Ai in Financial Forecasting: Optimized LSTM Framework for Robust Stock Price Prediction Utilizing Historical Time-Series Data

View at publisher Summarise with VIRAT
Authors: Jaspreet Singh, Anubhav Chib, Anshu Mehta
Cited by: 0
References: 15

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The intelligent systems are still an important usage area in financial forecasting because market data is stochastic in nature and nonlinear. In this paper, the data- driven model of stock trend prediction has been proposed based on Long Short-Term Memory (LSTM) network incorporating the use of temporal learning and deep sequence modelling to enhance the predictive performance of the model. Training of the model was done through 25 -year history of Apple Inc. (AAPL) available on Yahoo Finance and was compared with classical machine learning models, such as Random Forest, Support Vector Machine (SVM), XGBoost and Linear Regression. Results obtained in the experiment show that all the baseline strategies lose to the LSTM- based one with 92.6% prediction accuracy, MAE$=1.37$, RMSE$=1.62$, which is a 3.6 percentage point higher than the performance of traditional methods. These results show that the LSTM model is useful to identify the convoluted temporal dependence, nonlinear tendencies, and volatility patterns inherent in financial time-series data. The study is relevant to the design of intelligent decision support systems to support algorithmic trading and portfolio management to provide a dependable and flexible method to forecast financial data in dynamic markets in real-time.

Fields of Study & Subjects

Stock Market Forecasting Methods Time Series Analysis and Forecasting Hydrological Forecasting Using AI

Publication details

Journal / source
International Conference on Communication, Computing and Electronics Systems (ICCCES)
Pages
1895–1901
Publication date
21 January 2026
Language
EN