Simulation of Stock Prediction System using Artificial Neural Networks

2016 ◽  
Vol 3 (3) ◽  
pp. 25-44 ◽  
Author(s):  
Omisore Olatunji Mumini ◽  
Fayemiwo Michael Adebisi ◽  
Ofoegbu Osita Edward ◽  
Adeniyi Shukurat Abidemi
Keyword(s):  
Test Data ◽  
Stock Prices ◽  
Prediction Accuracy ◽  
Stock Exchange ◽  
Training Data ◽  
Prediction System ◽  
Stock Trading ◽  
Closing Price ◽  
Non Linear ◽  
Predicted Values

Stock trading, used to predict the direction of future stock prices, is a dynamic business primarily based on human intuition. This involves analyzing some non-linear fundamental and technical stock variables which are recorded periodically. This study presents the development of an ANN-based prediction model for forecasting closing price in the stock markets. The major steps taken are identification of technical variables used for prediction of stock prices, collection and pre-processing of stock data, and formulation of the ANN-based predictive model. Stock data of periods between 2010 and 2014 were collected from the Nigerian Stock Exchange (NSE) and stored in a database. The data collected were classified into training and test data, where the training data was used to learn non-linear patterns that exist in the dataset; and test data was used to validate the prediction accuracy of the model. Evaluation results obtained from WEKA shows that discrepancies between actual and predicted values are insignificant.

Simulation of Stock Prediction System using Artificial Neural Networks

2020 ◽  
pp. 511-530
Author(s):  
Omisore Olatunji Mumini ◽  
Fayemiwo Michael Adebisi ◽  
Ofoegbu Osita Edward ◽  
Adeniyi Shukurat Abidemi
Keyword(s):  
Neural Networks ◽  
Test Data ◽  
Stock Prices ◽  
Prediction Accuracy ◽  
Stock Exchange ◽  
Training Data ◽  
Prediction System ◽  
Closing Price ◽  
Non Linear ◽  
Predicted Values

Stock trading, used to predict the direction of future stock prices, is a dynamic business primarily based on human intuition. This involves analyzing some non-linear fundamental and technical stock variables which are recorded periodically. This study presents the development of an ANN-based prediction model for forecasting closing price in the stock markets. The major steps taken are identification of technical variables used for prediction of stock prices, collection and pre-processing of stock data, and formulation of the ANN-based predictive model. Stock data of periods between 2010 and 2014 were collected from the Nigerian Stock Exchange (NSE) and stored in a database. The data collected were classified into training and test data, where the training data was used to learn non-linear patterns that exist in the dataset; and test data was used to validate the prediction accuracy of the model. Evaluation results obtained from WEKA shows that discrepancies between actual and predicted values are insignificant.

scholarly journals THE XBRL TECHNOLOGY AND MARKET EFFICIENCY IN BANKING COMPANIES LISTED ON THE INDONESIA STOCK EXCHANGE (IDX)

2020 ◽  
Vol 4 (1) ◽  
pp. 26
Author(s):  
Erni Jayani ◽  
Jumiadi Abdi Winata ◽  
Khairunnisa Harahap
Keyword(s):  
Information Asymmetry ◽  
Market Efficiency ◽  
Financial Reporting ◽  
Stock Prices ◽  
Trading Volume ◽  
Sampling Method ◽  
Stock Exchange ◽  
Institutional Ownership ◽  
Accurate Information ◽  
Stock Trading

The problem in this research is the need for fast and accurate information in the format of the presentation of financial statements resulting in the distribution of information, and data management can be problematic. Therefore, a format for financial reporting systems, namely Extensible Business Reporting Language (XBRL), was formed. The purpose of this study was to determine the effect of XBRL technology, stock prices, Return on Assets (ROA), and institutional ownership on market efficiency (information asymmetry and stock trading volume). The population and sample of this study are banking companies listed on the Indonesia Stock Exchange from 2015-2016. The sampling method using a purposive sampling method and obtained a sample of 42 companies. Data collection techniques are carried out by taking data from the Indonesia Stock Exchange website (www.idx.co.id) and the site http://finance.yahoo.com. Data were analyzed with multiple regression tests after being declared normal with the normality test and though using SPSS 20. The results of this study simultaneously stated that XBRL technology, stock prices, ROA, and institutional ownership together have an influence on information asymmetry and stock trading volume. From the results of the study, it can be concluded that XBRL technology, stock prices, ROA, and institutional ownership cause a decrease in the level of information asymmetry and trading volume. This result also states that the company is in excellent condition when the value of information asymmetry decreases, but it is not good when the trading volume of its shares also decreases. Keywords: XBRL Technology; Stock Prices; Market Efficiency; Information Asymmetry; Stock Trading Volume. 

scholarly journals Prediksi Harga Saham Dalam Berinvestasi Pada Perusahaan Manufaktur

2021 ◽  
Vol 9 (2) ◽  
pp. 101-114
Author(s):  
Fauziyah Fauziyah
Keyword(s):  
Stock Prices ◽  
Stock Price ◽  
Manufacturing Industry ◽  
Stock Exchange ◽  
Manufacturing Sector ◽  
Prediction Method ◽  
Manufacturing Companies ◽  
Upward Trend ◽  
Stock Trading ◽  
The Past

Abstract Indonesia Stock Exchange (IDX) is a term that is well known in the world of stocks in Indonesia. One of the company sectors listed on the IDX is manufacturing. The contribution of the manufacturing sector to Gross Domestic Product (GDP) was recorded to be the largest compared to other sectors. In this research, the manufacturing companies that will be used as the object of research to predict their stock prices are manufacturing companies listed in LQ45. In stock trading, prices fluctuate up or down. Stock conditions that fluctuate every day make investors who are going to invest in the Manufacturing industry must observe and study the past company data before investing. This data is important for investors to find out what might happen to a company's stock price. Thus, predicting stock prices in the manufacturing industry for the future is needed as a stage in deciding which manufacturing companies are good to investing in. The prediction method in this research uses ARIMA. The results obtained are the stock prices of companies GGRM, HMSP, ICBP, INDF, INTP and UNVR following a downward trend, so that the actions taken by investor in these companies are selling stocks, while for the stock prices of companies ASII, CPIN, INKP, JPFA, SMGR, TKIM, following an upward trend, so that the actions taken by investors in these companies are buying stocks.Keywords: Prediction, ARIMA, Investment  BEI merupakan istilah yang terkenal pada dunia saham di Indonesia. Sektor perusahaan yang terdapat di BEI salah satunya adalah manufaktur. Kontribusi sektor manufaktur dalam Produk Domestik Bruto (PDB) tercatat yang paling besar dibandingkan sektor lainnya. Di dalam penelitian ini, perusahaan manufaktur yang akan dijadikan objek penelitian untuk diramalkan harga sahamnya yaitu perusahaan manufaktur yang terdaftar di LQ45.  Pada perdagangan saham, harga mengalami fluktuasi naik maupun turun.  Keadaan saham yang fluktuasi setiap hari menjadikan investor yang akan berinvestasi di industri Manufaktur harus mengamati dan mempelajari data perusahaan dimasa lalu sebelum melakukan investasi. Data tersebut penting bagi investor untuk mengetahui kemungkinan yang terjadi pada harga saham suatu perusahaan. sehingga, meramal harga saham pada industri manufaktur untuk masa yang akan datang sangat dibutuhkan sebagai tahapan dalam memutuskan perusahaan Manufaktur yang baik dalam melakukan investasi. Metode Prediksi dalam penelitian ini menggunakan ARIMA. Hasil yang didapat yaitu harga saham perusahaan GGRM, HMSP, ICBP, INDF, INTP dan UNVR mengikuti tren turun, sehingga langkah yang diambil untuk investor pada perusahaan tersebut adalah menjualnya sedangkan untuk harga saham perusahaan ASII, CPIN, INKP, JPFA, SMGR, TKIM, mengikuti tren naik, sehingga langkah yang diambil untuk investor pada perusahaan tersebut adalah membeli saham.Kata Kunci: Prediksi, ARIMA, Investasi

scholarly journals PENGARUH VOLUME PERDAGANGAN SAHAM DAN HARGA SAHAM TERHADAP BID-ASK SPREAD STUDI PADA PERUSAHAAN-PERUSAHAAN MANUFAKTUR YANG TERDAFTAR DI BURSA EFEK INDONESIA

2017 ◽  
pp. 62-74
Author(s):  
Ruminsar Nainggolan ◽  
Donalson Silalahi
Keyword(s):  
Stock Prices ◽  
Stock Price ◽  
Trading Volume ◽  
Stock Exchange ◽  
Sampling Technique ◽  
Multiple Regression Equation ◽  
Manufacturing Companies ◽  
Stock Trading ◽  
Bid Ask Spread ◽  
Bid Ask Spreads

ABSTRACT The purpose of this study is to determine the effect of stock trading volume and stock prices on bid-ask spreads on manufacturing companies listed on the Indonesia Stock Exchange. The population in research is 155 companies and by using purposive sampling as sampling technique, then the sample in this research is 46 company. The data used are secondary data and use multiple regression equation as an analytical tool. Based on the results of the research it can be argued that, trading volume and stock prices have a negative and significant effect on the bid-ask spread both before and after the data grouping. The results also show that stock trading in Indonesia Stock Exchange is liquid. Investors or potential investors who want to invest in the capital market should make trading volume and stock price as a reference in making investment decisions, because simultaneously these two variables have a significant effect on bid-ask spreads.

scholarly journals Identification of Non-linear Systems through Convolutional Neural Network

2019 ◽  
Vol 8 (3) ◽  
pp. 3429-3434
Keyword(s):  
Neural Network ◽  
Nonlinear Systems ◽  
Convolutional Neural Network ◽  
Control Systems ◽  
Linear Systems ◽  
Test Data ◽  
Training Data ◽  
Analysis And Design ◽  
Non Linear ◽  
Non Linear Systems

The theory of control systems deals with the analysis and design of interacting components of a system in a configuration that provides the desired behavior. This paper deals with the problem of the identification of non-linear systems through Convolutional Neural Network (CNN). We propose a structure of a CNN and perform simulations with test data using unsupervised learning for the identification of nonlinear systems. Also, MLP is used to compare the results when there is noise in the training data, which allows us to see that the proposed CNN has better performance and can be used for cases where the noise is present. The proposed CNN is validated with test data. Tests are carried out with Gas oven data, comparing the proposed structure of CNN with a MLP. When there is noise in the data, CNN has better performance than MLP.

scholarly journals Apakah Pembatasan Sosial Berskala Besar Warga Negara Asing Berdampak Pada Average Abnormal Return?

2021 ◽  
Vol 1 (2) ◽  
pp. 160-171
Author(s):  
Asnat Susanti Dangga Lolu ◽  
Lusianus Heronimus Sinyo Kelen
Keyword(s):  
Stock Prices ◽  
Abnormal Return ◽  
Large Scale ◽  
Stock Exchange ◽  
Abnormal Returns ◽  
Economic Sector ◽  
Stock Trading ◽  
Average Abnormal Return ◽  
Before And After ◽  
Research Period

This study examines the differences in stock prices listed on the Indonesia Stock Exchange as measured using average abnormal returns on events (event studies) before and after the enactment of Large-Scale Social Restrictions for Foreign Citizens, especially COVID-19 which has an impact not only threatening human health but also has an impact on the economic sector. This condition will certainly have an impact on all sectors including stock trading on the Indonesia Stock Exchange, especially the Tourism, Hospitality, and Restaurant sub-sector. By using a sample of 41 companies on the Indonesia Stock Exchange with a research period of 3 months (16 November 2020 to 15 February 2021) the type of purposive sampling research that meets the criteria and using paired sample t-test, the results show that there is no difference Average Abnormal Return before and after the occurrence of a PSBB event for Foreign Citizens. So it can be concluded that the PSBB for Foreign Citizens has no impact on the average abnormal return obtained by investors.

scholarly journals Capabilities of Statistical Residual-Based Control Charts in Short- and Long-Term Stock Trading

2016 ◽  
Vol 62 (1) ◽  
pp. 12-26 ◽  
Author(s):  
Berislav Žmuk
Keyword(s):  
Control Chart ◽  
Stock Prices ◽  
Control Charts ◽  
Stock Exchange ◽  
Moving Average ◽  
Stock Trading ◽  
Cusum Control Chart ◽  
Long Run ◽  
Short Run ◽  
Exponential Weighted Moving Average

Abstract The aim of this paper is to introduce and develop additional statistical tools to support the decision-making process in stock trading. The prices of CROBEX10 index stocks on the Zagreb Stock Exchange were used in the paper. The conducted trading simulations, based on the residual-based control charts, led to an investor’s profit in 67.92% cases. In the short run, the residual-based cumulative sum (CUSUM) control chart led to the highest portfolio profits. In the long run, when average stock prices were used and 2-sigma control limits set, the residual-based exponential weighted moving average control chart had the highest portfolio profit. In all other cases in the long run, the CUSUM control chart appeared to be the best choice. The acknowledgment that the SPC methods can be successfully used in stock trading will, hopefully, increase their use in this field.

scholarly journals Pengaruh Volume Perdagangan Saham, Volatilitas Laba, Dividend Yield, dan Ukuran Perusahaan Pada Volatilitas Harga Saham

2018 ◽  
pp. 2148
Author(s):  
Ni Wayan Sekar Andiani ◽  
Gayatri Gayatri
Keyword(s):  
Firm Size ◽  
Stock Prices ◽  
Stock Price ◽  
Trading Volume ◽  
Stock Exchange ◽  
Linear Regression Analysis ◽  
Price Volatility ◽  
Dividend Yield ◽  
Stock Trading ◽  
Stock Price Volatility

This study aims to obtain empirical evidence on the effect of stock trading volume, earning volatility, dividend yield, and firm size on stock price volatility. This research was conducted on companies listed in index LQ 45 in Indonesia Stock Exchange 2012 until 2016. This research took the population of 45 companies with the number of samples of 21 companies selected through purposive sampling, so the number of samples observation for 5 years to 105 companies. The analysis technique in this research is multiple linear regression analysis. Based on the analysis results found that the stock trading volume does not affect the stock price volatility. Earning volatility has a negative effect on stock price volatility. This shows the higher volatility of profits owned by the company tends to reduce the interest of investors to invest or can reduce the volatility of stock prices. Dividend yield has a positive effect on stock price volatility. Which means that the higher dividend rate can affect the high investor interest to invest in the capital market, causing a stock price reaction. The firm size has a negative affects on stock price volatility. This proves the greater the size of the company indicates a stable corporate condition and able to reduce the volatility of stock prices. Keywords: Stock Trading Volume, Earning Volatility, Dividend Yield, Firm Size, Stock Price Volatility.

scholarly journals Estimating the Distribution of Viral Taxa in Next-generation Sequencing data using Artificial Neural Networks

2020 ◽  
Author(s):  
Moritz Kohls ◽  
Magdalena Kircher ◽  
Jessica Krepel ◽  
Pamela Liebig ◽  
Klaus Jung
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Next Generation Sequencing ◽  
Test Data ◽  
Prediction Accuracy ◽  
Confusion Matrix ◽  
Training Data ◽  
Comparative Metagenomics ◽  
Artificial Neural ◽  
Generation Sequencing

Abstract Background: Estimating the taxonomic composition of viral sequences in a biological sample processed by next-generation sequencing is an important step for comparative metagenomics. For that purpose, sequencing reads are usually classified by mapping them against a database of known viral reference genomes. This fails, however, to classify reads from novel viruses and quasispecies whose reference sequences are not yet available in public databases. Methods: In order to circumvent the problem of a mapping approach with unknown viruses, the feasibility and performance of neural networks to classify sequencing reads to taxonomic classes is studied. For that purpose, taxonomy and genome data from the NCBI database are used to sample artificial reads from known viruses with known taxonomic attribution. Based on these training data, artificial neural networks are fitted and applied to classify single viral read sequences to di erent taxa. Model building includes di erent input features derived from artificial read sequences as possible predictors which are chosen by a feature selection method. Training, validation and test data are computed from these input features. To summarise classification results, a generalised confusion matrix is proposed which lists all possible misclassification combination frequencies. Two new formulas to statistically estimate taxa frequencies are introduced for studying the overall viral composition.Results: We found that the best taxonomic level supported by the NCBI database is that of viral orders. Prediction accuracy of the fitted models is evaluated on test data and classification results are summarised in a confusion matrix, from which diagnostic measures such as sensitivity and specificity as well as positive and negative predictive values are calculated. The prediction accuracy of the artificial neural net is considerably higher than for random classification and posterior estimation of taxa frequencies is closer to the true distribution in the training data than simple classification or mapping results. Conclusions: Neural networks are helpful to classify sequencing reads into viral orders and can be used to complement the results of mapping approaches. The machine learning approach is not limited to already known viruses. In addition, statistical estimations of taxa frequencies can be used for subsequent comparative metagenomics.

ANALISIS PENGARUH PENGUMUMAN RIGHT ISSUE TERHADAP ABNORMAL RETURN DAN VOLUME PERDAGANGAN SAHAM DI BURSA EFEK INDONESIA PERIODE TAHUN 2009 – KUARTAL 3 TAHUN 2012

2018 ◽  
Vol 8 (2) ◽  
pp. 116-148
Author(s):  
Maria Gladys Jessica Kamalsah ◽  
Yunia Panjaitan
Keyword(s):  
Stock Prices ◽  
Abnormal Return ◽  
Trading Volume ◽  
Stock Exchange ◽  
Investment Decision ◽  
Market Returns ◽  
Stock Trading ◽  
Daily Data ◽  
Average Abnormal Return ◽  
Rights Issue

The availability of the information on capital market transactions will affect decisions of investors who will also determine the price of the stock market. This study was conducted to examine the effect of the announcement of the rights issue on stock prices and trading volume. Sample for this study was 63 companies who do right issue on the Stock Exchange during 2009 - 3rd quarter of 2012. The data collected consisted of daily return actual data, the IHSG daily data as market returns, and daily stock trading volume from each sample company. The result of the analysis showed that there were no significant differences in average abnormal return, but there are significant differences in the average stock trading volume. So, it can be concluded that the announcement of the rights issue contains information for investors, but did not contain information to make an investment decision.

Sign in / Sign up

Export Citation Format

Share Document