Add to dashboard Cite

The stock market is an exceptionally powerful market where nothing is basically as steady as a stone however as the innovation is overhauling there are numerous ways and strategies one can attempt to realize this powerful change and be arranged appropriately. This paper centers around such various strategies for progressively learning the market and its patterns. We have involved two distinct models for this paper and have additionally performed sentiment analysis on the tweets in regards to the organization or the stock, the model with the least mistake is the ideal and the most favored technique for prediction. The aftereffects of this arrangement have given an unmistakable and shrewd thought regarding the random ups and downs of the market and furthermore another methodology for investors with the goal that they know where they can wager their cash. The ARIMA model is giving the best accuracy for each stock. Key Words: ARIMA, Time Series, Forecasting, Sentiment Analysis, Stock Market Prediction, Tweets

show abstract

“…Recurrent neural networks (RNNs) in the NLP community are very popular these days. The LSTM cells are implemented in hidden layers [31]. These LSTM cells helps to remember the previous information and steps.…”

Section: Performing Evaluation Processmentioning

confidence: 99%

Prediction of the Stock Market Based on Machine Learning and Sentiment Analysis

Jishtu¹,

Prajapati²,

Fiaidhi³

2022

Preprint

View full text Add to dashboard Cite

<p>Nothing is rock-steady in the stock market, which isa very volatile market. Nevertheless, there are a variety of ways and approaches one may utilise to learn about this dynamic movement and be prepared for it as technology develops. The focus of this essay is on different methods for quickly identifying market trends. The suggested strategy is comprehensive because it includes pre-processing the stock market dataset, a range of feature engineering techniques, and the integration of a customised deep learning-based system for forecasting stock market price patterns. The best and most suggested method for prediction is the model with the least amount of error. In order to conduct this study, we used three distinct models and ran sentiment analysis on news articles mentioning the firm or the stock. The results of this classification have given investors additional information to help them make decisions about where to stake their money as well as clear and incisive insight into the market’s irregular ups and downs.</p>

show abstract

LSTMSA: A Novel Approach for Stock Market Prediction Using LSTM and Sentiment Analysis

Cited by 16 publications

References 5 publications

LSTM based stock prediction using weighted and categorized financial news

LSTM based stock prediction using weighted and categorized financial news

Stock Prediction Application using Machine Learning

Prediction of the Stock Market Based on Machine Learning and Sentiment Analysis

Contact Info

Product

Resources

About