scholarly journals Optimizing Stock Market Prediction using Long Short Term Memory

2019 ◽  
Vol 9 (1) ◽  
pp. 2819-2823
Keyword(s):  
Stock Market ◽  
Financial Market ◽  
Stock Prices ◽  
Short Term Memory ◽  
Market Price ◽  
Data Set ◽  
Stock Market Prediction ◽  
Company Stock ◽  
Financial Gain ◽  
And Mathematics

Stock market prediction has been an important issue in the field of finance, engineering and mathematics due to its potential financial gain. Stock market prediction is a process of predicting the future value of a company stock or other financial instrument traded in financial market. Stock market prediction brings with it the challenge of proving whether the financial market is predictable or not, since stock market data is of high velocity. This project proposes a machine learning model to predict stock market price based on the data set available by using LSTM model for performing prediction by de-noising the data using wavelet transform and performing auto-encoding on the data. The process includes removal of noise, preprocessing, feature selection, data mining, analysis and derivations. This project focuses mainly on the use of LSTM algorithm along with a layer of neural network to forecast stock prices and allocate stocks to maximize the profit within the risk factor range of the stock buyers and sellers.

scholarly journals Convoluted Stock Market: Using Convolution Operation for Stock Market Prediction

2021 ◽  
Author(s):  
Yigit Alparslan ◽  
Edward Kim
Keyword(s):  
Computer Vision ◽  
Stock Market ◽  
Current Literature ◽  
Stock Prices ◽  
Stock Price ◽  
Short Term Memory ◽  
Stock Market Prediction ◽  
Convolution Operation ◽  
Price Data ◽  
Dollar Amount

Many studies in the current literature annotate patterns in stock prices and use computer vision models to learn and recognize these patterns from stock price-action chart images. Additionally, current literature also use Long Short-Term Memory Networks to predict prices from continuous dollar amount data. In this study, we combine the two techniques. We annotate the consolidation breakouts for a given stock price data, and we use continuous stock price data to predict consolidation breakouts. Unlike computer vision models that look at the image of a stock price action, we explore using the convolution operation on raw dollar values to predict consolidation breakouts under a supervised learning problem setting. Unlike LSTMs that predict stock prices given continuous stock data, we use the continuous stock data to classify a given price window as breakout or not. Finally, we do a regularization study to see the effect of L1, L2, and Elastic Net regularization. We hope that combining regression and classification shed more light on stock market prediction studies.

scholarly journals Indian Stock-Market Prediction using Stacked LSTM AND Multi-Layered Perceptron

2020 ◽  
Vol 9 (3) ◽  
pp. 1051-1055
Keyword(s):  
Stock Market ◽  
Short Term Memory ◽  
Stock Exchange ◽  
Future Research ◽  
Future Price ◽  
Data Set ◽  
Stock Market Prediction ◽  
The Future ◽  
Future Value ◽  
Indian Stock Market

We aim to construe the Stacked Long–Short term memory (LSTM) and Multi-layered perceptron intended for the NSE-Stock Market prediction. Stock market prediction can be instrumental in determining the future value of a company stock.It is imperative to say that a successful prediction of a stock's future price could yield significant profit which would be beneficial for those who invested in the pipeline of things including stock market prediction. The model uses the information pertaining to the stocks and contemplates the previous model accuracy to innovate the approach used in our paper. The experimental evaluation is based on the historical data set of National Stock Exchange (NSE). The proposed approach aims to provide models like Stacked LSTM and MLP which perform better than its contemporaries which have been achieved to a certain extent. This can be verified by the results embedded in the paper . The future research can be focused on adding more variables to the model by fetching live data from the internet as well as improving model by selecting more critical factors by ensemble learning.

scholarly journals Convoluted Stock Market: Using Convolution Operation for Stock Market Prediction

2021 ◽  
Author(s):  
Yigit Alparslan ◽  
Ethan Moyer ◽  
Edward Kim
Keyword(s):  
Computer Vision ◽  
Stock Market ◽  
Current Literature ◽  
Stock Prices ◽  
Stock Price ◽  
Short Term Memory ◽  
Stock Market Prediction ◽  
Convolution Operation ◽  
Price Data ◽  
Dollar Amount

Many studies in the current literature annotate patterns in stock prices and use computer vision models to learn and recognize these patterns from stock price-action chart images. Additionally, current literature also use Long Short-Term Memory Networks to predict prices from continuous dollar amount data. In this study, we combine the two techniques. We annotate the consolidation breakouts for a given stock price data, and we use continuous stock price data to predict consolidation breakouts. Unlike computer vision models that look at the image of a stock price action, we explore using the convolution operation on raw dollar values to predict consolidation breakouts under a supervised learning problem setting. Unlike LSTMs that predict stock prices given continuous stock data, we use the continuous stock data to classify a given price window as breakout or not. Finally, we do a regularization study to see the effect of L1, L2, and Elastic Net regularization. We hope that combining regression and classification shed more light on stock market prediction studies.

scholarly journals DAViS: a unified solution for data collection, analyzation, and visualization in real-time stock market prediction

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Suppawong Tuarob ◽  
Poom Wettayakorn ◽  
Ponpat Phetchai ◽  
Siripong Traivijitkhun ◽  
Sunghoon Lim ◽  
...  
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Data Collection ◽  
Stock Market ◽  
Real Time ◽  
Stock Prices ◽  
Contextual Information ◽  
Online News ◽  
Stock Prediction ◽  
Stock Market Prediction

AbstractThe explosion of online information with the recent advent of digital technology in information processing, information storing, information sharing, natural language processing, and text mining techniques has enabled stock investors to uncover market movement and volatility from heterogeneous content. For example, a typical stock market investor reads the news, explores market sentiment, and analyzes technical details in order to make a sound decision prior to purchasing or selling a particular company’s stock. However, capturing a dynamic stock market trend is challenging owing to high fluctuation and the non-stationary nature of the stock market. Although existing studies have attempted to enhance stock prediction, few have provided a complete decision-support system for investors to retrieve real-time data from multiple sources and extract insightful information for sound decision-making. To address the above challenge, we propose a unified solution for data collection, analysis, and visualization in real-time stock market prediction to retrieve and process relevant financial data from news articles, social media, and company technical information. We aim to provide not only useful information for stock investors but also meaningful visualization that enables investors to effectively interpret storyline events affecting stock prices. Specifically, we utilize an ensemble stacking of diversified machine-learning-based estimators and innovative contextual feature engineering to predict the next day’s stock prices. Experiment results show that our proposed stock forecasting method outperforms a traditional baseline with an average mean absolute percentage error of 0.93. Our findings confirm that leveraging an ensemble scheme of machine learning methods with contextual information improves stock prediction performance. Finally, our study could be further extended to a wide variety of innovative financial applications that seek to incorporate external insight from contextual information such as large-scale online news articles and social media data.

scholarly journals Understanding the Interdependency between the Nifty 50 Future Index and the Advanced Future Stock Market through Econometrics

2019 ◽  
Vol 8 (4) ◽  
pp. 3660-3664
Keyword(s):  
Hong Kong ◽  
Stock Market ◽  
Granger Causality ◽  
Foreign Exchange ◽  
Financial Market ◽  
Stock Prices ◽  
Economic Condition ◽  
The Future ◽  
Bidirectional Movement ◽  
High Degree

In recent times the stock market is accepted as a tool to measure the economic condition of a nation. It is found that the Indian financial market as highly volatile due to the lower value of rupees in foreign exchange with the dollar. This motivated the researchers to measure the interdependencies of [Nifty 50 future (India), Nikkei 225(Japan), NASDAQ 100 Futures (USA), Dow Jones 30 (USA), SSEC (China), Hang Seng Future (Hong Kong), and FTSE 100 (London)]. The analysis covers monthly stock prices for a period of 10years from April 2008 to March 2018. The measurement of interdependencies is studied through granger causality and correlation after the confirmation of the non-normality of data and stationary of data. The result shows a high degree of correlation between NASDAQ and Dow Jones shows 98.76% followed by 96.89% between Nifty 50 future and NASDAQ. The co-movement result of Nifty 50 future through granger causality states Nifty 50 future can explain the future stock market of Nikkei (Japan) and SSEC (China) and the Hang Seng future (Hong Kong) has a bidirectional movement with Nifty 50 futures. The study is useful for the investors to identify the interdependencies of the indices and understand the movement in a significant manner.

Fuzzy Crow Search Algorithm-Based Deep LSTM for Bitcoin Prediction

2020 ◽  
Vol 11 (4) ◽  
pp. 53-71
Author(s):  
Chandrasekar Ravi
Keyword(s):  
Stock Market ◽  
Stock Prices ◽  
Short Term Memory ◽  
Search Algorithm ◽  
Moving Average ◽  
Absolute Error ◽  
Rate Of Change ◽  
Flow Strength ◽  
Optimal Weights ◽  
Double Exponential

Prediction of stock market trends is considered as an important task and is of great attention as predicting stock prices successfully may lead to attractive profits by making proper decisions. Stock market prediction is a major challenge owing to non-stationary, blaring, and chaotic data and thus, the prediction becomes challenging among the investors to invest the money for making profits. Initially, the blockchain network is fed to the blockchain network bridge from which the bitcoin data is acquired that is followed with the bitcoin prediction. Bitcoin prediction is performed using the proposed FuzzyCSA-based Deep Long short-term memory (LSTM). At first, the flow strength indicators are extracted based on Double exponential moving average (DEMA), Rate of Change (ROCR), Average True Range (ATR), Simple Moving Average (SMA), and Moving Average Convergence Divergence (MACD) from the blockchain data. Based on the extracted features, the prediction is done using FuzzyCSA-based Deep LSTM, which is the combination of FuzzyCSA with Deep LSTM. Then, the CSA is modified using the fuzzy operator for determining the optimal weights in Deep LSTM. The experimentation of the proposed method is performed from the openly available dataset. The analysis of the method in terms of Mean Absolute Error (MAE), and Root Mean Square Error (RMSE) reveals that the proposed FuzzyCSA-based Deep LSTM acquired a minimal MAE of 0.4811, and the minimal RMSE of 0.3905, respectively.

scholarly journals Stock Prediction Using Sentiment Analysis and LSTM

2021 ◽  
Vol 9 (9) ◽  
pp. 1752-1756
Author(s):  
Ms. Anjima K. S
Keyword(s):  
Stock Market ◽  
Sentiment Analysis ◽  
Programming Language ◽  
Stock Prices ◽  
Short Term Memory ◽  
Short Term ◽  
Term Memory ◽  
Python Programming Language ◽  
Long Short Term Memory ◽  
Python Programming

Abstract: The stock market is a difficult area to anticipate since it is influenced by a variety of variables at the same time. The stock exchange is where equities are exchanged, transferred, and circulated. This research proposes a hybrid algorithm that predicts a stock's next day closing prices using sentiment analysis and Long Short Term Memory. The LSTM model seems to be quite popular in time-series forecasting, which is why it was selected for this project. Our proposed methodology makes use of the temporal association between public opinion and stock prices. Part-of-speech tagging is used to do sentiment analysis, and Long Short Term Memory is utilized to predict the stock's next day closing price. When these two factors are combined, we get a good picture of the stock's future. In this project, two main datasets have been used: HCLTECH company stock data and the news related to each stock of the HCL company for each day. The project is implemented by using the python programming language. The python programming language has been used to execute the project. This also incorporates machine learning along with public feedback. Sentiment analysis enables us to evaluate a diversity of political and economic factors, which have a significant impact on the stock market. Keywords: LSTM, sentiment analysis, RNN, Back propagation neural network.

Sign in / Sign up

Export Citation Format

Share Document