Stock Price Prediction Research Articles

Integrating LSTM Networks with Mean-Variance Optimization for Enhanced Portfolio Construction: An Empirical Study on UK Stock Market

Portfolio optimization has long been a central theme in finance. With ongoing advancements in machine learning, there is a significant opportunity to integrate predictive methods into portfolio optimization. This paper proposes leveraging Long Short-Term Memory (LSTM) networks alongside the established Mean-Variance (MV) optimization framework to construct optimal portfolios. These portfolios aim to help financial investors effectively manage and mitigate risk while maximizing returns. The study meticulously screened the leading stocks of 12 prominent UK companies listed on the London Stock Exchange (LSE), known for their influence and visibility. Initially, the study applies the LSTM networks to predict stock price volatility and integrates these predictions into the MV model to allocate portfolio weights effectively. To underscore the superiority of the proposed approach, the study compares cumulative returns from portfolios optimized for maximum and minimum variance Sharpe ratios with real data against the FTSE100 index over the same period. The results demonstrate that the portfolio optimized with the maximum Sharpe ratio significantly outperforms both the conservative minimum variance portfolio and the FTSE100 index. This empirical evidence underscores the practical value of integrating advanced machine learning techniques with established financial theory, enabling more innovative and efficient investment strategies to meet the evolving needs of financial investors.

Trading Momentum in the U.S. Crude Oil Futures Market

This paper investigates if the Rate of Change (ROC), as a popular measure of momentum, can serve as a reliable technical analysis indicator to improve stock price prediction for U.S. West Texas Intermediate (WTI) crude oil futures market. The methodology centers on the application of the ROC and/or Moving Average (MA) price crossover/cross under strategies as a trading system. End of month futures prices of West Texas Intermediate (WTI) crude oil prices are collected for the period 28th May 2004 – 30th April 2024. The performance of the trading system is measured using both the Sharpe and Sortino ratios, thereby adjusting for total and downside risks. The model is also benchmarked against the naïve buy-and-hold strategy. Overall findings suggest a ROC based on 14-month periods outperform other momentum-based indicators, including when combined with price-crossover moving average strategies, and the naïve buy-and-hold strategy. After adjusting for the negative returns, the downside risk or semi-deviation amounted to 8.5%, and a Sortino value of 4.58. The Sortino value is however biased due to the 295% return witnessed in 2009. Findings have some vital policy implications for regulatory bodies and traders in the WTI crude oil energy futures market.

Stock price crash risk prediction based on high-low frequency dual-layer graph attention network

The phenomenon of a stock price crash involves a rapid, significant decrease in stock prices, severely impacting the market, investors, and the economy. This study introduces the BiGAT-GRU model, which combines Graph Attention Networks (GAT) and Gated Recurrent Units (GRU) to predict stock price crash risk by analyzing multi-scale investor sentiment propagation using data from Baidu search index and public opinion texts. The model demonstrates superior performance in predicting crash risk, providing valuable insights for policymakers and investors.

Enhancing Stock Price Prediction in the Indonesian Market: a Concave LSTM Approach with RunReLU

This study addresses the pressing need for improved stock price prediction models in the financial markets, focusing on the Indonesian stock market. It introduces an innovative approach that utilizes the custom activation function RunReLU within a Concave Long Short Term Memory (LSTM) framework. The primary objective is to enhance prediction accuracy, ultimately assisting investors and market participants in making more informed decisions. The research methodology used historical stock price data from ten prominent companies listed on the Indonesia Stock Exchange, covering the period from July 6, 2015, to October 14, 2021. Evaluation metrics such as RMSE, MAE, MAPE, and R2 were employed to assess model performance. The results consistently favored the RunReLU-based model over the ReLU-based model, showcasing lower RMSE and MAE values, higher R2 values, and notably reduced MAPE values. These findings underscore the practical applicability of custom activation functions for financial time series data, providing valuable tools for enhancing prediction precision in the dynamic landscape of the Indonesian stock market.

Stock Price Prediction Using Artificial Intelligence and Neural Networks

Predicting the stock prices is a very complex task, and to predict an almost accurate stock price,we need a robust and accurate algorithm which can analyze and compute the longer-term share prices.Several researcher’s equally in the world and different industries have been very interested in the stockmarket. Stock processes are correlated within the nature of the market and that is why it is difficult topredict the share price. This project aims at processing and analyzing huge volumes of data (live data)and running comprehensive algorithms on the dataset. The purpose of the paper is to understand theshortcomings of the current prediction algorithms and to provide a method using neural networks andartificial intelligence through which we can predict the shared values with accuracy.By using the proposed method, anyone can monitor the preferred stock in real-time and can invest in thestock to make the most money by buying a large number of shares at the cheapest price and sellingthem at the highest price..

Dung beetle optimization with deep learning approach for solving inverse problems in predicting financial futures

Leveraging deep learning (DL) to inverse problems has proven transformative in predicting financial futures, mainly in stock price prediction. In terms of financial markets, where predicting stock price is a challenging inverse problem, DL methods like long short-term memory networks (LSTM) and recurrent neural networks (RNN) demonstrate notable prowess. These techniques successfully capture complex patterns and dependencies in historical stock price information, learning to discern subtle correlations and fundamental market trends. DL facilitates the extraction of nuanced features by leveraging large datasets and sophisticated techniques, enabling accurate prediction of future stock prices. This intersection of advanced ML approaches and financial predicting signifies a paradigm shift in leveraging technology to navigate the complexity of the financial market and improves decision-making for traders and investors. This manuscript introduces a Dung Beetle Optimization with a Deep Learning Approach for Solving Inverse Problems in Predicting Financial Futures (DBODL-SIPPFF) technique. The DBODL-SIPPFF technique resolves the inverse problem and predicts the stock prices adequately. In addition, the DBODL-SIPPFF technique exploits data consistency (DC) optimizer to solve inverse problems. Primarily, linear scaling normalization (LSN) is applied for data normalization. The honey badger algorithm (HBA) is utilized for the feature selection. Moreover, convolutional long short-term memory (ConvLSTM) is used for stock price prediction. Lastly, the DBO technique is utilized for the optimum hyperparameter selection of the ConvLSTM model. The empirical assessment of the DBODL-SIPPFF technique takes place under diverse stock datasets. The obtained values stated that the DBODL-SIPPFF technique performs optimally over compared methods.

Stock Price Forecasting using N-Beats Deep Learning Architecture

Stock prices present unique forecasting challenges due to factors such as market volatility, investor sentiment, and economic indicators, which contribute to significant fluctuations in time series data. This paper addresses these complexities by applying Deep Learning (DL) models to predict stock prices, with a particular focus on the S&P 500 index. Although DL models have shown remarkable success in fields like image processing and natural language processing, they require specialized architectures to effectively handle time series forecasting. This study examines the Neural Basis Expansion Analysis for Interpretable Time Series Forecasting (N-BEATS) model, a novel DL architecture specifically tailored for time series data, using S&P 500 stock price data. The performance of N-BEATS is benchmarked against three baseline models: Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRU). The evaluation metrics include Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). Results indicate that the N-BEATS model consistently surpasses the other models in all metrics. Additionally, the Diebold-Mariano (DM) test further validates the superior predictive accuracy of the N-BEATS model compared to the alternatives. This research underscores the potential of the N-BEATS model to significantly improve stock price forecasting, offering valuable insights for investors, financial analysts, and other market participants.

Robustness Investigation of ML Models for Stock Price Prediction During Market Volatility: A Case Study of the Japanese Stock Market Amidst the COVID-19 Pandemic

In the evolving realm of financial markets, precise stock price prediction remains a pivotal challenge. This paper investigates the efficacy of traditional machine learning models for stock price forecasting, particularly during the high volatility phase induced by the COVID-19 pandemic, using the Japanese stock market as a case study. This study utilized a dataset from the JPX Tokyo Stock Exchange Prediction competition, selecting two stocks at random to avoid bias. After standardizing the data for consistency, this study employed linear regression and decision trees to project stock prices, comparing their performance during stable periods and the economic upheaval of the pandemic. The analysis revealed that both models' predictive capabilities were compromised during the pandemic, with the decision tree model particularly underperforming. In normal times, linear regression showed improved accuracy for stock 1301 in 2021, while for stock 6758, the model's performance declined. These findings underscore the necessity for robust models that can withstand market turbulences like those observed during the COVID-19 crisis. The research contributes to both academic discussions on financial forecasting and practical strategies for market participants navigating complex stock environments. Future work will focus on developing more resilient forecasting methods to address these challenges.

Stock market index prediction based on market trend using LSTM

The stock market data analysis has received interest as a result of technological advancements and the investigation of new machine learning models, since these models provide a platform for traders and business people to choose gaining stocks. The business price prediction is a challenging and extremely complex process due to the impact of several factors on company prices. The numerous patterns that the stock market goes, they have been the focus of extensive research and analysis by numerous experts. There are several large data sets accessible, an artificial intelligence and machine learning techniques are developing quickly, and because of the machine’s improved computational power, complex stock price prediction algorithms can be developed. This paper presents stock market index prediction based on market trend using long short-term memory (LSTM). Using built-in application programmable interface (API), Yahoo Finance offers a simple method to programmatically retrieve any historical stock prices of an organization using the ticker name. The standard and poor’s 500 index (S&P 500 index) include the firms that have been taken into consideration here. Utilizing the selected input variable, single-layer and multi-layer LSTM models are implemented, and the measurement parameters of mean absolute error (MAE), root mean square error (RMSE), and correlation coefficient (R) are used to compare each performance. Nearly all of the real closing price’s curve and the prediction curve’s closing price for test data overlap. A potential stock investor may benefit significantly from such a prediction by using it to make well-informed choices that would increase his earnings.

Analyzing Stock Price Prediction Models: A Comparative Study of Linear Regression and Decision Trees During the COVID-19 Pandemic

Stock market forecasting plays a vital role in financial decision making. In a volatile and uncertain situation like the COVID-19 pandemic, it is important for us to compare the accuracy of different models for forecasting. This study compares the performance of the Linear Regression (LR) algorithm and the Decision Tree (DT) algorithm in predicting the stock price of Pfizer Inc. before and during a pandemic. The study evaluates the accuracy and stability of the predictions using datasets before and during the pandemic. The results show that the prediction accuracy of LR is better than that of DT in both cases, although both accuracies decrease during the pandemic. The results of the study emphasize the need to consider external factors in the selection of forecasting models and suggest some lessons for future research, leading to the selection of more stable and accurate models under turbulent market conditions. It is worth noting that overfitting occurs when a model learns to capture noise in the data rather than the underlying patterns, leading to reduced generalization performance on unseen data. Future research should address this by exploring techniques such as regularization or cross-validation to mitigate overfitting and enhance the robustness of predictive models in dynamic market environments.

Stock Price Prediction in Indonesia's Mining Sector Using a Hybrid Conv1D-LSTM Model

This study presents a novel approach to forecasting stock prices in Indonesia's mining sector by leveraging a hybrid model combining Convolutional Neural Networks (Conv1D) and Long Short-Term Memory (LSTM) networks. Given the volatile nature of stock markets and the specific characteristics of the mining industry, accurate prediction models are essential for investors and analysts. The hybrid Conv1D-LSTM model integrates the feature extraction capabilities of Conv1D with the sequence learning strengths of LSTM, providing a robust framework for time series forecasting.

Predicting Stock Prices in the Pakistan Market Using Machine Learning and Technical Indicators

Predicting Stock Prices in the Pakistan Market Using Machine Learning and Technical Indicators

Portfolio Prediction using Deep Learning

This research investigates the use of Long Short-Term Memory (LSTM) networks for predicting stock prices and optimizing investment portfolios. Utilizing a dataset comprising the top 30 U.S. companies by market capitalization from 2009-12-31 to 2021-12-31, excluding AbbVie, Meta, and Tesla due to their later market listings, we demonstrate that LSTM models outperform conventional Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN) in generating accuracy and portfolio returns. By efficiently capturing long-term dependencies within stock price data, LSTMs offer more reliable predictions, which are crucial for optimizing investment portfolios. Our methodology involves data collection and preprocessing, model building using LSTM architecture, and evaluating performance using metrics such as mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), mean absolute percentage error (MAPE), and mean percentage error (MPE). The results indicate that LSTM models not only enhance prediction accuracy but also improve portfolio returns compared to equally weighted and market capitalization weighted portfolios. This research provides significant insights into the benefits of using advanced deep learning techniques like LSTMs for financial market predictions and portfolio management.

ANALYZING FINANCIAL RATIOS' IMPACT ON STOCKS RETURNS: CASE STUDY OF LQ45 INDEX 2014-2023

This study examines the correlation between fundamental financial metrics and stock returns of Indonesia's LQ45 Index over a 10-year period (2014-2023). The study aims to provide actionable insights for investors and companies by identifying the most critical financial metrics in predicting stock price movements. By analyzing data from 16 consistently listed Indonesian companies, the study focuses on stocks that have consistently maintained their position in the index over the past decade, a gap that has been underexplored in prior research. The study employs various statistical tests to validate the regression model, with hypothesis testing conducted through t-test and F-tests to determine the significance of financial ratios on stock returns. The analysis shows that Return on Equity, Price to Earnings Ratio (PER), Price to Book Value (PBV), Free Cash Flow per Share to Price (PFCF), and Dividend Payout Rate (DPR) have a significant positive effect on stock return. The research recommends that retail investors prioritize the PFCF ratio when evaluating potential stock investments. Transparency in financial reporting is essential, with companies encouraged to provide accurate and comprehensive financial statements, including clear reporting of key financial metrics, to build investor confidence.

Integrating PCA with deep learning models for stock market Forecasting: An analysis of Turkish stocks markets

Financial data such as stock prices are rich time series data that contain valuable information for investors and financial professionals. Analysis of such data is critical to understanding market behaviour and predicting future price movements. However, stock price predictions are complex and difficult due to the intense noise, non-linear structures, and high volatility contained in this data. While this situation increases the difficulty of making accurate predictions, it also creates an important area for investors and analysts to identify opportunities in the market. One of the effective methods used in predicting stock prices is technical analysis. Multiple indicators are used to predict stock prices with technical analysis. These indicators formulate past stock price movements in different ways and produce signals such as buy, sell, and hold. In this study, the most frequently used ten different indicators were analyzed with PCA (Principal Component Analysis. This study aims to investigate the integration of PCA and deep learning models into the Turkish stock market using indicator values and to assess the effect of this integration on market prediction performance. The most effective indicators used as input for market prediction were selected with the PCA method, and then 4 different models were created using different deep learning architectures (LSTM, CNN, BiLSTM, GRU). The performance values of the proposed models were evaluated with MSE, MAE, MAPE and R2 measurement metrics. The results obtained show that using the indicators selected by PCA together with deep learning models improves market prediction performance. In particular, it was observed that one of the proposed models, the PCA-LSTM-CNN model, produced very successful results.

A Study on Stock Price Prediction Based on Attention GCN-BiLSTM Modeling

It is of great significance to accurately predict stock price movements. By combining the R-Vine-Copula structure with the relationship between the conceptual sectors to which the stocks belong, the price correlation between stocks is measured and the adjacency matrix is constructed, and the model AGLSTM, which is constructed by combining the temporal attention mechanism, Graph Convolutional Neural Network and Bi-directional Long and Short-Term Memory Neural Network, is proposed to predict the price of 46 stocks from the constituent stocks of the SSE 50 by modeling them. The experimental results show that, compared with the baseline, the AGLSTM can predict the stock price. The experimental results show that compared with the baseline model, the MAE and RMSE results of the AGLSTM model predicted one step forward outperform all the comparison models, and the MAPE results are close to the best baseline model results. The results of MAPE are close to those of the best baseline model. Moreover, good results are also achieved in the experiment of multi-step forward prediction, which demonstrates the ability of AGLSTM model in long-term prediction and can provide some reference for investors to make investment decisions.

PREDIKSI HARGA SAHAM BERDASARKAN ROA, ROE, PBV, DER, EPS DAN PER MENGGUNAKAN MACHINE LEARNING

Stocks are one of the popular investment instruments in Indonesia, but they also come with high risks. According to a report from PT Central Securities Depository Indonesia (KSEI) on November 21, 2022, the number of investors in the Indonesian capital market has reached 10 million people, followed by 9.3 million mutual fund investors and 803 thousand investors in government securities. Therefore, a method is needed to accurately predict stock prices. This research aims to apply a Machine Learning method based on Recurrent Neural Network (RNN) to predict stock prices on the Indonesia Stock Exchange (IDX) using financial ratio variables as features. The study uses stock data on the IDX from the Kompas100 stock index from 2008 to 2022. The data is then converted, cleaned, and divided into training and testing data. The model is trained with the training data and tested with the testing data. To measure the model's performance, this research uses the Root Mean Square Error (RMSE) metric. The study finds that the best-performing model produces an RMSE of 14.08. Additionally, the research also discovers that the best combination of financial ratio variables for the machine learning model includes ROA, ROE, PBV, DER, EPS, and PER, compared to combinations such as EPS, ROE, PER, and DER, or ROA, ROE, EPS, and PBV. In conclusion, this study suggests that the Machine Learning method based on RNN can be used to predict stock prices on the IDX using financial ratio variables as features.

Comparative Analysis of Financial Forecasting Techniques in Machine Learning for Netflix Stock Price Prediction

Abstract - In the stock market, predicting the price of stocks is still a hot research issue. One of the most challenging tasks in the field of computation is prediction of the stock market. The prediction depends on a number of variables, including physiological vs. Physical elements, rational vs. irrational investor behavior, investor attitude, market rumors, etc. All these factors work together to make stock values unpredictable and very challenging to predict accurately. Supervised Machine Learning (SML) algorithms is used to predict future value by using past stock price data. ML approaches have the ability to reveal trends and knowledge that hadn't previously noticed, and they can be used to predict that are incredibly accurate. The primary objective of this project is to predict stock prices of Netflix for analyzing profit on day closing. Data was gathered between the years of 2002 and 2022, and separated into two parts: training set and testing set. Only the testing portion is to be used for the final forecast. Four machine learning algorithms such as linear regression, decision tree, MLP, and KNN are used to forecast the close value of the Netflix stock price. This project's output adds to the body of knowledge on predicting stock prices and offers investors some new information for accurate prediction of stock prices.

Predicting Economic Trends and Stock Market Prices with Deep Learning and Advanced Machine Learning Techniques

The volatile and non-linear nature of stock market data, particularly in the post-pandemic era, poses significant challenges for accurate financial forecasting. To address these challenges, this research develops advanced deep learning and machine learning algorithms to predict financial trends, quantify risks, and forecast stock prices, focusing on the technology sector. Our study seeks to answer the following question: “Which deep learning and supervised machine learning algorithms are the most accurate and efficient in predicting economic trends and stock market prices, and under what conditions do they perform best?” We focus on two advanced recurrent neural network (RNN) models, long short-term memory (LSTM) and Gated Recurrent Unit (GRU), to evaluate their efficiency in predicting technology industry stock prices. Additionally, we integrate statistical methods such as autoregressive integrated moving average (ARIMA) and Facebook Prophet and machine learning algorithms like Extreme Gradient Boosting (XGBoost) to enhance the robustness of our predictions. Unlike classical statistical algorithms, LSTM and GRU models can identify and retain important data sequences, enabling more accurate predictions. Our experimental results show that the GRU model outperforms the LSTM model in terms of prediction accuracy and training time across multiple metrics such as RMSE and MAE. This study offers crucial insights into the predictive capabilities of deep learning models and advanced machine learning techniques for financial forecasting, highlighting the potential of GRU and XGBoost for more accurate and efficient stock price prediction in the technology sector.

Developing a Dynamic Feature Selection System (DFSS) for Stock Market Prediction: Application to the Korean Industry Sectors

For several years, a growing interest among numerous researchers and investors in predicting stock price movements has spurred extensive exploration into employing advanced deep learning models. These models aim to develop systems capable of comprehending the stock market’s complex nature. Despite the immense challenge posed by the diverse factors influencing stock price forecasting, there remains a notable lack of research focused on identifying the essential feature set for accurate predictions. In this study, we propose a Dynamic Feature Selection System (DFSS) to predict stock prices across the 10 major industries, as classified by the FnGuide Industry Classification Standard (FICS) in South Korea. We apply 16 feature selection algorithms from filter, wrapper, embedded, and ensemble categories. Subsequently, we adjust the settings of industry-specific index data to evaluate the model’s performance and robustness over time. Our comprehensive results identify the optimal feature sets that significantly impact stock prices within each sector at specific points in time. By analyzing the inclusion ratios and significance of the optimal feature set by category, we gain insights into the proportion of feature classes and their importance. This analysis ensures the interpretability and reliability of our model. The proposed methodology complements existing methods that do not consider changes in the types of variables significantly affecting stock prices over time by dynamically adjusting the input variables used for learning. The primary goal of this study is to enhance active investment strategies by facilitating the creation of diversified portfolios for individual stocks across various sectors, offering robust models and feature sets that consistently demonstrate high performance across industries over time.