scholarly journals Stock Price Movement Prediction Based on a Deep Factorization Machine and the Attention Mechanism

Mathematics ◽  
2021 ◽  
Vol 9 (8) ◽  
pp. 800
Author(s):  
Xiaodong Zhang ◽  
Suhui Liu ◽  
Xin Zheng
Keyword(s):  
Stock Prices ◽  
Stock Price ◽  
Prediction Accuracy ◽  
Time Series Data ◽  
Data Representation ◽  
Attention Mechanism ◽  
Supplementary Information ◽  
Series Data ◽  
Price Movement ◽  
Factorization Machine

The prediction of stock price movement is a popular area of research in academic and industrial fields due to the dynamic, highly sensitive, nonlinear and chaotic nature of stock prices. In this paper, we constructed a convolutional neural network model based on a deep factorization machine and attention mechanism (FA-CNN) to improve the prediction accuracy of stock price movement via enhanced feature learning. Unlike most previous studies, which focus only on the temporal features of financial time series data, our model also extracts intraday interactions among input features. Further, in data representation, we used the sub-industry index as supplementary information for the current state of the stock, since there exists stock price co-movement between individual stocks and their industry index. The experiments were carried on the individual stocks in three industries. The results showed that the additional inputs of (a) the intraday interactions among input features and (b) the sub-industry index information effectively improved the prediction accuracy. The highest prediction accuracy of the proposed FA-CNN model is 64.81%. It is 7.38% higher than that of traditional LSTM, and 3.71% higher than that of the model without sub-industry index as additional input features.

A Sectoral Analysis of the Role of Stock Market Development on Economic Growth: Empirical Evidence from Indian Economy

2017 ◽  
Vol 18 (4) ◽  
pp. 911-923 ◽  
Author(s):  
Madhu Sehrawat ◽  
A.K. Giri
Keyword(s):  
Economic Growth ◽  
Stock Market ◽  
Stock Prices ◽  
Stock Price ◽  
Time Series Data ◽  
Trade Openness ◽  
Series Data ◽  
Causality Test ◽  
Long Run ◽  
Short Run

The present study examines the relationship between Indian stock market and economic growth from a sectoral perspective using quarterly time-series data from 2003:Q4 to 2014:Q4. The results of the autoregressive distributed lag (ARDL) approach bounds test confirm the existence of a cointegrating relationship between sector-specific gross domestic product (GDP) and sector-specific stock indices. The empirical results reveal that sector-specific economic growth are significantly influenced by changes in the respective sector-specific stock price indices in the long run as well as in the short run. Apart from that, the control variables, such as trade openness and inflation, act as the instrument variables in explaining the variations in the sector-specific GDP of the economy. The results of Granger causality test demonstrate unidirectional long-run as well as short-run causality running from sector specific stock prices to respective sector GDP. The findings suggest that economic growth of the country is sensitive to respective sub-sector stock market investments. The findings highlight the reasons for cyclical and counter-cyclical business phase for the overall economy.

scholarly journals STL-ATTLSTM: Vegetable Price Forecasting Using STL and Attention Mechanism-Based LSTM

Agriculture ◽  
2020 ◽  
Vol 10 (12) ◽  
pp. 612
Author(s):  
Helin Yin ◽  
Dong Jin ◽  
Yeong Hyeon Gu ◽  
Chang Jin Park ◽  
Sang Keun Han ◽  
...  
Keyword(s):  
Time Series ◽  
Prediction Accuracy ◽  
Crop Production ◽  
Time Series Data ◽  
Short Term Memory ◽  
Attention Mechanism ◽  
Series Data ◽  
Percentage Error ◽  
Hot Pepper ◽  
Types Of Information

It is difficult to forecast vegetable prices because they are affected by numerous factors, such as weather and crop production, and the time-series data have strong non-linear and non-stationary characteristics. To address these issues, we propose the STL-ATTLSTM (STL-Attention-based LSTM) model, which integrates the seasonal trend decomposition using the Loess (STL) preprocessing method and attention mechanism based on long short-term memory (LSTM). The proposed STL-ATTLSTM forecasts monthly vegetable prices using various types of information, such as vegetable prices, weather information of the main production areas, and market trading volumes. The STL method decomposes time-series vegetable price data into trend, seasonality, and remainder components. It uses the remainder component by removing the trend and seasonality components. In the model training process, attention weights are assigned to all input variables; thus, the model’s prediction performance is improved by focusing on the variables that affect the prediction results. The proposed STL-ATTLSTM was applied to five crops, namely cabbage, radish, onion, hot pepper, and garlic, and its performance was compared to three benchmark models (i.e., LSTM, attention LSTM, and STL-LSTM). The performance results show that the LSTM model combined with the STL method (STL-LSTM) achieved a 12% higher prediction accuracy than the attention LSTM model that did not use the STL method and solved the prediction lag arising from high seasonality. The attention LSTM model improved the prediction accuracy by approximately 4% to 5% compared to the LSTM model. The STL-ATTLSTM model achieved the best performance, with an average root mean square error (RMSE) of 380, and an average mean absolute percentage error (MAPE) of 7%.

Terrorism and Stock Market Linkages: An Empirical Study from a Front-line State

2017 ◽  
Vol 18 (2) ◽  
pp. 365-378 ◽  
Author(s):  
Imtiaz Arif ◽  
Tahir Suleman
Keyword(s):  
Stock Prices ◽  
Stock Price ◽  
Time Series Data ◽  
Negative Impact ◽  
Stock Exchange ◽  
Series Data ◽  
Front Line ◽  
Long Run ◽  
Factor Index ◽  
The Impact

This article investigates the impact of prolonged terrorist activities on stock prices of different sectors listed in the Karachi Stock Exchange (KSE) by using the newly developed terrorism impact factor index with lingering effect (TIFL) and monthly time series data from 2002 (January) to 2011 (December). Johansen and Juselius (JJ) cointegration revealed a long-run relationship between terrorism and stock price. Normalized cointegration vectors are used to test the effect of terrorism on stock price. Results demonstrate a significantly mixed positive and negative impact of prolonged terrorism on stock prices of different sectors and show that the market has not become insensitive to the prolonged terrorist attacks.

scholarly journals PENGARUH RETURN ON EQUITY, DEBT TO EQUITY RATIO DAN SIZE TERHADAP HARGA SAHAM PADA PERUSAHAAN MANUFAKTUR YANG TERDAFTAR DI BURSA EFEK INDONESIA (BEI)

BISMA ◽  
2019 ◽  
Vol 13 (1) ◽  
pp. 27
Author(s):  
Marzuki Marzuki
Keyword(s):  
Firm Size ◽  
Significant Influence ◽  
Stock Prices ◽  
Stock Price ◽  
Time Series Data ◽  
Stock Exchange ◽  
Series Data ◽  
Manufacturing Companies ◽  
Return On Equity ◽  
Section Data

The objective of this study is to examine the effect of ROE, DER, and firm size on stock prices of the manufacturing companies listed on the Indonesia Stock Exchange (IDX). The data used in this study were panel data sourced from the combination of cross section data and time series data. This research used purposive sampling method with the sample consisted of 86 manufacturing companies listed on IDX in 2017. Data were analyzed using multiple linear regression. The results showed that ROE and firm size had a positive and significant influence on stock price. However, DER did not have a significant influence on stock price. Keywords : ROE, DER, company size, stock price

scholarly journals Application of Short-term Forecasting Models for Energy Entity Stock Price (Study on Indika Energi Tbk., JII)

2019 ◽  
Author(s):  
Fajrin Satria Dwi Kesumah ◽  
Rialdi Azhar ◽  
Edwin Russel
Keyword(s):  
Stock Prices ◽  
Stock Price ◽  
Time Series Data ◽  
Investment Decision ◽  
Share Price ◽  
Series Data ◽  
Arch Effect ◽  
Heterogeneous Variances ◽  
Short Term Forecasting ◽  
Autoregressive Conditional Heteroscedasticity

Share price as one of financial data is the time series data that indicates both a level of fluctuate movement and heterogeneous variances called heteroscedasticity. The method that can be used to overcome the effect of autoregressive conditional heteroscedasticity (ARCH effect) is GARCH model. This study aims to design the best model that can estimate the parameters, to predict share price based on the best model, and to show its volatility. In addition, this paper also discuss the predicted-based-model investment decision. The finding indicating the best model correspond to the data is AR(4) – GARCH(1,1). It is then implemented to forecast the stock prices of Indika Energy, Tbk, Indonesia, for upcoming 40 days that presents significantly good findings with the error percentage below the mean absolute.

scholarly journals Implementation of Long Short-Term Memory and Gated Recurrent Units on Grouped Time-Series Data to Predict Stock Prices Accurately

2021 ◽  
Author(s):  
Armin Lawi ◽  
Hendra Mesra ◽  
Supri Amir
Keyword(s):  
Time Series ◽  
Stock Prices ◽  
Stock Price ◽  
Time Series Data ◽  
Short Term Memory ◽  
Series Data ◽  
Percentage Error ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

Abstract Stocks are an attractive investment option since they can generate large profits compared to other businesses. The movement of stock price patterns on the stock market is very dynamic; thus it requires accurate data modeling to forecast stock prices with a low error rate. Forecasting models using Deep Learning are believed to be able to accurately predict stock price movements using time-series data, especially the Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) algorithms. However, several previous implementation studies have not been able to obtain convincing accuracy results. This paper proposes the implementation of the forecasting method by classifying the movement of time-series data on company stock prices into three groups using LSTM and GRU. The accuracy of the built model is evaluated using loss functions of Rooted Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE). The results showed that the performance evaluation of both architectures is accurate in which GRU is always superior to LSTM. The highest validation for GRU was 98.73% (RMSE) and 98.54% (MAPE), while the LSTM validation was 98.26% (RMSE) and 97.71% (MAPE).

scholarly journals Does Macroeconomic Indicators Influence Stock Price Behavior? Evidence from Nigerian Stock Market

2019 ◽  
Vol 6 (2) ◽  
pp. 26
Author(s):  
Peter Ego Ayunku
Keyword(s):  
Stock Market ◽  
Significant Influence ◽  
Stock Prices ◽  
Stock Price ◽  
Time Series Data ◽  
Unit Root Test ◽  
Series Data ◽  
Price Behavior ◽  
Market Growth ◽  
Integration Test

This paper investigate whether macroeconomics indicators influences stock price behavior in Nigerian stock market, using an annual time series data spanning from 1985-2015. The study employed some econometric tools such as Augmented Dicker Fuller (ADF) Unit Root test, Johansen’s co integration test, Vector Error Correction Model (VECM) to analyze the variables of interest. The study found out that Money Supply (MS) has an inverse but statistically significant  influence on stock prices in Nigerian stock market also Treasury Bill Rate (TBR) has an inverse and statistically insignificant influence on stock market prices. While on the other hand, Market Capitalization (MCAP) has a positive and statistically significant influence on stock prices while Exchange Rate (EXR) has positive but statistically insignificant relationship with stock prices in the Nigerian Stock Market. In view of the above, the study recommends amongst others that monetary authorities should try as much as possible to implement sound macroeconomic policies that would enhance stock market growth and development in Nigeria. 

scholarly journals Relationship between Foreign Exchange Rate and Stock Price of Commercial Joint Stock Banks: Evidence from Vietnam

2016 ◽  
Vol 8 (7) ◽  
pp. 193 ◽  
Author(s):  
Tran Mong Uyen Ngan
Keyword(s):  
Exchange Rate ◽  
Foreign Exchange ◽  
Stock Prices ◽  
Stock Price ◽  
Time Series Data ◽  
Foreign Exchange Rate ◽  
Series Data ◽  
Causality Test ◽  
Using Data ◽  
The Relationship

The relationship between foreign exchange rate and stock price is one popular topic that is interested by not only board managers of banks but also stock investors. By using data about foreign exchange rate between Vietnam Dong (VND) and United State Dollar (USD), stock prices data of nine commercial joint stock banks in Vietnam from the first day of 2013 to the last day of 2015, this paper try to answer the question “Does foreign exchange rate impact on stock price and vice verse?”. Applying Dickey Fuller test and Var Granger Causality test for the time series data, the results show that there is an impact of foreign exchange rate on stock price. Although the fluctuation in foreign exchange rate VND/USD causes the change in stock prices of commercial joint stock banks in Vietnam, however, the vector of this impact is not clearly. On the opposite way, the change in stock price does not cause the change in foreign exchange rate, this relation is one-way relation.

scholarly journals The Effect of Return on Equity (ROE) and Earning per Share (EPS) on Stock Prices In Indonesia Stock Exchange 2015-2018

2020 ◽  
Vol 1 (3) ◽  
pp. 132-138
Author(s):  
Herlina Lusiana
Keyword(s):  
Stock Prices ◽  
Stock Price ◽  
Time Series Data ◽  
Stock Exchange ◽  
Sampling Technique ◽  
Financial Statements ◽  
Series Data ◽  
Return On Equity ◽  
Earnings Per Share ◽  
Food And Beverage

This study aims to analyze the source of a company's profitability by choosing two main factors namely, Return on Equity (ROE) and Earning per Share (EPS) as the strength and resilience of companies engaged in food and beverage listed on the Indonesia Stock Exchange. This study uses time series data from 2015 to 2018. The dependent variable is the stock price. Meanwhile the independent variables are Return on Equity (ROE) and Earning per Share (EPS). The determination of the sample uses positive sampling, the sampling technique uses two special criteria from researchers. The first criterion, only food and beverage companies that publish financial statements in full during the period 2015 to 2018, and the second criterion, food and beverage companies that have financial statement data in accordance with the studied variables, namely Return on Equity (ROE) and Earning per Share (EPS). Samples that meet the criteria are 11 registered food and beverage companies on the Indonesia Stock Exchange for the period 2015 to 2018. Data analysis techniques using multiple linear regression with the help of the SPSS program.The findings show that Return on Equity (ROE) has a positive and significant impact on stock prices, while Earning per Share (EPS) has an impact negative and significant to stock prices. This finding confirms that strength the profitability of a company through Return on Equity (ROE) affects the stock prices of food and beverage companies in Indonesia. Therefore, it is important to maintain the company's profitability through Return on Equity (ROE) from the investor's perspective, not from the company's view. Meanwhile, interesting findings from a company's profitability through Earning per Share (EPS) do not affect the stock prices of food and beverage companies in Indonesia. Because earnings per share or earning per share (EPS) is obtained from the perspective of the company's financial statements where there are differences in the size and size of the company's expenses other than earning per share (EPS) can turn out to be high if the number of shares outstanding is reduced. Keywords: Profitability, Return on Equity (ROE), Earnings per Share (EPS), Stock Prices, Indonesia stock exchange (IDX)  

scholarly journals The Influence of the World Gold Price, the Dow Jones Islamic Market, and the Composite Stock Price Index on the Jakarta Islamic Index for the 2014 - 2018 period

2021 ◽  
Vol 4 (1) ◽  
pp. 13
Author(s):  
Siti Chaerunisa Prastiani
Keyword(s):  
Stock Prices ◽  
Stock Price ◽  
Price Index ◽  
Oil And Gas ◽  
Time Series Data ◽  
Research Output ◽  
Gold Price ◽  
Series Data ◽  
The World ◽  
Stock Price Index

This study aims to determine how much influence the variables of the World Gold Price and Stock Prices with proxies: Dow Jones Islamic Market (DJIM) stock prices, and the Composite Stock Price Index (IHSG), on the Jakarta Islamic Index (JII). This study uses a quantitative approach, namely data that is measured in a numerical scale, based on the 2014-2018 Time Series data relating to variables sourced from the Central Statistics Agency, the Indonesia Stock Exchange and the Directorate General of Oil and Gas. This research uses one of the SPSS Series. The variables in this study consist of World Gold Price (X1), Dow Jones Islamic Market (DJIM) (X2), Composite Stock Price Index (IHSG) (X3) against the Jakarta Islamic Index (JII) (Y). The purpose of this research is to know each variable partially or simultaneously from the variable World Gold Price, Dow Jones Islamic Market and the Jakarta Islamic Index. Research Output expected by an Accredited journal

Sign in / Sign up

Export Citation Format

Share Document