Research Article
Enhancing Stock Market Prediction Through LSTM Modeling and Analysis
@INPROCEEDINGS{10.4108/eai.2-6-2023.2334692, author={Weihao Huang}, title={Enhancing Stock Market Prediction Through LSTM Modeling and Analysis}, proceedings={Proceedings of the 2nd International Conference on Information Economy, Data Modeling and Cloud Computing, ICIDC 2023, June 2--4, 2023, Nanchang, China}, publisher={EAI}, proceedings_a={ICIDC}, year={2023}, month={8}, keywords={neural network stock price prediction long short term memory;}, doi={10.4108/eai.2-6-2023.2334692} }- Weihao Huang
Year: 2023
Enhancing Stock Market Prediction Through LSTM Modeling and Analysis
ICIDC
EAI
DOI: 10.4108/eai.2-6-2023.2334692
Abstract
The pursuit of profitable stock investments has driven the exploration of advanced techniques in data mining, machine learning, and mathematical models. Neural networks, particularly Long Short-Term Memory (LSTM) models, have emerged as highly successful tools due to their autonomous learning capabilities, stability, and capacity to represent intricate concepts. This research focuses on leveraging the LSTM model to predict future prices of GOOGL stocks based on historical price data. The study incorporates six essential indicators (Open, Close, High, Low, Adj Close, Volume) as inputs, employing min-max normalization and time steps for data preprocessing. Through a comparative analysis of models trained on different stock history datasets, the LSTM model surpasses the predictive performance of Xu and Cohen's model by 35.18% and K. Ullah and M. Qasim's model by 5.86%. These findings underscore the efficacy of the LSTM model in accurately forecasting Google stock prices, highlighting its potential for informed decision-making in stock investment strategies.