Predicting the Next Day's Closing Price of Stock Indices Using Machine Learning and Deep Learning Algorithms - Research paper

Sep 17, 2026

An effective approach for forecasting stock-index share prices is needed because prices fluctuate and are rarely constant. This study examines machine learning algorithms—including long short-term memory, artificial neural networks, and linear regression—for predicting the next day’s closing price. Models are trained on S&P 500 data from 1990–2023 collected via Yahoo Finance, using only 1-day lagged features. Performance is evaluated with MAE, R-squared, and MAPE, with linear regression performing best. The models are also applied to NASDAQ and Hang Seng, following the same performance trend.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages18

Reading Time45 min

AccessFree to download

Abstract

Introduction

INTERNATIONAL JOURNAL ON INFORMATICS VISUALIZATION [journal homepage :](journal homepage : www.joiv.org/index.php/joiv)[ www.joiv.org/index.php/joiv](journal homepage : www.joiv.org/index.php/joiv) Predicting the Next Day's Closing Price of Stock Indices Using Machine Learning and Deep Learning Algorithms Ahmad Firdaus Cayzer a,*, Yoon-Teck Bau a a Faculty of Computing and Informatics, Multimedia University, Persiaran Multimedia, Cyberjaya, Malaysia Corresponding author:*[ahmadfirdauscayzer@gmail.com](ahmadfirdauscayzer@gmail.com) Abstract—Share prices are a critical factor in a stock index’s worth but are never constant. Thus, an effective method of predicting share prices is needed. This is where machine learning comes in. This research discusses the applicability of machine learning algorithms, precisely long short-term memory, artificial neural networks, and linear regression in predicting share prices. Additionally, this research goes in-depth, explaining how each algorithm functions. These three algorithms were implemented using the financial dataset of the S&P 500, one of the more known stock indices out there. Data was collected from Yahoo Finance for 34 years, from 1990 to 2023. Then, the algorithms mentioned were used to train a model using the collected dataset. All three algorithms were measured using three performance metrics: mean absolute error, R-squared score, and mean absolute percentage error. The final implementation involved training them by only using 1-day lagged features to create a model that can predict the next day's closing price. All the algorithms performed considerably well, with linear regression being the best, followed by artificial neural networks and long shortterm memory being the worst. Finally, the implemented algorithms were used to predict the closing prices of other stock indices, NASDAQ and Hang Seng Index. All algorithms performed well and followed the same trend, wherein linear regression performed the best and long-and short-term memory the worst. Future research should be conducted to explore the possibilities of utilizing lagged features along with external features like GDP growth rate, political trends, etc. Keywords—Share price prediction; linear regression; long short-term memory; machine learning; deep learning. Manuscript received 15 Aug. 2024; revised 23 Oct. 2024; accepted 14 Nov. 2024. Date of publication 31 Mar. 2025. International Journal on Informatics Visualization is licensed under a Creative Commons Attribution-Share Alike 4.0 International License. I. INTRODUCTION Shares are a crucial aspect of the financial world. They represent ownership of a company or a stock index, and the share price indicates the company's value or stock index. Asthe performance of a company or index is never stagnant and always changing, this means that its inherent value is in a constant state of fluctuation. Hence, evaluating its share price value is a near-impossible task for those not specialized in this field. A study by [1] even says that “Nonlinearity and high volatility of financial time series have made it difficult to predict stock price”. This is where machine learning comes in. Machine learning is a subset of artificial intelligence (AI) where you develop algorithms that order the machine to do a specific task. The machine does this task via statistical patterns through the data that it has been fed. A group of authors also attested to machine learning by stating that its predictive power on historical data outperforms other methods of predictions [2]. Essentially, machine learning allows one to predict share prices within the financial world. Machine learning in this field is appealing because machine learning can analyze extreme quantities of data and detect significant patterns within the data. While humans could also do this, it requires expertise, knowledge, and significant time. Drawbacks that the machines do not have. The complication that machine

FAQs

Which algorithms are evaluated for predicting the next day’s closing price?

The paper evaluates long short-term memory, artificial neural networks, and linear regression.

What dataset and time span are used to train the models?

Training uses the S&P 500 financial dataset collected from Yahoo Finance for 34 years, covering 1990 to 2023.

How are predictions generated for the next day’s closing price?

The models are trained using only 1-day lagged features to predict the next day’s closing price.

Sep 17, 2026

Uploaded by Clementine