Browse Items (5511 total)
Sort by:
-
Deep learning framework for stock price prediction using long short-term memory
Forecasting stock prices is always considered as complicated process due to the dynamic and noisy characteristics of stock data influenced by external factors. For predicting the stock market, several approaches have been put forward. Many academics have successfully forecasted stock prices using soft computing models. Recently, there has been growing interest in applying deep learning techniques in combination with technical indicators to forecast stock prices, attracting attention from both investors and researchers. This paper focuses on developing a reliable model for anticipating future stock prices in one day advance using Long Short-Term Memory (LSTM). Three steps make up the suggested model. The approach begins with ten technical indicators computed from previous data as feature vectors. The second phase involves data normalization to scale the feature vectors. Finally, in the third phase, the LSTM model analyzes the closing price for the next day using the normalized characteristics as input. Two stock markets, NASDAQ and NYSE are chosen to evaluate the efficacy of the developed model. To demonstrate how effective the new model is in making predictions, its performance is compared to earlier models. Comparing the suggested model to other models, the findings revealed that it had a high level of prediction accuracy. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024. -
Convolutional neural network for stock trading using technical indicators
Stock market prediction is a very hot topic in financial world. Successful prediction of stock market movement may promise high profits. However, an accurate prediction of stock movement is a highly complicated and very difficult task because there are many factors that may affect the stock price such as global economy, politics, investor expectation and others. Several non-linear models such as Artificial Neural Network, fuzzy systems and hybrid models are being used for forecasting stock market. These models have limitations like slow convergence and overfitting problem. To solve the aforementioned issues, this paper intends to develop a robust stock trading model using deep learning network. In this paper, a stock trading model by integrating Technical Indicators and Convolutional Neural Network (TI-CNN) is developed and implemented. The stock data investigated in this work were collected from publicly available sources. Ten technical indicators are extracted from the historical data and taken as feature vectors. Subsequently, feature vectors are converted into an image using Gramian Angular Field and fed as an input to the CNN. Closing price of stock data are manually labelled as sell, buy, and hold points by determining the top and bottom points in a sliding window. The duration considered over a period from January 2009 to December 2018. Prediction ability of the developed TI-CNN model is tested on NASDAQ and NYSE data. Performance indicators such as accuracy and F1 score are calculated and compared to prove effectiveness of the proposed stock trading model. Experimental results demonstrate that the proposed TI-CNN achieves high prediction accuracy than that of the earlier models considered for comparison. 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature. -
Forecasting intraday stock price using ANFIS and bio-inspired algorithms
The main focus of this study is to explore the predictability of stock price with variants of adaptive neuro-fuzzy inference system (ANFIS) and suggests a hybrid model to enhance the prediction accuracy. Two variants of ANFIS model are designed which includes genetic algorithm-ANFIS (GA-ANFIS) and particle swarm optimisation-ANFIS (PSO-ANFIS) to forecast stock price more accurately. The standard ANFIS is tuned employing GA and PSO algorithm. The experimental data used in this investigation are stocks traded per minute price of four companies from NSE. Sixteen technical indicators are calculated from the historical prices and used as inputs to the developed models. Prediction ability of the developed models is analysed by varying number of input samples. Numerical results obtained from the simulation confirmed that the PSO-ANFIS model has the potential to predict the future stock price more precisely than GA-ANFIS as well as other earlier methods. Copyright 2021 Inderscience Enterprises Ltd. -
Stock market prediction using subtractive clustering for a neuro fuzzy hybrid approach
Stock market prediction is the challenging area for the investors to yield profits in the financial markets. The investors need to understand the financial markets which are more volatile and affected by many external factors. This paper proposes a subtractive clustering based adaptive neuro fuzzy approach for predicting apple stock data prices. The research data used in this study is from 3rd Jan 2005 to 30th Jan 2015. Four technical indicators are proposed in this study. They are Simple moving average for 1week, simple moving average for 2weeks, 14days Disparity and Larry Williams R%. These variables are used as inputs to the neuro fuzzy system to predict the daily apple stock prices. Also, this study compares the proposed work with the ANFIS training method and subtractive clustering method etc. The performance of all these models is analyzed. The measures like training error, testing error, number of rules and number of parameters are calculated and compared for analysis. From the simulation results, the average performance of subtractive clustering based neuro fuzzy approach was found considerably better than the other networks. 2017, Springer Science+Business Media, LLC. -
Forecasting gold prices based on extreme learning machine
In recent years, the investors pay major attention to invest in gold market because of huge profits in the future. Gold is the only commodity which maintains its value even in the economic and financial crisis. Also, the gold prices are closely related with other commodities. The future gold price prediction becomes the warning system for the investors due to unforeseen risk in the market. Hence, an accurate gold price forecasting is required to foresee the business trends. This paper concentrates on forecasting the future gold prices from four commodities like historical data's of gold prices, silver prices, Crude oil prices, Standard and Poor's 500 stock index (S & P500) index and foreign exchange rate. The period used for the study is from 1st January 2000 to 31st April 2014. In this paper, a learning algorithm for single hidden layered Feed forward neural networks called Extreme Learning Machine (ELM) is used which has good learning ability. Also, this study compares the five models namely Feed forward networks without feedback, Feed forward back propagation networks, Radial basis function, ELMAN networks and ELM learning model. The results prove that the ELM learning performs better than the other methods. 2006-2016 by CCC Publications. -
Prediction of stock market price using hybrid of wavelet transform and artificial neural network
Background/Objectives: Accurate prediction of stock market is highly challenging. This paper presents a forecasting model based on Discrete Wavelet Transform (DWT) and Artificial Neural Network (ANN) for predicting financial time series. Methods/Statistical analysis: The idea of forecasting stock market prices with discrete wavelet transform is the central element of this paper. The proposed forecasting model uses the Discrete Wavelet Transform to decompose the financial time series data. The obtained approximation and detail coefficients after decomposition of the original time series data are used as input variables of back propagation neural network to forecast future stock prices. Approximation coefficients can characterize the coarse structure of the data and detail coefficients capture ruptures, discontinuities and singularities in the original data, to recognize the long-term trends in the original data. Findings: The proposed model was applied to five datasets. For all of the datasets, accuracy measures showed that the presented model outperforms a conventional model. It also proved that the hybrid forecasting technique has achieved better results compared with the approach which is not using the wavelet transform. Applications/Improvements: The accuracy of the proposed hybrid method can also be improved by developing a model using artificial neural network with Adaptive Neuro Fuzzy Interference System. -
Foreign exchange rate forecasting using Levenberg-Marquardt learning algorithm
Background/Objectives: Foreign currency Exchange (FOREX) plays a vital role for currency trading in the international market. Accurate prediction of foreign currency exchange rate is a challenging task. The paper investigates the FOREX prediction using feed forward neural network. Methods/Statistical analysis: This paper employs artificial neural network to forecast foreign currency exchange rate in India during 2010-2015.The exchange rates considered between Indian Rupee and four major currencies Euro, Japanese Yen, Pound Sterling and US Dollar. The network developed consists of an input layer, hidden layer and output layer. The neural network was trained with Levenberg-Marquardt (LM) learning algorithm. Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and Forecasting Error (FE) are used as indicators for the performance of the networks. Findings: Simulation results are presented to show the performance of the proposed system. The paper also aims to suggest about network topology that must be chosen in order to fit time series kind of complicated data to a neural network model. The proposed technique gives the evidence that there is possibility of extracting information hidden in the foreign exchange rate and predicting into the future. Applications/Improvements: Finally, this paper presents the best network topology for FOREX prediction by comparing the effectiveness of various hidden layer performance algorithm using MATLAB neural network software as a tool. -
Business intelligence techniques for customer relationship management in the banking sector /
International journal Of Applied Engineering Research, Vol.10, Issue 79, pp.835-838, ISSN No: 0973-4562. -
Radon transform based image steganography in frequency domain /
International journal Of Applied Engineering Research, Vol.10, Issue 70, pp.830-834, ISSN No: 0973-4562. -
Predicting the stock price index of yahoo data using elman network /
International Journal of Control Theory and Applications, Vol.10, Issue 10, pp.481-497, ISSN: 0974-5572. -
Stock market prediction using subtractive clustering for a neuro fuzzy hybrid approach /
Cluster Computing (The Journal Of Networks, Software Tools And Applications), Vol.22, pp.13159–13166. -
Forecasting gold prices based on extreme learning machine /
International Journal Of Computers Communications & Control, Vol.11, Issue 3, pp.372-380, ISSN: 1841-9836. -
Prediction of stock market price using hybrid of wavelet transform and artificial neural network /
Indian Journal of Science and Technology, Vol.9, Issue 8, pp.1-5, ISSN: 0974-5645 (Online) 0974-6846 (Print). -
The Mindful Self: Exploring Mindfulness in Relation with Self-esteem and Self-efficacy in Indian Population
The aim of the current study was to evaluate and compare the relationship of mindfulness with self-efficacy and self-esteem. The study has also investigated the difference in mindfulness levels across five dimensions: observing, describing, acting with awareness, non-judging of inner experiences and non-reactivity to inner experience between males and females and between young adults and middle-aged adults who belong to the Indian population. There was a total of 146 participants (F = 80, M = 66), 84 in the young adult group (2040years) and 62 participants in the middle adult group (4165years). Pearson correlation showed statistically significant (p < 0.01) moderate positive correlation between all the five dimensions of mindfulness and self-esteem; while self-efficacy had significant (p < 0.01) moderate positive correlation with all the dimensions of mindfulness except for non-judging of inner experiences. Multiple linear regression (MLR) with self-esteem as outcome variable showed model fitness of 51% (p < 0.01) with acting with awareness, non-reactivity to inner experience, non-judging of inner experiences and describing as predictive variables. With self-efficacy as outcome variable, MLR showed model fitness of 40% (p < 0.01) with non-reactivity to inner experiences, acting with awareness, observing and describing as predicting variables. Females were found to be significantly higher in acting with awareness and observing dimensions of mindfulness compared to males. Middle adults were found to be significantly higher only in the non-judging of inner experiences dimension as compared to early adults. Importance of mindfulness in improving self-concept has been established in western world. The present study, by exploring the relationship between mindfulness and self-variables in Indian population, highlights the probable positive outcomes of mindfulness enhancing techniques on self-esteem and self-efficacy of individuals, and therefore on the quality of life. 2022, National Academy of Psychology (NAOP) India. -
IBA Graph Selector Algorithm for Big Data Visualization using Defence Dataset
International Journal of Scientific & Engineering Research Vol.4,Issue 3 pp. 1-5 ISSN No. 2229-5518 -
SVM Ensemble Model for Investment Prediction
International Journal of IT, Engineering and Applied Sciences Research, Vol-1 (2), pp. 19-23. ISSN-2319-4413 -
Correlation based ADALINE neural network for commodity trading
Commodity trading is one of the most popular resources owning to its eminent predictable return on investment to earn money through trading. The trading includes all kinds of commodities like agricultural goods such as wheat, coffee, cocoa etc. and hard products like gold, rubber, crude oils etc.,. The investment decision can be made very easily with the help of the proposed model. The proposed model correlation based multi layer perceptron feed forward adaline neural network is an integrated method to forecast the future values of all commodity trading. The correlation based adaline neuron is used as an optimized predictor in the multi layer perceptron feed forward neural network. The correlation is used for feature selection before building the predictive model. The aim of the paper is to build the predictive model for commodity trading. The model is created using correlation based feature selection and adaline neural network to prognosticate all future values of commodities. The adaptive linear neuron is formed with the help of linear regression. To implement the proposed model the live data is captured from mcxindia. The mcxindia is considered as one the popular website for doing commodities and derivatives in India. To train the proposed model, few random samples are used and the model is evaluated with the help of few test samples from the same data set. 2015 Chandra, J., M. Nachamai and Anitha S. Pillai. -
Study on Mechanical Properties of Lime Stabilized Active Bauxite Residue (Red Mud) and Fly Ash to Use as a Subgrade Material in Road Construction
Bauxite residue (Red mud) is a waste product produced during the extraction of aluminium from Bauxite by Bayers process. The huge requirement of aluminium for the various needs of mankind resulted to the enormous production of bauxite residue which is a very fine substance with high alkalinity. The high alkaline nature of this waste material shows a high impact on environment if it not covered or used in an appropriate method. This paper focusses on the usage of bauxite residue with the support of lime and flyash as a stabilizing material to use as a subgrade in road constructions and understand the toxicity levels of it upon leaching. Bauxite residue was stabilized with various ratios of fly ash and lime powder to its dry weight and determined the mechanical properties like California bearing ratio and unconfined compressive strength of all the combinations. Any industrial waste material will pose a environmental threat if the chemical analysis was not made upon using it as a subgrade material. In this study more emphasis was given to study the various hazardous chemicals present in the leachate collected from bauxite residue with fly ash and lime mixture. Leachate was collected by using Total characteristics leaching procedure (TCLP Method) and chemical analysis was performed and compared the results with the various water standards to recommend this material as a chemically safe material in the nature. All the results proved that bauxite residue upon stabilizing with the fly ash and lime is very much suitable to use as a subgrade material and environmentally safe. Kalahari Journals. -
Strength Development of Geopolymer Composites Made from Red Mud-Fly Ash as a Subgrade Material in Road Construction
The application of industrial waste in construction reduces the dependency on natural resources. The materials, including red mud (RM) and fly ash (FA), proved to be favorable materials. However, the materials potential together as a geopolymer composite for road applications has rarely been explored. This study will examine the possibility of the replacement of natural materials in subgrade applications. To achieve this, the geopolymer compositions will be prepared by replacing RM with FA at replacement rates of 10%, 20%, and 30% by dry weight basis. The alkaline activator solution of 8 M will be prepared using sodium hydroxide (NaOH) and sodium silicate to develop geopolymer composites. The strength properties will be studied using the California Bearing Ratio (CBR) and unconfined compression strength (UCS) and validated with microstructural analysis using scanning electron microscopy (SEM), X-ray diffraction (XRD), and Fourier-transform infrared spectroscopy (FTIR). The results reveal that geopolymer composites could achieve a maximum CBR value of 12% and UCS of 2,700 kPa. The microstructural analysis revealed that the formation of dense calcium aluminate hydrate (C-A-H) and calcium silicate hydrate (C-S-H) are the reason for strength improvement. The leaching studies show that the toxic elements were within the permissible limits. Overall, the test results confirmed that the geopolymer composites meet the required strength and could be used as a subgrade material in road construction. 2020 American Society of Civil Engineers. -
Evaluation of Clove Phytochemicals as Potential Antiviral Drug Candidates Targeting SARS-CoV-2 Main Protease: Computational Docking, Molecular Dynamics Simulation, and Pharmacokinetic Profiling
The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus can cause a sudden respiratory disease spreading with a high mortality rate arising with unknown mechanisms. Still, there is no proper treatment available to overcome the disease, which urges the research community and pharmaceutical industries to screen a novel therapeutic intervention to combat the current pandemic. This current study exploits the natural phytochemicals obtained from clove, a traditional natural therapeutic that comprises important bioactive compounds used for targeting the main protease of SARS-CoV-2. As a result, inhibition of viral replication effectively procures by targeting the main protease, which is responsible for the viral replication inside the host. Pharmacokinetic studies were evaluated for the property of drug likeliness. A total of 53 bioactives were subjected to the study, and four among them, namely, eugenie, syzyginin B, eugenol, and casuarictin, showed potential binding properties against the target SARS-CoV-2 main protease. The resultant best bioactive was compared with the commercially available standard drugs. Furthermore, validation of respective compounds with a comprehensive molecular dynamics simulation was performed using Schringer software. To further validate the bioactive phytochemicals and delimit the screening process of potential drugs against coronavirus disease 2019, in vitro and in vivo clinical studies are needed to prove their efficacy. Copyright 2022 Chandra Manivannan, Malaisamy, Eswaran, Meyyazhagan, Arumugam, Rengasamy, Balasubramanian and Liu.