Stock Prediction Research Articles

Associating deep learning and the news headlines sentiment for Bursa stock price prediction

Accurate stock price prediction is appealing to academics, economists, and financial analysts for its potential to increase profits. Although remarkable progress has been made in stock prediction accuracy, studies to explore the relationship between public sentiments and the prediction of stock price movement based on online news portals in Malaysia context are limited. Therefore, this study aims to determine whether news sentiments influence the movement of the Bursa stock price. The stock prediction model was implemented using long short-term memory (LSTM), with stock data from Bursa Malaysia between January 2017 and April 2022, and the root mean squared error (RMSE) value was calculated. In addition, LSTM prediction model was compared to the decision tree algorithm, and LSTM performed significantly better than the decision tree, particularly when using the New York stock exchange (NYSE) dataset. Furthermore, sentiment analysis was carried out using a Malaysian online news portal's business and financial news. The findings showed that i) news has a significant impact on Malaysian stock market price movement; ii) the RMSE of the LSTM model was improved by adding a parameter (news polarity values); and iii) the RMSE value generated is less than one for every company stock and is influenced by stock price and price change magnitude.

Stock Prediction using LSTM model

With the development of the times, investors are increasingly in demand for stock price forecasting. However, stock price fluctuations are full of uncertainty, making traditional machine learning algorithms more erroneous in long-term forecasting. Based on the LSTM model, this paper uses Tushare to obtain the historical price of stocks, and the optimal structure and best training parameters of the LSTM model in stock price prediction are determined experimentally. The prediction accuracy of the LSTM model was evaluated by MAE, and the best result was 69.15, which achieved accurate prediction of stock prices. Compared with the traditional SVR model and the ARMA model, the prediction results of LSTM are more in line with the actual value, and the prediction accuracy of the algorithm is higher.

Spatial correlation analysis and prediction of carbon stock of “Production-living-ecological spaces” in the three northeastern provinces, China

The “Production-Living-Ecological Space” (PLES) is a paramount indicator in the filed of territory space development and optimization in China, under the new era. Exploring the driving factors of the PLES'land expansion is of great significance for improving space utilization, mitigating severe climate changes, and promoting green, healthy and sustainable development. In the background of the “Carbon Emissions Peak and Carbon Neutrality” strategy, analyzing and predicting the carbon stock of PLES is effective to boosting the achievement of ‘Dual-Carbon’ vision. Based on the above research questions， this study constructs the PLES based on statistics about land use (Year 1990, 2000, 2010 and 2020) in three northeastern provinces, and reveals the spatial correlation of PLES’ carbon stock in the research area through ArcGIS spatial analysis and InVEST model. Then, the PLUS model was used to clarify the contribution of each driver to the conversion of space land, and to predict the distribution of the PLES pattern and the carbon stock's spatial correlation in 2030 and 2060 under the Natural-Development Scene and Ecological-Protection-Development Scene. Results show that: (1) The PLES in the three northeastern provinces of China is primarily green ecological space (55.71%) and agricultural production space (38.10%), while industrial production space (3.60%) and urban living space (2.76%) expand significantly, and green ecological space (−0.17%) and blue ecological space (−0.89%) are on a recession trend. Besides, 2000–2010 is the most intense period of all kinds of space land transformation in the study area. (2) Population density, proximity to roads at all levels, annual average temperature and elevation are the prime drivers of PLES’ profile within the scope of the study region, but the contribution rate is significant difference. (3) The urban living space decreases and the green and blue ecological space increases significantly in the predicted years under the scene of Natural-Development and Ecological-Protection development; the pattern of PLES is relatively stable in the predicted years under both scenarios. (4) The spatial correlation of carbon stock is closely related to the distribution of PLES, with the high-value significant regions primarily in the distribution region of green ecological space, otherwise, the low-value significant regions mostly concentrated in the region with complex spatial land use types and large spatial development intensity; the overall structure within the scope of the study region shows a layout of high value areas surrounding low value areas. It can show that insisting on the ecological civilization construction is an effective way to achieve sustainable development and practice the “double carbon” strategy; in the future spatial land use control, ecological protection measures should still be adopted to ensure the sustainable development and positive operation of the study area.

Exploiting Long Short-term Memory Neural Network for Stock Price Prediction

Stock as a high yield, high risk investment has been favored by the public. In order to increase the return on investing in stocks, investors need to predict stock prices. In the past, investors used traditional mathematical methods to make predictions. Now, neural networks are used by investors to predict stocks, which can improve the accuracy of stock forecasting. To further verify the effectiveness of these methods, this work discusses the effects of different network structures and hyperparameters on stock prediction models using short-term memory (LSTM) neural networks. The results show that deeper network layer can get better training effect, but it needs more training time, resulting in a lot of time waste. In addition, this experiment tests the prediction effect under different dropout parameters. The results show that the dropout function should not be too large or too small. Multiple experiments are needed to find an appropriate dropout value.

SISTEM PERAMALAN PENJUALAN MENGGUNAKAN METODE SINGLE EXPONENTIAL SMOOTHING BERBASIS WEB DI PT. SANGHIANG PERKASA

Nutrition Industry, does not have a stock prediction system. So far, PT Sanghiang has relied solely on the warehouse manager's estimates to make decisions about inventory for the next period. This is a problem because stockouts often occur, and sometimes there are insufficient supplies to fulfill orders. Therefore, to avoid such issues, there is a need for a system that can help predict stock levels and make informed decisions in planning future sales strategies. The objective of this research is to develop a web-based sales forecasting system for PT Sanghiang Perkasa and implement the Single Exponential Smoothing method in the forecasting system. The results of this research indicate that the Single Exponential Smoothing method achieves the best forecasting accuracy with an alpha value of 0.2 and a MAPE (Mean Absolute Percentage Error) of 4.01%. The sales forecast for Fitbar Choco Delight 22 G Multigrain in January 2023 is 121,741. Therefore, this method is considered highly accurate as it has the lowest MAPE value.

Research on Improved GRU-Based Stock Price Prediction Method

The prediction of stock prices holds significant implications for researchers and investors evaluating stock value and risk. In recent years, researchers have increasingly replaced traditional machine learning methods with deep learning approaches in this domain. However, the application of deep learning in forecasting stock prices is confronted with the challenge of overfitting. To address the issue of overfitting and enhance predictive accuracy, this study proposes a stock prediction model based on a gated recurrent unit (GRU) with reconstructed datasets. This model integrates data from other stocks within the same industry, thereby enriching the extracted features and mitigating the risk of overfitting. Additionally, an auxiliary module is employed to augment the volume of data through dataset reconstruction, thereby enhancing the model’s training comprehensiveness and generalization capabilities. Experimental results demonstrate a substantial improvement in prediction accuracy across various industries.

Perancangan Sistem Prediksi Pembelian Stok Masker dengan Metode Fuzzy Mamdani (Studi Kasus: Ud Masker Murah Jogja)

This research aims to design a fuzzy Mamdani-based prediction system to assist in stock management decision-making for masks at UD MASKER MURAH JOGJA. The system will provide recommendations for mask brands with the highest sales and revenue. The fuzzy Mamdani method is considered effective in addressing subjectivity and providing highly precise mask stock predictions. This research will also consider profit variables as additional attributes to enhance prediction accuracy. The prediction system will help UD MASKER MURAH JOGJA make informed decisions in mask stock management, with the goal of maximizing profits and overcoming subjectivity. The results obtained from the fuzzy Mamdani method will reduce subjectivity, and the developed web system will function as intended.

Comparison of ARIMA and Exponential Smoothing Models in Prediction of Stock Prices

Stock prices tend to show trends or seasonality or have random walk movements. Time series statistical models developed over time aid prediction of stock prices to assist informed decision-making for investors. These models provide quantitative information to financial specialists at the time of placing their buy–sell orders. The paper compares the movement of two univariate time series using two forecasting models—exponential smoothing and autoregressive integrated moving average (ARIMA) (p; d; q). We predict stock prices of selected 15 companies across three sectors (banking, pharmaceuticals, and Information technology) from NIFTY 50 data for the period April 01, 2016 to March 31, 2021. All these 15 companies are representative constituents of the three sectors within the Nifty 50 index. Performances of models were assessed through forecasting error measures such as root mean square error and mean absolute percentage error. Performances of both models were identical for nine stocks. Prediction based on ARIMA was more accurate for six stocks, whereas exponential smoothing model was a better indicator of stock prices in the case of one stock. However, the differences in error measures of the both the models are marginal, and parsimony principle may drive the choice of model.

Moments, shocks and spillovers in Markov-switching VAR models

To investigate how economies, financial markets or institutions can deal with stress, we often analyze the effects of shocks conditional on being in a recession or a bear market. MSVAR models are perfectly suited for such analyses because they combine gradual movements with sudden regime switches. In this paper, we develop a comprehensive methodology to conduct these analyses. We derive first and second moments conditional only on the regime distribution and propose impulse response functions for both moments. By formulating the MSVAR as an extended linear non-Gaussian VAR, all results are available in closed-form. We illustrate our methods with an application to stock and bond return predictability. We show how forecasts of means, volatilities and (auto-)correlations depend on the regimes. The effect of shocks becomes highly nonlinear, and they propagate via different channels. During bear markets, shocks have stronger effects on means and volatilities and die out more slowly.

Modeling soil accretion and carbon accumulation in deltaic rice fields

Rice cultivation is popular in low-lying areas such as deltas, but climate change threatens the viability of the crop. In recent decades, the resilience of deltas to sea level rise (SLR) has been influenced by the reduction of sediment load from rivers due to the construction of dams, disrupting natural deposition in deltaic plains. Sediment and organic matter accumulation in wetlands are key to vertical accretion in the face of SLR and soil organic carbon (SOC) sequestration. In this sense, deltaic rice fields can retain sediments as well as wetlands and promote SOC sequestration, which is effective in adapting to SLR. In the Ebro Delta, the sediments that reached the fields through irrigation channels were used to build up and form rice fields in the wetlands of the area. We hypothesize that this sedimentation has been key to vertical accretion and SOC sequestration in rice fields. These processes were simulated by developing a process-based cohort model inspired by accretion in marsh equilibrium models (MEM). The model was able to simulate the soil carbon profile of rice fields in the Ebro Delta, based on the soil-accretion concept and considering the spatial heterogeneity of the area. Its predictions of vertical accretion and carbon content were more accurate for mineral and clay-like soils than for organic and sandy soils. Topsoil decomposition rate and organic matter content were the parameters that most influenced predictions of total vertical accretion and final soil organic carbon stock. Simulations were carried out according to future climate change scenarios, considering restoration of river sediment flux, to evaluate effects on SOC sequestration and vertical accretion in rice fields. Results showed that only with significant river sediment restoration did rice fields show positive vertical accretion, which facilitates SOC sequestration.

Stock Price Prediction of PT. Jasa Marga (Persero) Tbk Using Linear Regression Algorithm

The Covid-19 pandemic that has occurred throughout the world has resulted in crises in various sectors, one of which is also affecting the economic sector. This has affected the movement of the index on several stocks listed on the Indonesian Stock Exchange (IDX). During the Covid-19 pandemic, stock price movements were very random with significant increases and decreases. Therefore, it is necessary to predict stock prices that can help investors to see investment prospects in the future. In this study, stock predictions from PT Jasa Marga (Persero) Tbk will be carried out using the Linear Regression algorithm. The linear regression method is usually used to make predictions by measuring the correlation between two or more variables. Historical data on the shares of PT Jasa Marga (Persero) Tbk used in this test were obtained from finance.yahoo.com from 2017-2023. The results of this study indicate that using the linear regression algorithm can predict prices with an RMSE value of 216.379.

Improved tests for stock return predictability

– Predictive regression methods are widely used to examine the predictability of (excess) stock returns by lagged financial variables characterized by unknown degrees of persistence and endogeneity. We develop a new hybrid test for predictability in these circumstances based on simple regression t-statistics. Where the predictor is endogenous, the optimal, but infeasible, test for predictability is based on the t-statistic on the lagged predictor in the basic predictive regression augmented with the current period innovation driving the predictor. We propose a feasible version of this augmented test, designed for the case where the predictor is an endogenous near-unit root process, using a GLS-based estimate of the innovation used in the infeasible test regression. The limiting null distribution of this statistic depends on both the endogeneity correlation parameter and the local-to-unity parameter characterizing the predictor. A method for obtaining asymptotic critical values is discussed and response surfaces are provided. We compare the asymptotic power properties of the feasible augmented test with those of a (non augmented) t-test recently considered in Harvey et al. and show that the augmented test is more powerful in the strongly persistent predictor case. We then propose using a weighted combination of the augmented statistic and the t-statistic of Harvey et al., where the weights are obtained using the p-values from a unit root test on the predictor. We find this can further improve asymptotic power in cases where the predictor has persistence at or close to that of a unit root process. Our final hybrid testing procedure then embeds the weighted statistic within a switching-based procedure which makes use of a standard predictive regression t-test, compared with standard normal critical values, when there is evidence for the predictor being weakly persistent. Monte Carlo simulations suggest that overall our new hybrid test displays superior finite sample performance to comparable extant tests.

A Dual-View Model for Stock Price Prediction of Internet-of-Thing Enterprises

In recent years, with the continuous development of the capital market and intelligent internet of things (IIoTs) technologies, investors have focused more on IIoTs enterprises’ stocks. Since the stocks of IIoTs enterprises have the characteristics of heavy capital flows and high stock price volatility, the effective prediction of IIoTs stock price changes plays an extremely important role in improving investment returns and controlling investment risks. According to the above characteristics, our model takes stock trend fluctuations and time series indicator changes into consideration and comprehensively captures IIoTs stock information from both the temporal domain and the spatial domain. Specifically, the proposed model is a dual-view model that incorporates selected trading indicators to predict the closing prices of stocks. In the first view, an RNN model is designed to enlarge the receptive field of the model. In the second view, we introduce an attention mechanism to extract the influences of individual stock trends on the forecasting target. To verify the validity of this prediction method, we compare it with six other stock prediction methods. The results show that on the Ping An (601318) and IFLYTEK (002230) datasets, our method achieves the best results, that is, the lowest RMSE values.

A knowledge graph–GCN–community detection integrated model for large-scale stock price prediction

Owing to uncertainty in the stock market, stock price prediction has always been a challenging research hotspot. In recent years, many stock prediction methods have used stock price series and technical indicators as inputs and the time series algorithm to predict, but they often ignore the influence of deeper factors such as the situation of the stock company and current situation of the stock industry. In addition, most of them predict based on small-scale stock datasets with limited characteristics and have certain defects such as bias, poor stability of prediction results, and lack of statistical significance tests on experimental results. To solve these problems, we propose a new method for stock price prediction based on knowledge graph (KG) and graph convolution neural network (GCN) models. First, stock KG is constructed, and the semantic relationships between stocks are described in the form of triples. Second, the correlations between stocks are quantified by fully utilizing their explicit/implicit relationships in the KG. Third, K-means, community detection (CD), and GCNs are merged to obtain accurate clustering results for similar stocks. Finally, the historical prices of similar stocks are used as the input characteristics of the time series models to predict stock price trends. We collect 4684 A-share market stocks in China from 2013 to 2019 and predicted the stock price trends for 762 of them. The experimental results and significance test show that the proposed method achieve the best accuracy, precision, and F1-measure on large-scale stock datasets and have the best stability, proving that the overall prediction effect outperforms that by state-of-the-art methods.

Pengaruh Likuiditas Dan Cash Flow Operation Terhadap Nilai Perusahaan serta dampaknya Terhadap Ketepatan Prediksi Saham

The impact of liquidity and cash flow operations on firm value and on the accuracy of stock predictions is the goal of this research. This study also examines the impact of liquidity and cash flow operations on the accuracy of stock predictions through firm value. The research sample consisted of 40 companies listed on the Indonesia Stock Exchange in 2019-2021 in the food and beverage and information technology sectors. The research model was tested by path analysis, using Stata software to test the direct and indirect effects. The results of the study prove that liquidity has a positive and significant effect on firm value. Cash flow operations have no effect and are negative on company value. The accuracy of stock predictions has a positive and significant effect on firm value. Liquidity has a positive and significant effect on the accuracy of stock predictions. Cash flow operations have no positive effect on the accuracy of stock predictions. Firm value is able to mediate a positive and significant relationship between liquidity and the accuracy of stock predictions. Firm value is not able to mediate and there is a negative relationship between cash flow operations and the accuracy of stock predictions.

Comparative Study of Machine Learning Algorithms towards Predictive Analytics

Background: The trend of the stock market prediction has always been challenging and confusing for investors There is tremendous growth in stock market prediction with the advancement of technology, machine learning, data science, and big data. The media and entertainment sector is one of the diverse sectors in the stock market. In the Indian stock market, Sensex and Nifty are the two indexes. The 2019 pandemic forced the movie theatres to shut down. As a result, distributors and film directors were not able to release their movies in theatres, and production also was stopped. Consequently, during the lockdown, people spent more time at home watching media. Resulting in a higher degree of media consumption. Objectives: The objective of the research is to predict the performance of the media and entertainment company's stock prices using machine-learning techniques. Investors will be benefited by maximizing the profit and minimizing the loss. Methods: The proposed stock prediction system is used to predict the stock values and find the accuracy of linear regression and logistic regression in machine learning algorithms for data science. Results: The experiments are conducted for the media and entertainment stock price data using Machine-learning algorithms. Media stock prices are considered as the input dataset. The model has been developed using the daily frequency of stock prices with different attributes. Conclusion: Thus, the media and entertainment stocks are predicted using linear regression and logistic regression. Using the above techniques, stock prices are predicted accurately to maximize profits and minimize the loss for the investors.

DEEP REINFORCEMENT LEARNING ON STOCK DATA

This study proposes using Deep Reinforcement Learning (DRL) for stock trading decisions and prediction. DRL is a machine learning technique that enables agents to learn optimal strategies by interacting with their environment. The proposed model surpasses traditional models and can make informed trading decisions in real-time. The study highlights the feasibility of applying DRL in financial markets and its advantages in strategic decision- making. The model's ability to learn from market dynamics makes it a promising approach for stock market forecasting. Overall, this paper provides valuable insights into the use of DRL for stock trading decisions and prediction, establishing a strong case for its adoption in financial markets. Keywords: reinforcement learning, stock market, deep reinforcement learning.

A STOCK PREDICTION SYSTEM USING TEKNIKAL INDICATORS WITH THE LSTM METHOD

The capital market industry in Indonesia is developing in a better direction so that the growth of new investors is also increasing. Until the end of February 2021, operational data from the Indonesian Stock Exchange (IDX) and data from the Indonesian Central Securities Depository (KSEI) recorded that the number of new capital market investors had increased by 16.35% or 634,350 investors, from the previous 3,880,753 investors. to 4,515,103 investors. The development of the capital market industry in Indonesia, which has increased investor interest in investing, is expected to mobilize public funds to support national economic development. Some companies that are familiar to the community are BCA, BNI, BRI and MANDIRI. This study attempts to forecast banking stock prices on the LQ45 index, using the Long Short-Term Memory (LSTM) method. LSTM is one of the Recurrent Neural Networks (RNN) which has good accuracy in predictions. The identified fields are Close, Open, RSI, MACD and MA. The evaluation method used in this prediction system is MAPE in the form of percent output.

A Hybrid Model Using PCA and BP Neural Network for Time Series Prediction in Chinese Stock Market with TOPSIS Analysis

The stock price changes rapidly and is highly nonlinear in the financial market. One of the common concerns of many scholars and investors is how to accurately predict the stock price and the trend of rising and falling in a short time. Machine learning and deep learning techniques have found their place in financial institutions thanks to the ability of time series data prediction with high precision. However, the prediction accuracy of these models is still far from satisfactory. Most existing studies use original, single prediction algorithms that cannot overcome inherent limitations. This study proposes a hybrid model using principal component analysis (PCA) and backpropagation (BP) neural networks. The historical records of China Merchants Bank are used for data collection from 2015 to 2021. PCA preprocesses the original data to reduce the dimensionality and is then adopted by the BP neural network to predict the stock closing price of China Merchants Bank. We compare and analyze the PCA–BP model with three training algorithms, and the results indicate that the Bayesian regularization algorithm performs best. Besides, we perform the stock prediction using a traditional exponential smoothing approach. The experiment results show that the predicted stock closing price is close to the actual value, and the mean absolute percentage error can reach 0.0130, which is more significant than the traditional approach. Furthermore, A TOPSIS approach is utilized to evaluate the robustness of the proposed model. Finally, we demonstrate the usability of the designed hybrid model by predicting the stock price of another selected stock.

Improved optimization model for forecasting stock directions (FSD)

The study of stock market price predictions is very important. The Recurrent Neural Network (RNN) has shown excellent results with this issue. There are two significant problems with using this strategy. One is that it constantly struggles with extensive neural network construction efforts and hyper-parameter adjustments. Two, it often fails to come up with a superior answer. The suggested model is proposed to optimize the network topology and hyper-parameters of the RNN model. RNN is utilized for effective forecasting of stock directions in this research. Additionally, the Improved Differential Evolution (IDE) method is used to tune the RNN's hyperparameters to their best potential. Utilizing the IDE method helps in achieving the best stock direction prediction results possible. The direction of Stock Prediction (SP) changes has been accurately predicted by the proposed model that is being presented. A series of tests on two popular benchmark datasets (AAPL and FB) revealed the superiority of the proposed model over the other strategies with accuracy of 99.02% and the loss close of 0.1% for training and testing.