Indexed In Scopus
  Scopus ID: 21100926589

Stock Price Prediction Using Long Short-term Memory

B. Veda Vidhya and Ajmeera Kiran

Abstract

One of the most difficult challenges facing investors in this day and age is trying to accurately predict stock values. Since the prices of stocks are very non-linear and fluctuate often, it is exceedingly difficult to make precise forecasts regarding their future performance. Prior to the advent of artificial intelligence, it was never simple to visualize them in an exact manner. People are now able to accurately measure and predict the tends of the stock market, which in turn is producing an abundant amount of profit for the companies. This is made possible by the exponential growth in techniques and algorithms for artificial intelligence (AI), machine learning (ML), and deep learning (DL). In this area, numerous different algorithms were developed to anticipate stock values; nevertheless, when compared to LSTM (Long Short-Term Memory), these other algorithms could not produce accurate results. This study focuses primarily on the application of a Recurrent Neutral Network (RNN) model known as LSTM to the problem of forecasting stock prices.

Published on: December 06, 2023
doi: 10.17756/nwj.2023-s4-080
Citation: Vidhya BV, Kiran A. 2023. Stock Price Prediction Using Long Short-term Memory. NanoWorld J 9(S4): S477-S482.

Download Citation (XML)

12 Downloads
Bitnami