Stock data

This paper deals with the problem of combining predictive densities for financial series. We summarize the general combination approach based on a Bayesian state space representation of the predictive densities and of the combination scheme which allows for incomplete model space proposed by Billio et al. [2010]. In the combination model the weights follow logistic autoregressive processes, change over time and their dynamics are possible driven by the past forecasting performances of the predictive densities. For illustrative purposes we apply it to combine White Noise and GARCH models to forecast the Amsterdam Exchange index and use the combined predictive forecasts in an investment asset allocation exercise.

This paper deals with the problem of combining predictive densities for financial series. We summarize the general combination approach based on a Bayesian state space representation of the predictive densities and of the combination scheme which allows for incomplete model space proposed by Billio et al. [2010]. In the combination model the weights follow logistic autoregressive processes, change over time and their dynamics are possible driven by the past forecasting performances of the predictive densities. For illustrative purposes we apply it to combine White Noise and GARCH models to forecast the Amsterdam Exchange index and use the combined predictive forecasts in an investment asset allocation exercise.

Navigating the complex terrain of financial markets requires accurate forecasting tools, underscoring the need for effective forecasting methods to assist investors and policymakers alike. This paper explores deep learning techniques for forecasting the Moroccan all shares index (MASI), a prominent indicator of the Moroccan stock market. The study aims to evaluate the performance of technical indicators in enhancing the accuracy of MASI predictions. A comprehensive dataset of daily closing prices of the MASI index is collected and 26 technical indicators are computed from the historical price data. Deep learning models based on artificial neural networks (ANNs) are trained and optimized using the dataset. The performance of the models is evaluated using standard metrics such as mean absolute error (MAE), mean square error (MSE), mean absolute percentage error (MAPE), and root mean square error (RMSE). Additionally, feature selection techniques are employed to identify the subset of technical indicators that contribute most significantly to the prediction accuracy. The findings provide insights into the effectiveness of deep learning models and the impact of technical indicators on MASI prediction accuracy. This research has important implications for investors, financial analysts, and policymakers, enhancing investment strategies and risk management approaches.

Navigating the complex terrain of financial markets requires accurate forecasting tools, underscoring the need for effective forecasting methods to assist investors and policymakers alike. This paper explores deep learning techniques for forecasting the Moroccan all shares index (MASI), a prominent indicator of the Moroccan stock market. The study aims to evaluate the performance of technical indicators in enhancing the accuracy of MASI predictions. A comprehensive dataset of daily closing prices of the MASI index is collected and 26 technical indicators are computed from the historical price data. Deep learning models based on artificial neural networks (ANNs) are trained and optimized using the dataset. The performance of the models is evaluated using standard metrics such as mean absolute error (MAE), mean square error (MSE), mean absolute percentage error (MAPE), and root mean square error (RMSE). Additionally, feature selection techniques are employed to identify the subset of ...

The approach stated in this paper mainly focuses on generating optimized rules in fragment based association mining using genetic algorithm. we call this approach as Genetic based Fragment Rule Mining. we designed a novel method for generation of optimized rule. In which a Fragment mining is used to generate the rules on which we use the optimization mechanism. This deals mainly with reducing the time and space complexity required in processing the data using fragment mining & generate strong rules using genetic algorithm. The results reported in this paper are very promising since the discovered rules are of optimized rules.

Navigating the complex terrain of financial markets requires accurate forecasting tools, underscoring the need for effective forecasting methods to assist investors and policymakers alike. This paper explores deep learning techniques for forecasting the Moroccan all shares index (MASI), a prominent indicator of the Moroccan stock market. The study aims to evaluate the performance of technical indicators in enhancing the accuracy of MASI predictions. A comprehensive dataset of daily closing prices of the MASI index is collected and 26 technical indicators are computed from the historical price data. Deep learning models based on artificial neural networks (ANNs) are trained and optimized using the dataset. The performance of the models is evaluated using standard metrics such as mean absolute error (MAE), mean square error (MSE), mean absolute percentage error (MAPE), and root mean square error (RMSE). Additionally, feature selection techniques are employed to identify the subset of ...

The approach stated in this paper mainly focuses on minimizing the length of the transaction table of the stock market, based on some common features among the attributes which indirectly minimize the complexity involved in processing; we call this approach as Fragment Based Mining. This deals mainly with reducing the time and space complexity involved in processing the data. Experimentally we try to show our approach is promising one. We conclude that this approach can potentially be used for predictions and recommendations stock trading platforms.

In this research we mainly focus on overcoming the drawbacks in FITI approach in predicting the stock market and propose a new approach called fragment based mining which gives some promising results as compared to FITI. FITI consists of all the transaction from the stock market some of which are not necessary and simply increases the overhead in processing the data, so we improve this by reducing the number of transactions using some aggregate functions, so the time needed to process the transactions will be less and generate some efficient rules from which we predict the stock market behavior. This research is purely based on the data mining technique called association mining. Association rules suites the behavior of stock market and helps in analyzing the associations among the companies. As mentioned above we propose a technique Fragment Based mining which helps in minimizing the input transaction table size which leads to reduced processing time. Keywords— FITI; Fragment Based...

The previous work is carried out on sliding window approach for fragment mining rules which results in large & complex processing the data. In this paper we present an idea to find out association within inter-transaction with different windowing approach. These approaches first minimizes the huge input dataset using tumbling window approach and then apply fragment mining to generate rules among different transactions with window length. This experimental work find out effect of different windowing approaches and select the best windowing method which will best suited for processing huge amount of data with minimum complexity . We conclude that this approach is promising one and will be suitable for predictions and useful in stock trading platforms for proper investment in Indian Stock market depend on finance sector. Keywordssliding window, tumbling window, stock market, fragment mining.

In this research we propose an idea of using a JStock framework for getting accuracy of stock market prediction algorithms. Stock Market is the most unpredictable, popular and a big resource of income all over the world. Many researches are done for predicting the future market prices. Various algorithms lead to varying amount of accuracy. The proposed work will compare the various predictions made by the indicators and algorithms and will lead to a proper testing tool for checking accuracy of the stock market predictors. We have used JStock an open source software which analyses stock market by using technical indicators. By using the data provided by yahoo finance and the data extraction methods of JStock, we try to analyze the various stock market prediction methods and try to compare their accuracy. The performance of this testing is checked by the dataset provided by yahoo finance of Indian Stock markets and particular Indian Companies. However, they are less accurate in case o...

The globalization in market, foreign investment and effect of current news issues makes difficult for investor to take better decisions. This paper introduces a new algorithm CII and describes the process of finding best association rules which is promising one to forecast the market. This experimental work reduces the time required for processing huge stock data and extract best rules with minimum window size to proper investment in stock market.

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.

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&...

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

Stock market data is considered to be one of the chaotic data in nature. Analyzing the stock market and predicting the stock market has been the area of interest among the researchers for a long time. In this paper, we have stepped forward and used a deep learning algorithm with classification to predict the behavior of the stock market. LSTM deep learning algorithm is used with an optimization algorithm to formulate the hyperparameters. To further improve the accuracy of prediction the stock data is first given to a classification algorithm to reduce the number of input parameters. In this research technical indicators are subjected to classification and deep LSTM algorithm which are both integrated to improve the accuracy of prediction. deep LSTM hyperparameters are trained using the optimization algorithm. In this paper infosys and zensar stocks data is collected from the Indian stock market data i.e. both national stock exchange (NSE) and bombay stock exchange (BSE). The proposed approach is applied on Infosys and Zensar share values, the prediction accuracy obtained by employing this integrated approach of classification and LSTM has given a prominent value of MSE and RMSE as 1.034 and 1.002 respectively.