Library

A Robust Stock Price Prediction using improved Linear Regression Model with LSTM improved Feature Selection Process

The ability of deep learning models to catch complicated patterns in financial data has led to their increased use in recent years for the crucial job of stock price prediction. Using a mix of regression and recurrent neural networks for improved feature selection process, we suggest a deep learning-based method for stock price forecast in this research. The proposed method shows better accuracy than other previous methods with training accuracy of 100%, validation accuracy of 99%, and final testing accuracy of 96%. The proposed method also shows lower errorscores as compared to other previous methods: a mean absolute percentage error (MAPE) of 1.45, a mean square error (MSE) of 1.48, a root mean square error (RMSE) of 1.22, and a mean absolute error (MAE) of 0.76.

Computer ScienceBusiness
View graphSource

Paper

Full text

PDF

A Robust Stock Price Prediction using improved Linear Regression Model with LSTM improved Feature Selection Process

Semantic Scholar · Computer Science · 2023

Abstract

The ability of deep learning models to catch complicated patterns in financial data has led to their increased use in recent years for the crucial job of stock price prediction. Using a mix of regression and recurrent neural networks for improved feature selection process, we suggest a deep learning-based method for stock price forecast in this research. The proposed method shows better accuracy than other previous methods with training accuracy of 100%, validation accuracy of 99%, and final testing accuracy of 96%. The proposed method also shows lower errorscores as compared to other previous methods: a mean absolute percentage error (MAPE) of 1.45, a mean square error (MSE) of 1.48, a root mean square error (RMSE) of 1.22, and a mean absolute error (MAE) of 0.76.

Source of record · Semantic Scholar

Similar papers

A COMPARATIVE ANALYSIS FOR STOCK PRICE PREDICTION USING IMPROVED EXPANSIVE DEEP LSTM MODELPankaj Rambhau Patil, Deepa Parasar, Shrikant Charhate2022 · Indian Journal of Computer Science and Engineering In Library
Profitability Analysis in Stock Investment Using an LSTM-Based Deep Learning ModelJaydip Sen, Abhishek Dutta, Sidra Mehtab2021 · 2021 2nd International Conference for Emerging Technology (INCET) · 18 citations In Library
Stock Market Prediction Using a Deep Learning ApproachThitimanan Damrongsakmethee, V. Neagoe2020 · European Conference on Artificial Intelligence · 15 citations In Library
Stock Price Prediction using Recurrent Neural Network and LSTMPasala Sandhya, Raswitha Bandi, D. Dakshayani Himabindu2022 · 2022 6th International Conference on Computing Methodologies and Communication (ICCMC) In Library
Long Short-Term Memory Network (LSTM) based Stock Price PredictionAkshat Gaurav, V. Arya, K. Chui et al.2023 · Research in Adaptive and Convergent Systems · 7 citations In Library
Improving Stock Price Prediction using Linear Regression and Long Short-Term Memory Model (LR-LSTM)Haoyan Wu2023 · BDEIM · 2 citations In Library
Robust Analysis of Stock Price Time Series Using CNN and LSTM-Based Deep Learning ModelsSidra Mehtab, Jaydip Sen, S. Dasgupta2020 · arXiv.org · 67 citations In Library
Stock Market Prediction using Recurrent Neural Network’s LSTM ArchitectureKoushik Sutradhar, Sourav Sutradhar, Iqbal Ahmed Jhimel et al.2021 · Ubiquitous Computing, Electronics & Mobile Communication Conference · 7 citations In Library
Deep Learning-Based Stock Price Prediction Using LSTM and Bi-Directional LSTM ModelMerin Sunny, M. Maswood, Abdullah G. Alharbi2020 · Novel Intelligent and Leading Emerging Sciences Conference · 247 citations In Library
Forecasting stock prices in two ways based on LSTM neural networkJingyi Du, Qingli Liu, Kang Chen et al.2019 · 2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC) · 32 citations In Library
© 2026 NYSGPT2525 LLC