scholarly journals Back-Propagation Neural Network and ARIMA Algorithm for GDP Trend Analysis

2022 ◽  
Vol 2022 ◽  
pp. 1-9
Author(s):  
Siqi Hua

GDP (gross domestic product) is a key indicator for assessing a country’s or region’s macroeconomic situation, as well as a foundation for the government to develop economic development strategies and macroeconomic policies. Currently, the majority of methods for forecasting GDP are linear methods, which only take into account the linear factors that affect GDP. GDP (gross domestic product) is widely regarded as the most accurate indicator of a country’s economic health. GDP not only reflects a country’s economic development over time but can also reflect its national strength and wealth. As a result, the GDP trend forecast partially reflects China’s transformation and future development. The time series ARIMA (Autoregressive Integrated Moving Average) model and the BPNN (BP neural network) model are combined in this article to create the ARIMA-BPNN fusion prediction model. The predicted values of the two models were then weighted averaged to obtain the predicted values of the linear part of the improved fusion model. To get the predicted values of the improved fusion model, we weighted average the residual parts of the two models, predict the nonlinear residual with BPNN, and add the predicted values of the two parts. It is applied to the actual GDP forecast in H province from 2019 to 2022, and the actual forecast verifies the effectiveness of the fusion forecast model in the actual forecast.

2021 ◽  
pp. 1-11
Author(s):  
Yuan Zou ◽  
Daoli Yang ◽  
Yuchen Pan

Gross domestic product (GDP) is the most widely-used tool for measuring the overall situation of a country’s economic activity within a specified period of time. A more accurate forecasting of GDP based on standardized procedures with known samples available is conducive to guide decision making of government, enterprises and individuals. This study devotes to enhance the accuracy regarding GDP forecasting with given sample of historical data. To achieve this purpose, the study incorporates artificial neural network (ANN) into grey Markov chain model to modify the residual error, thus develops a novel hybrid model called grey Markov chain with ANN error correction (abbreviated as GMCM_ANN), which assembles the advantages of three components to fit nonlinear forecasting with limited sample sizes. The new model has been tested by adopting the historical data, which includes the original GDP data of the United States, Japan, China and India from 2000 to 2019, and also provides predications on four countries’ GDP up to 2022. Four models including autoregressive integrated moving average model, back-propagation neural network, the traditional GM(1,1) and grey Markov chain model are as benchmarks for comparison of the predicted accuracy and application scope. The obtained results are satisfactory and indicate superior forecasting performance of the proposed approach in terms of accuracy and universality.


2019 ◽  
Vol 31 (1) ◽  
pp. 61-67
Author(s):  
Rwida Kreiw

Regarding the Libyan macroeconomic framework, the petroleum sector returns caused to the government and the need to support civil service job opportunity and preserve the widespread funding system. In 2006, the increasing of the price of the Libyan price oil, around US $63.05, had a significant and positive influence on the Libyan economic situation. The price increased around 65 % compared to the corresponding value in 2004 which was in averaged around US $38.In the same context, the favorable enhancement in the oil sector donated to an observable development in balance of payment surplus, which achieved around 15.4 % of gross domestic product. Also, international reserves improved to be around 19 billion US dollars. Moreover, the Libyan authorities have decreased the bank the percentage of interest rates across the board to enhance the demand in the private sector for credit and established a strategy to update the payment system. All these monetary policies and strategies affect positively on the Libyan macroeconomic and financial situations to be satisfactory in 2004.In 2005, the performance of the macroeconomic stayed comparatively strong. The gross domestic product achieved approximately about 3.5 %. Moreover, the inflation stayed 2.5 %. On the other hand, the economic development is assessed to have been created mainly 4.5 % in the non-oil sectors. In details, the non-oil sectors such as hotels and transportation, construction and services, agriculture and manufacturing sector with respectively values 7%, 5%, 2.5 % and 1.8%. unfortunately, all these sectors showed weak performance recently because of the unstable political situation in the country.Regarding to the banking sectors, according to (Murugiah and Akgam, 2015), Libyan banking sector has realized especially after the issuance of laws. In 2005, this Central Bank of Libya has significant impact on establishing banks and reorganization assets inducing them to look for new investment chances. In our model, the variables Stock Capital, Libyan Oil PriceNumber of population in Libya and dummy variable for the political instability have significant impact on the Libyan gross domestic products at 5% significance level. The heteroscedasticity and autocorrelation tests are checked in the model.Finally, we conclude that increasing (decreasing) the oil and gas prices has a significant influence on the economic development generally in Libya and on the macroeconomic indicators, such as gross domestic product, monetary policy, the unemployment rate, and the inflation rate in the country.


Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Hui Wang ◽  
Lu Qiao ◽  
Chuang Tian ◽  
Qiaoqiao Lin

Optimising the allocation of population, land, and capital production resources is crucial for promoting an efficient urbanisation and solving the urban land financial problem. This study uses a panel threshold model to identify the response boundary of urban construction land use efficiency to government debt level for 51 postfinancial crisis Chinese coastal cities. The results indicate that the threshold of economic development level and provincial gross domestic product (per capita gross domestic product: pgdp) are 2.67 and 5.17, respectively. In cities with relatively backward economic development, an expansion of the government debt scale hinders the improvement of the utilisation efficiency of construction land. Also, the threshold value of the government’s accumulated debt level threshold (sd) is 15.83%. When cities fall below the government accumulated debt level threshold (sd < 15.83%), the new debt level has a positive effect on the utilisation efficiency of construction land. When sd > 15.83%, the new debt level impedes the improvement of the utilisation efficiency of construction land. Local governments should reduce their dependence on land finance in cities with high cumulative debt ratios, especially those with negative responses to both thresholds (pgdp and sd thresholds). This study’s findings can provide a reference for a sustainable promotion of new urbanisation in both China and in other countries to avoid the risk of land urbanisation.


2016 ◽  
Vol 8 (6) ◽  
pp. 210 ◽  
Author(s):  
Joseph Ugochukwu Madugba ◽  
Michael Chidiebere Ekwe ◽  
Stella Ogechukwu Okezie

The study evaluation of the contributions of oil revenue on economic development in Nigeria tested the impact of growth rate in oil revenue and growth rate in Gross Domestic product and growth rate in total federally collected revenue of the Government from 1991 to 2012. Regression analysis was used to carry out data analysis with the aid of SPSS version 20. Results showed that a unit change in growth rate of oil revenue will lead to an equal unit change in growth rate of gross domestic product. The study recommends that federal government should intensify efforts to increase revenue derived from oil especially as it impacts on GDP and federally collected revenue.


Author(s):  
Y. Marko ◽  
V. Kuzmenko

The article provides the importance of Ukraine's economic development to ensure national security, highlights the main internal and external threats to Ukraine's national security, such as: hybrid economic war, the "needle" of loans from the International Monetary Fund, communal tariffs, opening the gas market in Ukraine, inefficient introduction of the circulation of domestic agricultural lands and insufficient use of the capabilities of the country's economy. The cyclical nature of economic development is practically proved by distinguishing four phases of economic development of the studied countries for the last ten years, weak efficiency of economic policy of Ukraine and possible applied mechanisms of economic growth. An econometric analysis of GDP of Ukraine and countries that occupy the largest share in Ukrainian imports of goods, the budget of Ukraine and the budget of the Ministry of Defense of Ukraine using the method of least squares and even linear regressions, calculated the intensity of changes in Ukraine's economic processes. The model of gross domestic product of Ukraine depending on the gross domestic product of China, Poland, Russia, Turkey, Germany, Italy, Belarus, the United States and France (nine-factor model), as well as the model of Ukraine's defense budget depending on the domestic gross domestic product product, budget expenditures, taxes, minimum and average wages and inflation (seven-factor model). On the example of the Ministry of Defense of Ukraine as a public sector institution, the registration algorithm for economic (additional) activities by military units and the distribution of revenues to increase the special fund of the state budget of Ukraine and create recovery of the country economy in general.


2020 ◽  
Vol 31 (2) ◽  
pp. 211-220
Author(s):  
Emília Krajňáková ◽  
Vaida Pilinkienė ◽  
Patrik Bulko

The scope of the data presented in this study offers a comprehensive view of the issue of the HEI graduates employability in the Czech Republic and also in the Slovak Republic – related to determinants of economic development and their impact on them. This paper examines the impact of gross domestic product, gross domestic expenditure on research and experimental development by only higher education sector and foreign direct investment on HEI graduates employability. The results indicate that correlation between unemployment of tertiary educated Slovaks and GDP, GERD and FDI values was very big. Correlation relationship of similar determinants, except determinant GERD in conditions of the Czech Republic was characterized as weak. On the other hand, significantly stronger (very big to perfect) correlation affecting employment of tertiary educated Czechs regarding to indicators of gross domestic product, gross domestic expenditure on research and experimental development by sector of higher education and foreign direct investments as well. In conditions of the Slovak Republic, correlation relationship between employment of tertiary educated Slovaks and GDP was almost perfect.


2021 ◽  
Vol 1 (3) ◽  
pp. 555-571
Author(s):  
Aida Azmi Nabila ◽  
Endang Hatma Juniwati ◽  
Fifi Afiyanti Tripuspitorini

Islamic banking has a role to encourage economic development and enhance economic growth. One way to do this is by allocating Islamic banking financing funds to all economic sectors or industrials in Indonesia. There is a mismatch between the growth statistics of financing distribution to Gross Domestic Product based on industrials consisting of seven industrial. This istudy iaims ito idetermine iwhether ior inot ithere iis ia  relationship, iconstribution, and the effect iof ifinancing ichanneled on Indonesia's Gross Domestic Product. The isample iin ithis istudy was determined using ipurposive isampling. iThis iresearch imethod iis ia idescriptive imethod iwith ia iquantitative iapproach. iThe iresults iof  the model test of the effect of BUS and UUS financing on Indonesia’s Gross Dometic Product based on the industrial in 2012-2019 show that not all financing has a relationship, constribution, and the effect to Indonesia’s Gross Domestic Product based on the industrial.


2018 ◽  
pp. 1369
Author(s):  
Rio Surya Wijaya ◽  
I Made Sukartha

National development of a nation includes economic development and Micro, Small and Medium Enterprises (MSMEs). MSME performance needs to be examined because the contribution of the MSME sector to the Gross Domestic Product (GDP) has increased from 57.84% to 60.34% in the last 5 years. This study aims to determine the effect of intellectual intelligence, emotional intelligence, and spiritual intelligence of the owner on the performance of Micro, Small and Medium Enterprises. Research subjects are the performance of UMKM in Denpasar City. The sample determination technique used in this study is Probably sampling used using a simple random technique. There are 100 MSMEs as samples with a questionnaire statement totaling 71 statements. Based on the results of the analysis of research obtained intellectual intelligence has a positive influence on the performance of MSMEs, Emotional Intelligence has a positive influence on the performance of SMEs, and Spiritual Intelligence has a positive influence on the performance of SMEs. Keywords: Intellectual Intelligence, Emotional Intelligence, and Spiritual Intelligence.


2018 ◽  
Vol 4 ◽  
pp. 237802311877362 ◽  
Author(s):  
Xiaorui Huang ◽  
Andrew K. Jorgenson

The authors examine the potentially asymmetrical relationship between economic development and consumption-based and production-based CO2 emissions. They decompose economic development into economic expansions and contractions, measured separately as increases and decreases in gross domestic product per capita, and examine their unique effects on emissions. Analyzing cross-national data from 1990 to 2014, the authors find no statistical evidence of asymmetry for the overall sample. However, for a sample restricted to nations with populations larger than 10 million, the authors observe a contraction-leaning asymmetry whereby the effects of economic contraction on both emissions outcomes are larger in magnitude than the effects of economic expansion. This difference in magnitude is more pronounced for consumption-based emissions than for production-based emissions. The authors provide tentative explanations for the variations in results across the different samples and emissions measures and underscore the need for more nuanced research and deeper theorization on potential asymmetry in the relationship between economic development and anthropogenic emissions.


2015 ◽  
Vol 137 (4) ◽  
Author(s):  
Ammar Mohammed Ameen ◽  
Jagadeesh Pasupuleti ◽  
Tamer Khatib ◽  
Wilfried Elmenreich ◽  
Hussein A. Kazem

This paper proposes a novel prediction model for photovoltaic (PV) system output current. The proposed model is based on cascade-forward back propagation artificial neural network (CFNN) with two inputs and one output. The inputs are solar radiation and ambient temperature, while the output is output current. Two years of experimental data for a 1.4 kWp PV system are utilized in this research. The monitored performance is recorded every 2 s in order to consider the uncertainty of the system’s output current. A comparison between the proposed model and other empirical and statistical models is done in this paper as well. Moreover, the ability of the proposed model to predict performance with high uncertainty rate is validated. Three statistical values are used to evaluate the accuracy of the proposed model, namely, mean absolute percentage error (MAPE), mean bias error (MBE), and root mean square error (RMSE). These values are used to measure the deviation between the actual and the predicted data in order to judge the accuracy of the proposed model. A simple estimation of the deviation between the measured value and the predicted value with respect to the measured value is first given by MAPE. After that, the average deviation of the predicted values from measured data is estimated by MBE in order to indicate the amount of the overestimation/underestimation in the predicted values. Third, the ability of predicting future records is validated by RMSE, which represents the variation of the predicted data around the measured data. Eventually, the percentage of MBE and RMSE is calculated with respect to the average value of the output current so as to present better understating of model’s accuracy. The results show that the MAPE, MBE, and RMSE of the proposed model are 7.08%, −0.21 A (−4.98%), and 0.315 A (7.5%), respectively. In addition to that, the proposed model exceeds the other models in terms of prediction accuracy.


Sign in / Sign up

Export Citation Format

Share Document