scholarly journals RLSTM: A New Framework of Stock Prediction by Using Random Noise for Overfitting Prevention

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Hongying Zheng ◽  
Zhiqiang Zhou ◽  
Jianyong Chen
Keyword(s):  
Deep Learning ◽  
Financial Risk ◽  
Short Term Memory ◽  
Random Noise ◽  
Composite Index ◽  
Stock Prediction ◽  
Stock Market Index ◽  
Market Index ◽  
Prediction Module ◽  
Training Need

An accurate prediction of stock market index is important for investors to reduce financial risk. Although quite a number of deep learning methods have been developed for the stock prediction, some fundamental problems, such as weak generalization ability and overfitting in training, need to be solved. In this paper, a new deep learning model named Random Long Short-Term Memory (RLSTM) is proposed to get a better predicting result. RLSTM includes prediction module, prevention module, and three full connection layers. Input of the prediction module is a stock or an index which needs to be predicted. That of the prevention module is a random number series. With the index of Shanghai Securities Composite Index (SSEC) and Standard & Poor’s 500 (S&P500), simulations show that the proposed RLSTM can mitigate the overfitting and outperform others in accuracy of prediction.

scholarly journals Cross Border Portfolio Investment and The Volatility of Stock Market Index and Rupiah's Rate

2015 ◽  
Vol 17 (4) ◽  
pp. 403-432 ◽  
Author(s):  
Al Muntasir
Keyword(s):  
Foreign Capital ◽  
Composite Index ◽  
Capital Flow ◽  
Capital Inflows ◽  
Stock Market Index ◽  
Dynamic Relationship ◽  
Market Index ◽  
Daily Data ◽  
Foreign Capital Inflows ◽  
The Impact

This paper use daily data during the period 2010-2014 to analyse the impact of foreign capital inflows on capital market volatility and on the volatility of Rupiah’s rate. The results shows the flow of foreign capital positively affect the Jakarta Composite Index (JCI) but not the rate of Rupiah. Using Vector Error Correction Model, this paper finds a cointegrated and dynamic relationship between the changes in foreign capital flow in Indonesia, with the JCI and the exchange rate of Rupiah against USD. Changes in the Rupiah’s rate significantly affect the foreign capital flow and the JCI, while the JCI does not significantly affect the flow of foreign capital and the changes of Rupiah’s rate.

scholarly journals Prediksi Indeks BEI dengan Ensemble Convolutional Neural Network dan Long Short-Term Memory

2021 ◽  
Vol 5 (3) ◽  
pp. 456-465
Author(s):  
Harya Widiputra ◽  
Adele Mailangkay ◽  
Elliana Gautama
Keyword(s):  
Time Series ◽  
Stock Market ◽  
Time Series Data ◽  
Short Term Memory ◽  
Series Data ◽  
Stock Market Index ◽  
Short Term ◽  
Term Memory ◽  
Market Index ◽  
Long Short Term Memory

The Indonesian Stock Exchange (IDX) stock market index is one of the main indicators commonly used as a reference for national economic conditions. The value of the stock market index is often being used by investment companies and individual investors to help making investment decisions. Therefore, the ability to predict the stock market index value is a critical need. In the fields of statistics and probability theory as well as machine learning, various methods have been developed to predict the value of the stock market index with a good accuracy. However, previous research results have found that no one method is superior to other methods. This study proposes an ensemble model based on deep learning architecture, namely Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM), called the CNN-LSTM. To be able to predict financial time series data, CNN-LSTM takes feature from CNN for extraction of important features from time series data, which are then integrated with LSTM feature that is reliable in processing time series data. Results of experiments on the proposed CNN-LSTM model confirm that the hybrid model effectively provides better predictive accuracy than the stand-alone time series data forecasting models, such as CNN and LSTM.  

scholarly journals Reaksi Pasar Modal di Asia Tenggara Terhadap Pandemi Covid-19

2021 ◽  
Vol 23 (1) ◽  
pp. 162-172
Author(s):  
Sari Octavera ◽  
Febri Rahadi
Keyword(s):  
Stock Market ◽  
Regression Model ◽  
Composite Index ◽  
Least Square ◽  
Stock Market Index ◽  
Market Reactions ◽  
Ordinary Least Square ◽  
Market Index ◽  
Panel Data Regression ◽  
Result Show

Covid 19 is global case in almost around the world. Early April 2020, Covid 19 cases reached 1 million in a number of countries and increased significantly. This pandemic caused a major impact on economic activity, and more than 100 countries carried out a full or partial lockdown which resulted in economic disruption in many sectors including the stock market. This study investigation impact that occurs on the stock market, especially in Southeast Asia (Malaysia, Indonesia, Thailand and Singapore). Change in the composite index from the capital market are used as a proxy to measure market reactions using the OLS panel data regression model. The natural log of GDP is used as a control variabel for differences between the four capital markets. In addition, to control for the effect of different transaction days, a dummy variable is included in the regression model. The result show that changes in the number of covid 19 infections have been shown to significantly affect index changes. The market response in this regard has moved in a negative direction. Meanwhile, the measurement of the effect to the death  to covid 19 is not proven to significantly affect change in the composite stock market index. ABSTRAK Covid 19 menjadi kasus global dengan penyebaran yang sangat cepat hampir diseluruh belahan dunia. Awal April 2020 kasus Covid 19 menyentuh angka 1 juta penderita yang tersebar di sejumlah negara dan terus meningkat secara signifikan. Pandemi ini berpengaruh besar terhadap aktifitas perekonomian hampir di seluruh dunia. Puncaknya, akhir Maret 2020 lebih dari 100 negara melakukan Lockdown baik secara penuh maupun sebagian yang memberikan dampak terbatasnya aktifitas ekonomi di berbagai sektor seperti transportasi, pariwisata, perbankan, asuransi termasuk pasar modal. Penelitian ini berupaya melihat dampak yang terjadi di pasar modal khususnya di empat negara di Asia Tenggara (Malaysia, Indonesia, Thailand dan Singapura). Perubahan Indeks gabungan dari pasar modal dipergunakan sebagai proksi untuk mengukur reaksi pasar dengan menggunakan pendekatan model regresi data panel Ordinary Least Square (OLS). Untuk mengendalikan dampak yang mungkin muncul dari perbedaan yang mendasar dari keempat pasar modal tersebut, dipergunakan log natural PDB sebagai variabel kontrol. Selain itu, untuk mengontrol efek perbedaaan hari transaksi dimasukkan pula variabel dummy didalam model regresi. Hasil menunjukkan perubahan angka terinfeksi COVID-19 terbukti secara signifikan mempengaruhi perubahan indeks. Respon pasar terkait hal tersebut bergerak kearah negatif. Sementara pengukuran terhadap pengaruh angka maninggal dunia akibat COVID-19 tidak terbukti secara signifikan mempengaruhi perubahan indeks pasar saham gabungan

scholarly journals Deep Learning for Stock Market Index Price Movement Forecasting Using Improved Technical Analysis

2021 ◽  
Vol 14 (5) ◽  
pp. 129-141
Author(s):  
Chinthakunta Manjunath ◽  
◽  
Balamurugan Marimuthu ◽  
Bikramaditya Ghosh ◽  
◽  
...  
Keyword(s):  
Deep Learning ◽  
Stock Market ◽  
Technical Analysis ◽  
Stock Market Index ◽  
Price Movement ◽  
Market Index

Deep learning neural network for the prediction of asian tiger stock markets

2021 ◽  
pp. 2150040
Author(s):  
Kok-Leong Yap ◽  
Wee-Yeap Lau ◽  
Izlin Ismail
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Stock Prices ◽  
Stock Markets ◽  
Short Term Memory ◽  
Stock Market Index ◽  
Short Term ◽  
Asian Tiger ◽  
Deep Learning Neural Network

Motivated by the recent interest of stock traders and investors towards the deep learning neural network, this study employs the deep learning neural networks, namely, multilayer perceptron, long short-term memory, and convolutional neural network, to forecast the Asian Tiger stock markets. One of the challenges to using deep learning neural networks is to select the input variable. We propose to use multiple linear regression to select the input variable that is significant to the output. Besides, we construct a regional stock market index as a significant input to forecast the Asian Tiger stock markets. A comparison study on the forecasting model shows that the deep learning model can be used as a decision-making system that assists investors to predict short-term movement and trends of stock prices.

scholarly journals Application of Multifactor Model to Stock Market Index Prediction using Multi-Task Deep Learning

2018 ◽  
Vol 35 (4) ◽  
pp. 45-67
Author(s):  
Ha Young Kim ◽  
JEONG GYE EUN ◽  
Leem JoonBum ◽  
유재인 ◽  
Hyeng Keun Koo
Keyword(s):  
Deep Learning ◽  
Stock Market ◽  
Stock Market Index ◽  
Multifactor Model ◽  
Market Index

scholarly journals Risk Analysis of Textile Industry Foreign Investment Based on Deep Learning

2022 ◽  
Vol 2022 ◽  
pp. 1-6
Author(s):  
Jingyi Liu ◽  
Jiaolong Li
Keyword(s):  
Deep Learning ◽  
Risk Analysis ◽  
Foreign Investment ◽  
Financial Distress ◽  
Textile Industry ◽  
Financial Risk ◽  
Short Term Memory ◽  
Indicator System ◽  
Risk Indicator ◽  
Huge Impact

With the decline of China’s economic growth rate and the uproar of antiglobalization, the textile industry, one of the business cards of China’s globalization, is facing a huge impact. When the economic model is undergoing transformation, it is more important to prevent enterprises from falling into financial distress. So, the financial risk early warning is one of the important means to prevent enterprises from falling into financial distress. Aiming at the risk analysis of the textile industry’s foreign investment, this paper proposes an analysis method based on deep learning. This method combines residual network (ResNet) and long short-term memory (LSTM) risk prediction model. This method first establishes a risk indicator system for the textile industry and then uses ResNet to complete deep feature extraction, which are further used for LSTM training and testing. The performance of the proposed method is tested based on part of the measured data, and the results show the effectiveness of the proposed method.

Sign in / Sign up

Export Citation Format

Share Document