Open AccessOptimizing Stock market prediction using Long Short Term Memory
Author(s) -
R. Kavitha,
Sonal Singh
Publication year - 2019
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.j9824.119119
Subject(s) - stock market prediction , stock market , profit (economics) , stock (firearms) , financial engineering , data pre processing , computer science , feature engineering , econometrics , finance , data mining , artificial intelligence , economics , deep learning , engineering , microeconomics , mechanical engineering , paleontology , horse , biology
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.