Agricultural Economics
M.R. Haj-Seyedjavadi; R. Heydari
Abstract
IntroductionThe agricultural sector is one of the most basic and vital component in the social and economic structures of any country. Today, with increasing in the world's population and needing to provide food on the other hand, and increasing in the price fluctuations of agricultural products on the ...
Read More
IntroductionThe agricultural sector is one of the most basic and vital component in the social and economic structures of any country. Today, with increasing in the world's population and needing to provide food on the other hand, and increasing in the price fluctuations of agricultural products on the other hand, traditional agriculture is no longer responsible for the sustainable food security of the world population. In recent years, the occurrence of two incidents of the spread of the corona virus and the outbreak of war in Ukraine, have made the price of agricultural products extremely unstable. Today, even many farmers and agricultural associations in developing countries are not aware of the changes in market prices and the latest technological developments in the field of agricultural product prices, and they do not have the ability to discover the optimal price for selling their products. In such a situation, the use of intelligent models in order to accurately forecast the price of agricultural goods is vitally important for farmers and agricultural sector activists.Smart agriculture is an emerging concept that involves the integration of advanced technologies to collect and analyze data in order to solve the challenges and problems of the agricultural sector. In the meantime, forecasting the price of agricultural products involves with some basic challenges; including: 1) Data of agricultural product price is mostly non-linear, unstable, non-normal, and noisy and follows chaotic behavior, 2) There is uncertainty in the forecasted data obtained from different models, 3) In the studies related to price forecasting, the "publishable base model" is not provided in order to provide the forecasted price values. Therefore, the aim of this study is to provide a non-linear hybrid intelligent model for accurate forecasting of the future price of pistachios in the field of smart agriculture through managing the multidimensional nature of data, considering uncertainty in the forecasting data and finally building a publishable base model in the field of product price prediction.The hybrid model proposed in this study has the following innovations; 1) the deep learning neural network model and the Auto-Encoder network have been used to forecast the agricultural product price and determine the optimal lag of price as an input variable simultaneously, 2) The Monte Carlo method has been used as a non-parametric method to provide a confidence interval and calculate the most likely price that can happen, 3) The practical application of price forecasting models, i.e., "publishable base model" is presented in order to provide forecasted price values. Materials and MethodsThe implementation of the proposed hybrid model in this study includes the steps of "data preparation", "data feature engineering", "training and testing the final deep learning neural network model", "building the optimal base model", "creating the most likely price scenarios" using the Monte Carlo method and "inferring new prices or making out-of-sample forecasting" with new data sets” by feeding new price data into the deep learning neural network model. In the proposed hybrid model, data mining techniques are used, including Wavelet Transform (WT), Long-Short Term Memory (LSTM), Auto-Encoder network (AE), Monte Carlo-Markov chain (MCMC) simulation method and the concept of "inferring new prices".In the data preparation stage, using methods such as data smoothing, data rebuilding, correction of duplicate data in several consecutive days, and correction of missing data, the continuous set of pistachio future price time series is prepared to enter the primary model. Also, the wavelet transform function has been used for de-noising the data, the Auto-Encoder network has been used to determine the optimal lag, the Monte Carlo-Markov chain simulation has been used to create the most probable price scenarios, and the deployment concept has been used for out-of-sample forecasting with new data sets. The data used in this study is the time series of the daily price of pistachio futures on the Iran Commodity Exchange in the period from 10/13/2019 to 12/14/2021 in Rials per kilogram. Results and DiscussionThe results of this study showed that 1) by using the wavelet theory to de-noise the data, the error rate of the price data was reduced and the data had a stable trend, 2) the results of the implementation of the Auto-Encoder network showed that the optimal lag of one can be used as an input variable to forecast the future price of pistachios, 3) The outcomes derived from employing Monte Carlo-Markov chain simulation, coupled with out-of-sample forecasting using the new dataset, reveal compelling insights into the future pricing of pistachios on the Iranian Commodity Exchange. According to the analysis, the most probable and sanguine projection places the future price at the price ceiling of 213 thousand Tomans. Impressively, the forecasted price exhibits a minimal variance of merely 0.7% from the actual observed price, attesting to the precision of the proposed model. The overall accuracy of the model stands commendably high at approximately 93%. ConclusionBased on the results, firstly, the forecasted price has a small error with the actual price and this small error shows the power of the built model in forecasting the future price trend of pistachios. Secondly, the alignment of the price resulting from the Monte Carlo simulation with the new price can also be used as a confidence index in risk management for traders and market participants. Thirdly, the process set is the most complete value chain in the production of price forecasting models. Therefore, the use of the proposed hybrid model and the use of the components used in it, i.e. wavelet transform function, Auto-Encoder network, deep learning neural network, Monte Carlo simulation and the concept of inferring new prices; are suggested.
Agricultural Economics
R. Heydari
Abstract
In recent years, the fluctuation in agricultural commodity prices in Iran is increased and thus, accurate forecasting of price change is necessary. In this article, a flexible combined method in modeling monthly prices of beef, lamb and chicken from April 2001 to March 2021, was proposed. In this new ...
Read More
In recent years, the fluctuation in agricultural commodity prices in Iran is increased and thus, accurate forecasting of price change is necessary. In this article, a flexible combined method in modeling monthly prices of beef, lamb and chicken from April 2001 to March 2021, was proposed. In this new method, three different approaches namely simple averaging, discounted and shrinkage methods were effectively used to combine the forecasting outputs of three hybrid methods (MLPANN-GA, MLPANN-PSO and MLPANN-ICA) together. In implementation stage of hybrid methods, based on test and error method, the optimal MLPANN structure was found with 3/2/4–6–1 architectures and the controlling parameters are carefully assigned. The results obtained from three hybrid methods indicate that, based on the RMSE statistical index, the MLPANN-ICA method performs the best when forecasting prices for beef, lamb, and chicken. The outputs of three combination approaches show that the shrinkage method, with a parameter value of K=0.25, achieves the highest prediction accuracy when forecasting prices for these three meats. In summary, the proposed method outperforms the other three hybrid methods overall.
Agricultural Economics
R. Heydari
Abstract
IntroductionMeat is one of the most important sources of animal protein and plays an important role in human nutrition. In addition, meat is one of the main commodities in the basket of Iranian households, so that it included about 20% of food costs in Iran. In recent years, fluctuations in meat prices ...
Read More
IntroductionMeat is one of the most important sources of animal protein and plays an important role in human nutrition. In addition, meat is one of the main commodities in the basket of Iranian households, so that it included about 20% of food costs in Iran. In recent years, fluctuations in meat prices have always been one of the main challenges of the meat market of Iran and every year the imbalance in its market reduces the welfare of consumers and causes damage to producers. In the current situation where the Iran foreign exchange resources are limited and prices of the meat market has many fluctuations, examining the price drivers of meat price in Iran from the perspective of microeconomics and especially the chain of vertical price transmission can be a good guide for policymakers and planners in adopting appropriate policies to control prices and domestic consumption of these products. The purpose of this study is to identify the drivers of the price of meat different types in Iran using the Panel-SVAR model in 30 provinces of the country during the years 2006-2019. Materials and MethodsWe use the panel SVAR methodology developed by Pedroni (2013) to analyze the implications of shocks on the price of meat types. Defining zπt ≡ (yππ‘, xππ‘, sππ‘, mππ‘)′, the heterogeneous panel SVAR model can be formulated as:π΅π zππ‘ = π΄π (πΏ) zππ‘−1 + , π = 1,…,, π‘ = 1, … , π and π’it ∼ (0,Σπ)Where π΅π is the matrix of structural parameters, reflecting the instantaneous relations among model variables, π§ππ‘ is the vector of endogenous variables, (πΏ) is a polynomial of lagged coefficients for ith province. π’ππ‘ ≡ (π’π¦ππ‘, π’xππ‘, π’sππ‘, π’mππ‘)′ is the vector of the structural shocks or innovations in π§ππ‘, the variance-covariance matrix Σπ is diagonal. Assuming π΅π be an invertible matrix, pre-multiply both sides of Equation (1) by , we get the reduced form VAR model:π§it = Ππ (πΏ) π§it−1 + πit where Ππ (πΏ) = π΄π (πΏ), πππ‘ = π’ππ‘ and πit ∼ (0,Ωπ)Moreover, the variance-covariance matrix Ωπ of the reduced form error πππ‘ = (ππ¦ππ‘, πxππ‘, πsππ‘, πmππ‘)′ is full rank and no diagonal. The reason is that the errors are correlated between equations, implying that the innovations are not orthogonal. Traditionally, when this happens, innovations are correlated with each other and the matrix Ωπ can be orthogonal zed by structural Cholesky decompositions. This method imposes an economic structure and allows the specific ordering of the panel SVAR variables. Finally, the contemporary matrix π΅π is of the following form:Bi = Results and DiscussionThe results of Pedroni and Cao co-integration test showed that the hypothesis of no co-integration among the variables could not be rejected. The optimal lags length for the Panel-VAR model, using the criterion of Schwartz-Bayesian, was determined as 2. The unit root test of the circle also showed that the estimated Panel-VAR model provides the stability condition. The results of Panel-VAR Granger causality test also showed that there is a direct or indirect causal relationship between all the studied variables. The results of estimating the "matrix of long-term response function in the Panel-SVAR model showed that all estimated coefficients are significant. The results of the Impulse Response Functions (IRFs) showed that the effect of shocks of the value added of the agricultural sector in the agricultural sector on meat price index, mutton price and beef price is negative and on chicken price is positive, while the shocks effect of the price index of imported inputs (corn, soybean meal and barley), livestock prices and meat prices are positive on meat price changes (chicken, sheep and beef). The maximum and minimum effect of these variables occurred between the first to the fifth period and their effect pattern is sinusoidal, afterwards shocks continue to be almost constant (or with low amplitude). This result shows that the effect of shocks of meat price stimuli in Iran is continuous and stable. The results of analysis of variance and historical decompositions also showed that the shocks related to the value added of the agricultural sector have the least effect and the shocks of the meat price variable have the greatest effect on meat price changes in Iran. The results of analysis of variance and historical analysis also showed that the shocks related to the value added variable of the agricultural sector have the least effect and the shocks of the meat price variable itself have the greatest effect on variation of meat prices in Iran. This result indicates that the impact of agricultural shocks on the meat price of is relatively weak, in contrast, the impact of shocks of the price transmission especially in the short term (beginning of periods) play a vital role.ConclusionIn this study, impulses effect of four variables of the value added of agricultural sector, price index of imported inputs (corn, barley and soybean meal) and livestock price (live chicken, live sheep, live calf) was examined in four channels (equation) of price including meat price index (Total meat market), chicken, mutton and beef using the Panel-SVAR model in 30 provinces during the years 2006-2019. The findings of this study showed that the most important cause of price fluctuations in the Iran meat market is due to shocks to the vertical price transmission channel, especially in the short term. Therefore, preventing from price shocks in the Iran meat market will be one of the most important tools to create efficiency in the market of this product. Managing inflation expectations is a good way to reduce the price of meat in Iran. In addition, the use of appropriate protectionist policies throughout the meat production, distribution and consumption chain, such as monitoring the production, distribution and consumption stages; modify market structure instead of price control; timely provision of production inputs for producers; development of livestock inputs in the country; providing the supply of meat in the stock market; adequate and timely distribution to consumers; cash payments are offered to households and meat producers in the event of price shocks and explosions, is suggested.
R. Heydari Kamalabadi; S.A. Hosseini Yekani; S.M. Mojaverian; A.R. Nikooie
Abstract
Introduction: Uncertainty existence in farmers crop production pulsed on important and necessity of science of risk management in the agricultural sector. The new risk management selects the best tools and techniques to minimize risks and consequences of decisions. Furthermore, determining the nature ...
Read More
Introduction: Uncertainty existence in farmers crop production pulsed on important and necessity of science of risk management in the agricultural sector. The new risk management selects the best tools and techniques to minimize risks and consequences of decisions. Furthermore, determining the nature of the risk of crops yield can provide useful information about how to manage the risk of the agricultural sector. One of the effects of climate change is caused damage in the agricultural sector. Dependence of crops to climate change is caused that climate factors have a determinative role in the occurrence of crops damaged. Performed studies on the economic effects of climate change have shown that climate change has a significant impact on agricultural yield and its production risk. Moreover, climate change influences crop yield and the risk of crop yield. Although several studies have been carried out about the impact of climate change on crops yield in Iran, the effect of climate change on crops yield risk is infrequently considered. Therefore, this article tries to offer a new way for calculating the risk of crops yield using of CVaR in the period 2017-2047 in the zayanderud agricultural system. The innovation of this study can be stated as follows:1) This study used of Value at Risk index, as one of the most important indicators of risk measuring, to measure the risk of crops yield, 2) For calculating of Value at Risk index, different studies are used from a famous probability distribution such as normal distribution, historical data or Monte-Carlo simulation, while in this study tried to calculate VaR index based on the forecasted scenarios of crops yield, and 3) In this study, in order to produce future scenarios of crops yield is used from ANN-PSO combined method for forecasting crops yield.
Materials and Methods: The method of this study includes the following steps:
1) The production of possible scenarios of temperature and precipitation using of AOGCM models: Today, one of the best tools for the production of climate scenarios is Atmosphere-Ocean General Circulation Models (AOGCM).But the main problem in the use of the output of the AOGCM models is the large spatial scale of their computational cells toward the area under study. LARS-WG model is also one of the most famous models to small scale for outputs of AOGCM models. In this study uncertainty related to AOGCM models, is used of for scenarios of all AOGCM models(including A1B, B1 and A2).
2)The production of scenarios of selected crop yield and available water in the period 2017-2047: The production of scenarios of selected crops yield and available water is performed using of combinedmethod of ANN-PSO.To combine neural network with particles warm optimization algorithm, from particles warm optimization algorithm is instead of training the neural network using gradient-based algorithms.
3) Measuring risk of crops yield using of VaR and CVaR indexes: VaR index is one of the most important criteria to measure downside risk that it determines the maximum amount of expected losses of a variable for a certain time period and specific confidence level. In this study (according to the non-normal distribution of crops yield scenarios) is used on the historical simulation approach.
Results and Discussion: In the first phase of research methodology, for producing of climate scenarios from daily available stats related to weather stations of Isfahan, Kabuotarabad, Kuohrang, and Daranwere used. Validation results of LARS-WG model showed that this model is well able to simulate changes of climate parameters. Eventually, 44 scenarios of the maximum temperature, minimum temperature and rainfall wereproduced in each studied stations and for each year. The results of the network design using trial and error methods revealed the best forecast combination model obtained with 3 and6 neurons in the input layer and hidden layer of neural network and assuming the initial population of 200, in PSO algorithm. Results of this step showed that ANN-PSO model is well able to forecast crops yield (wheat, barley, maize and alfalfa) and available water. Furthermore, calculating VaR and CvaR criterain confidence level %95 and for future period of 2017-2047, showed that the values of these two criterions for wheat, barley, maize and alfalfa were equal to (4240, 4205), (4062, 4057), (49061,48480) and (10875,10743) kg/ha. The comparison of the values of these two criterions with the values of last period also showed that for all selected crops, VaR and CvaR criterions is bigger in future period toward last period.
Conclusions: The new offered method can calculate the risk of crops yield due to climate change. The more accurate measuring of risk using of new methods such as CVaR can be suitable guidance for policy man to better management of production risk of crops.
M. Daneshvar Kakhki; R. Heidari Kamalabadi
Abstract
AbstractThis study is an attempt to investigate the influence of targeting subsidies on price transmission pattern in Iran's egg market. The targeting subsidies plan was imposed by 20 December 2010. Using of daily Price time series data, the study was conducted during December 2009 to October 2011. Using ...
Read More
AbstractThis study is an attempt to investigate the influence of targeting subsidies on price transmission pattern in Iran's egg market. The targeting subsidies plan was imposed by 20 December 2010. Using of daily Price time series data, the study was conducted during December 2009 to October 2011. Using ECM model, price transmission models were estimated for the two periods (e.g. before and after imposing the targeting subsidies plan. Results present a decrease in the transmission speed of increasing and decreasing of the wholesale price after the targeting subsidies plan. Comparison between significant levels of negative and non-negative residuals variables indicated that negative deviations from long-run equilibrium relationship are not adjustable. Having compared the price transmission elasticities in long run with short run, the amount and value of transmission elasticities has been reducing after imposing the targeting subsidies plan. The comparison of symmetric price transmission tests show that the targeting subsidies plan lead to the asymmetric of price transmission Iran's egg market. It is concluded that improvement of infrastructure, reduction of government intervention and creating producers’ cooperation is effective to improve the daily price transmission of Iran's egg market.
