Vegetable Prices Research Articles

Hybrid Deep Learning Model for Vegetable Price Forecasting Based on Principal Component Analysis and Attention Mechanism

Abstract With the aim of enhancing the accuracy of current models for forecasting vegetable prices and improving market structures, this study focuses on the prices of bell peppers at the Nanhuanqiao Market in Suzhou. In this paper, we propose a hybrid Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) model for vegetable price forecasting based on Principal Component Analysis (PCA) and Attention Mechanism (ATT). Initially, we utilized the Pearson correlation coefficient to filter out the factors impacting prices. Then, we applied PCA to reduce dimensionality, extracting key price features. Next, we captured local sequence patterns with CNN, while handling time-series features with GRU. Finally, these outputs were integrated via ATT to generate the final prediction. Our results indicate that the hybrid CNN-GRU model, enhanced by PCA and ATT, achieved a Root Mean Square Error (RMSE) as low as 0.16. This performance is 11.11%, 11.11%, and 15.79% better than that of the PCA-CNN, PCA-GRU, and CNN-GRU-ATT models, respectively. Furthermore, in order to prove the effectiveness of our proposed model, the proposed model is compared with the state-of-the-art models and classical machine learning algorithms under the same dataset, the results indicate that our proposed hybrid deep learning model based on PCA and ATT shows the best performance. Consequently, our model offers a valuable reference for vegetable price prediction.

Exploring Price Patterns of Vegetables with Recurrence Quantification Analysis

This study investigates the time-series behavior of vegetable prices in the Central Market of Thessaloniki, Greece, using Recurrence Plot (RP) analysis and Recurrence Quantification Analysis (RQA), which considers non-linearities and does not necessitate stationarity of time series. The period of study was 1999–2016 for practical and research reasons. In the present work, we focus on vegetables available throughout the year, exploring the dynamics and interrelationships between their prices to avoid missing data. The study applies RP visual inspection classification, a clustering based on RQA parameters, and a classification based on the RQA analysis graphs with epochs for the first time. The aim of the paper was to investigate the grouping of products based on their price dynamical behavior. The results show that the formed groups present similarities related to their use as dishes and their way of cultivation, which apparently affect the price dynamics. The results offer insights into market behaviors, helping to inform better management strategies and policymaking and offer a possibility to predict variability of prices. This information can interest government policies in various directions, such as what products to develop for greater stability, identity for fluctuating prices, etc. In future work, a larger dataset including missing data could be included, as well as a machine-learning algorithm to classify the products based on the RQA with epochs graphs.

Determinants of food insecurity among adults residing in peri-urban municipal settings in Flanders, Belgium

Food insecurity is a global public health issue associated with noncommunicable diseases. Individual factors are strongly associated with food insecurity, but there is limited literature on the broader impact of both the social and food environments on food insecurity in non-English speaking European countries, given that the research was predominantly conducted in Anglophone settings. In addition, these studies have mostly been conducted in urban areas. Therefore, this study aimed to identify the main determinants of food insecurity among adults living in peri-urban areas in Flanders, Belgium. Data on socio-demographics, neighborhood social cohesion, social isolation, and perceived food environments were collected from 567 adults through a self-administered questionnaire, and objective data on the food environment were obtained through (commercial) databases on food outlets. Food insecurity was measured using the USDA Household Food Security Survey Module. Multivariable logistic regression models revealed that lower socioeconomic status (OR14.11,95%CI:4.72;61.11), reasonable (OR4.16,95%CI: 2.11;8.47) to poor and very poor (OR6.54,95%CI: 2.11;8.47) subjective health status, and living in private (OR7.01, 95% CI:3.0;17.0) or government-assisted (OR6.32,95%CI: 3.13;13.26) rental housing significantly increased the odds of food insecurity. Additionally, residing in a neighborhood with low (OR2.64, 95% CI:1.13;6.26) to medium (OR2.45,95% CI:1.21;5.11) social cohesion, having a neutral opinion (OR4.12,95%CI:1.51;11.54) about the availability of fruit and vegetables in one's neighborhood, and having an opinion that fruit and vegetable prices are too expensive (OR5.43,95% CI 2.26;14.4) significantly increased the odds of experiencing food insecurity. This study underscores the need for policies that consider factors related to social and food environments, in addition to individual factors, to effectively address food insecurity.

The role of market in motivating farmers to reduce pesticide use: Evidence from vegetable farms in Shiraz

The overuse of pesticides has harmful impacts on both the environment and human health. Implementing efficient techniques is crucial to manage pesticides and reduce negative impacts effectively. In order to achieve this objective, we evaluated the harm of pesticide application in vegetable fields in Shiraz and identified the factors that impact farmers' behavior in using pesticides. The Environmental Impact Quotient (EIQ) indicator was initially utilized to evaluate the effects of pesticide residues on both human health and the environment. Afterwards, the Logit model was employed to investigate the likelihood of excessive pesticide usage among farmers. Our findings suggest that farmers may not give high importance to environmental and human health considerations when deciding on pesticide usage. Market incentives, such as the quantity and price of vegetables produced without pesticide use, play a significant role in reducing pesticide use in Shiraz vegetable farms. The results of the study can help policy makers in implementing pesticide-free agricultural practices.

Erratic Rise in Tomato Prices, Status, Issues, Government Initiatives and Policy Suggestions to Manage the prices of Tomato and other Vegetables

Tomatoes, hold a paramount position in both Indian cuisine and the nation's economy. The status of tomato area and production in India and in states show its importance in Indian economy. India is leading tomato producer in the world. In India, MP and Andhra Pradesh are the largest producer of tomato in India. The erratic weather conditions, pest attack and transport bottlenecks have raised the tomato prices in June to August 2023. In this regard, the paper is to analyze the status and issues in erratic rise in tomato prices, government initiatives and Policy suggestions to manage the prices of tomato and other vegetables. In the study, it is found that the number of reasons that has led to rise in prices starting from poor prices received for tomato for rabi crop, rise in temperature in May – June and to high rainfall in July end. Government has then initiated number of needed measures to support both producers and consumers from creating the awareness, purchase of produce from surplus areas and then distribution of produce in high price areas. To prevent the abnormal price situations in tomatoes or other vegetables, there is need of a multi-pronged approach involving both short-term relief and long-term strategies. As a policy suggestion, to combat such crisis in future, a collaborative effort and coordination required among government agencies, weather departments, agricultural experts, extension machinery and farmers themselves is essential.

Volatility analysis and forecasting of vegetable prices using an ARMA‐GARCH model: An application of the CF filter and seasonal adjustment method to Korean green onions

AbstractThe vegetable market experiences significant price fluctuations due to the complex interplay of trend, cyclical, seasonal, and irregular factors. This study takes Korean green onions as an example and employs the Christiano–Fitzgerald filter and the CensusX‐13 seasonal adjustment methods to decompose its price into four components: trend, cyclical, seasonal and irregular fluctuations. To estimate the price volatility and forecast future prices, we apply an ARMA‐GARCH model and use various statistical measures to assess the prediction accuracy. The empirical results demonstrate the effectiveness of ARMA(1, 2)‐GARCH(1, 1) model in modeling and forecasting the seasonally adjusted price of Korean green onions. Our study provides an important reference for expanding research in the field of vegetable price fluctuations and formulating strategies for stabilizing prices. [EconLit Citations: Q11, C22, Q02].

Hybrid approach for vegetable price forecasting in electronic commerce platform

<span lang="EN-US">The significance of the agriculture sector in Malaysia is often overlooked, and there is a notable deficiency in the advancement of digitalization within the country's agricultural domain. The integration of a price forecasting model in the platform enables the relevant parties, including farmers, to make informed decisions and plan their crop selection based on projected future prices. In this research, the authors proposed the hybrid approach with the combination of linear model and non-linear model in doing the vegetable price forecasting model. The hybrid SARIMA-DWT-GANN model is utilized to forecast the monthly vegetable prices in Malaysia. The historical vegetable price data is collected from the FAMA Malaysia and split into training/test set for modelling. The performance of the models is evaluated on the accuracy metrics including MAE, MAPE, and RMSE. The forecasted results using the proposed hybrid model are compared to that using the single SARIMA model. In conclusion, the hybrid SARIMA-DWT-GANN model is superior to the individual model, which obtained the smaller MAE, RMSE, and got the forecast accuracy of at least 95%. </span>

Exploring reasons for high levels of food insecurity and low fruit and vegetable consumption among university students post-COVID-19

High rates of food insecurity and low consumption of fruit and vegetables among university students have been observed prior to the COVID-19 pandemic and intensified during the pandemic. This study aimed to investigate food insecurity among university students and its associations with sociodemographic factors, fruit and vegetable consumption behaviours, and preferred campus programs to address these issues. A convenience sample of 237 Australian university students completed a cross-sectional online survey from October to December 2022. Food insecurity was assessed using the 10-item US Adult Food Security Module, applying the Canadian classification scheme. Sociodemographic variables, fruit and vegetable consumption behaviours, and perceptions of fruit and vegetable access and their affordability were included in the survey. Students were also asked to select the most suitable program(s) and provide reasons for their choice using open-ended questions. Approximately half of respondents (46.4%) were identified as food insecure. The proportion of students meeting the recommended intake of vegetables as specified in the Australian Dietary Guidelines was very low (5.1%) compared with fruit (46.2%). Low fruit consumption was significantly associated with food insecurity (OR = 1.81; 95%CI 1.03, 3.18, p = 0.038). Factors such as the perceived lower accessibility and higher price of fruit and vegetables were significantly associated with higher odds of food insecurity. In terms of potential programs, a free fruit and vegetable campaign was the most popular program, with affordability and physical access being the most frequently cited reasons. These findings suggest that food insecurity is associated with low fruit and vegetable consumption in university students. Therefore, transforming campus food environments and developing food policies at the university level must be considered to address food and nutrition security in university students.

Vegetable pricing and replenishment decisions based on the optimization model

Vegetables are one of the essential foods in human daily life. Due to the short shelf life, it is difficult to preserve, the supermarket needs to timely and reasonable purchases and pricing. This paper aims to establish a model that can predict vegetable price fluctuations and develop reasonable pricing and replenishment strategies. According to the data given from a wet market, this paper studies the pricing and replenishment decisions of supermarket vegetables. By establishing the SARIMA model and Markov forecast model, the wholesale price of the same project on July 1 is calculated based on the wholesale price forecast of the previous week, and reasonable market demand is predicted. It is found that the predicted results have a reasonable error with the actual situation, and the accuracy is relatively high. The establishment of these two models is of great significance for market regulation. The model has good predictability and practical value, with good dynamic predictive ability, suitable for a reasonable allocation of resources in supermarkets and other trading places to obtain maximum benefit.

Sustainable Food Value Chains: Approaches to Transaction Costs in Agro-Alimentary Systems of Developing Countries—A Chile Case Study

This study delves into the dynamics of price linkages and transaction costs in agricultural markets, emphasizing the sustainability of food supply chains. By exploring vertical and horizontal price linkages in agro-farming value chains of a developing country, it addresses the efficiency of market information transmission and the capacity for arbitrage among chain participants. The methodological core of the research involves analyzing price linkages in Chilean horticultural wholesale markets, focusing on key vegetables such as, onions, lettuce, maize, and tomatoes. This analysis is underpinned by a novel approach that models and estimates time-dependent, conditional threshold bands, extending the traditional cointegration models. This method allows a more nuanced understanding of how agricultural market linkages evolve over time, enhancing our comprehension of price transmission behavior and market integration. The results reveal significant non-linear relationships between fuel prices and vegetable prices, particularly in central Chilean regions. This finding challenges the traditional linear perspective, suggesting that factors such as storage capacity and arbitrage behavior can influence price signal transmission. Such insights are crucial for stakeholders in the agribusiness value chain, offering a deeper understanding of market dynamics and aiding in the development of more sustainable and efficient market strategies. This research contributes significantly to the field of agricultural economics by providing a more robust framework for analyzing market behaviors and transaction costs in the context of sustainability and value chains. Its findings have profound implications for both theory and practice, informing policy-making and strategic decision-making in the agribusiness sector.

Vegetable Price Flow

Abstract: The volatility of vegetable prices poses significant challenges to consumers, producers, and policymakers alike. This research paper examines the price fluctuations of three commonly consumed vegetables: tomatoes, potatoes, and cabbages. Through an analysis of empirical data spanning a specified period, we investigate why tomatoes and cabbages exhibit higher price fluctuations compared to potatoes. Our findings suggest that the short life span and susceptibility to rotting inherent in tomatoes and cabbages contribute significantly to their price volatility. Additionally, the need for extra care in handling these vegetables further exacerbates their price instability. By comparing the magnitude and frequency of price fluctuations among the three vegetables, this study sheds light on the economic implications of such volatility. Ultimately, our research underscores the importance of understanding the factors driving price fluctuations in the vegetable market and suggests avenues for mitigating their impact on consumers, producers, and other stakeholders

Pemberdayaan Kelompok Wanita Tani Cendawan 31 Melalui Peningkatan Produksi Sayuran Dan Pendapatan Di Kota Pangkalpinang

The concept of urban farming refers to the practice of farming in urban areas, which is usually done on limited land such as house yards, rooftops or vacant lots in the city. Urban farming aims to meet the very high food needs of urban communities when there is a scarcity of land for food production in urban areas. The demand for vegetables is not matched by vegetable production, resulting in inflation. Some of the obstacles faced by KWT Cendawan 31 include: vegetable farming is not yet commercially oriented, management is still simple, motivation and awareness of members are still low, production patterns are not well planned, vegetable price information is still limited, marketing channels are not efficient and simple and limited promotion of vegetable products. This farmer women group empowerment program aims to increase vegetable production & income. The methods used in this program are active participatory methods, mentoring and counseling on vegetable production processes from upstream to downstream. The success of the work program carried out was able to overcome the problem of the lack of creativity and innovation of the Cendawan 31 Women Farmers Group (KWT) in developing the planting of types of vegetables, the low production of vegetables in the area of the Cendawan 31 Women Farmers Group (KWT) and being able to arrange a planting schedule, choosing the right type of plant and rotating the planter.

ACSICS: Joint Distribution Mode Integrating Agricultural Industry Chain Logistics Under the Background of Artificial Intelligence

The purpose is to study the new application of artificial intelligence (AI) technology in the Agro logistics industry distribution modes. This work summarizes the problems in agricultural logistics by investigating the current situation of the logistics distribution modes (LDMs) of Agro products and establishes a joint LDM integrating logistics and agricultural industry chain (AIC). An intelligent virtual center is established for the joint LDM according to the specific situation of Xi’an. Experts are invited to evaluate the proposed LDM. The results show that the existing third-party logistics (3PL), agricultural supermarket docking LDM, and company+farmer shared LDM have respective advantages and disadvantages. The virtual center for the proposed joint LDM multiplies the weight matrix [Formula: see text] and fuzzy evaluation matrix A to obtain a comprehensive fuzzy evaluation result. It evaluates the result according to the maximum membership criterion. Most experts have a relatively good evaluation of the joint LDM. In the comprehensive fuzzy evaluation results, the comprehensive “excellent” score is 0.3755, and the comprehensive “good” score is 0.2678. According to the principle of maximum subordination, the AIC logistics integrating Agro products logistics has an excellent performance, and the overall satisfaction level of performance has exceeded 85%. In addition, Yonghui supermarket adopts the joint LDM, and the price of fruits and vegetables is lower than that of other LDMs. Therefore, the proposed AI-based joint LDM can optimize the distribution route, improve distribution efficiency, and save logistics costs to a great extent.

Investigating the intention and behavior of vegetable farmers to adopt IoT technology: survey—based evidence from China

A key instrument for upgrading China’s agriculture is the Internet of Things (IoT). To solve the problem of IoT technology promotion, farmers’ intentions to adopt IoT technology must be transformed into behavior, and their intentions and behaviors must be unified. The multivariate logistic model was used to analyses the factors influencing farmers’ intention to adopt IoT technology and behavioral deviation based on survey data of vegetable farmers in Jiangxi Province. The ISM model was used to investigate the relationship and hierarchy between the factors influencing farmers’ intention to adopt IoT technology and behavioral deviation. The findings revealed that first, a significant deviation exists between vegetable farmers’ IoT technology adoption intention and behavior, with 72.69% of those surveyed having the intention to adopt, but did not follow through. Second, among the 12 factors confirmed as remarkably influencing the deviation, expected return is the most superficial factor; intermediate influencing factors include vegetable price volatility, adoption cost, credit support, related knowledge and skills, and technology maturity; secondary factors include social capital, whether vegetables are registered trademarks, planting scale, planting method, and IoT related equipment supply; and age is the deepest root factor.

Effects of early and late sowing on the profitability of cucumber (Cucumis sativus L.) production

Objective: To analyze how early and late sowing can improve the income of cucumber producers in the state of Michoacán, Mexico. Design/Methodology/Approach: Monthly income, production cost, profit, and benefit-cost ratio were calculated in three sowing scenarios: middle, early, and late. Results: In an early sowing scenario, the income and profit of the producers increase by 10.2 and 9.2 million pesos, respectively, compared to the middle sowing scenario. Likewise, in a late sowing scenario, producer income and profits increase by 29.2 and 20.0 million pesos, regarding the middle sowing scenario. Study Limitations/Implications: The negative effects on vegetable prices of temporary excess supply prove the need to plan the surface that will be used for early and late sowing, as well as to create a regulatory body that plans the cucumber sowing area. Findings/Conclusions: Sowing cucumber and other vegetables in early or late dates is recommended, since better production planning will increase the producers’ income and profit.

Enhancing Vegetable Price Forecasting Accuracy: A Hybrid SARIMA- DWT-GANN Approach

In the context of Malaysia's agricultural sector, the development of a robust vegetable price forecasting model holds paramount importance. The pricing dynamics of vegetables can significantly affect various stakeholders, including farmers, distributors, and consumers. The agricultural sector in Malaysia encounters persistent challenges such as supply-demand imbalances, seasonal variations, and market uncertainties, which can lead to income disparities for farmers and disruption in supply chains. Addressing these issues requires accurate and timely predictions of vegetable prices to enhance planning, resource allocation, and decision-making. This study introduces an innovative SARIMA-DWT-GANN hybrid model for vegetable price forecasting. By fusing the strengths of traditional time series modeling with the capabilities of neural networks, the proposed model offers a comprehensive solution to capture both linear and non-linear price patterns. The results demonstrate the superiority of the SARIMA-DWT-GANN model over the individual SARIMA model, as evident from correlation coefficients that closely approach unity and p-values confirming statistical significance. The model's ability to predict price changes has significant implications for making informed decisions throughout the agricultural supply chain. This research provides a robust forecasting tool that not only enhances market efficiency and profitability but also offers a promising solution to address the challenges in Malaysia's agricultural sector.

CONSUMER PREFERENCE TOWARDS THE ATTRIBUTES OF AQUAPONICS PRODUCTS AT PT. TANIKOTA

The increasing awareness of healthy lifestyle among the public has made consumers more selective in choosing their food, particularly vegetables. Aquaponic vegetable products, which are free from pesticides, have emerged as an alternative for health-conscious consumers. This study aimed to identify the characteristics of consumers who purchase aquaponic vegetables based on product attributes at PT. Tanikota and to determine the ranking of attributes of aquaponic vegetables according to consumer preferences. The research method employed in this study was a case study, using a whole population of 70 aquaponic vegetable consumers at PT. Tanikota as the respondents. Data were analyzed using descriptive analysis of frequency distribution. The results of the study revealed that the characteristics of consumers who buy aquaponic vegetables at PT. Tanikota were generally women aged 26-35 years, holding an undergraduate degree, with 3 family dependents, employed in private sectors, and having an income range of 2,600,000-Rp 5,200,000/month. The attributes of aquaponic vegetables at PT. Tanikota were ranked based on consumer preferences, with the level of freshness of vegetables, variety of vegetables, color of vegetables, method of payment, method of purchase, physical form of vegetables, vegetable size, distance, vegetable packaging, and the price of vegetables, respectively. The lower rank of price attributes can be attributed to the lack of aquaponic vegetable cultivation in the city of Bandung, which makes it difficult for consumers to compare the prices offered by PT. Tanikota with those offered by other companies.

The Price Prediction of Vegetables by Using Machine Learning

Vegetable prices are great important in ensuring people's livelihood. With the progress of science and technology, machine learning algorithms have been applied in the field of vegetable price prediction. This paper analyzed the model that has been used in vegetable price prediction and its results and compared the accuracy of each model. The study in this paper concluded that LSTM is suitable for handling sequence data with long-term dependence but this model requires a large amount of data for training. ARIMA is suitable for short-term predictions but may not fit well with non-stationary and nonlinear data. In addition, this paper introduces other algorithms. For example, the paper shows How to use Lasso regression to compress the input variables and how to reduce model complexity and improve model generalization ability. The BP neural network was used to fit the output variables to improve the model fitting ability. This paper further studies and summarizes the combination of each model and the accuracy of the combined model for predicting vegetable prices. It can be seen that the prediction error of the L-LBNN model is very small, which can be effectively used in the price prediction of vegetables. The purpose of this study is to summarize the current situation of predicting vegetable prices with machine learning algorithms to provide guidance and inspiration for researchers and to promote the development of the use of machine learning in the field of price prediction of vegetables.

Comparative Analysis of ARIMA and LSTM Models for Agricultural Product Price Forecasting

The fluctuations in vegetable prices can have an impact on the economy. Machine learning can identify price trend changes. This study investigates the performance of ARIMA and LSTM models in predicting price trends for agricultural products, focusing on greens and lotus roots. The objective was to ascertain the superior model in terms of accurately reflecting market oscillations—a critical aspect for stakeholders in the agricultural sector. The investigation contrasted the ARIMA model's adeptness at detecting linear tendencies against the LSTM's capacity to decode intricate nonlinear dynamics. Empirical assessment employing metrics such as RMSE, MAE, and SMAPE disclosed a consistent supremacy of the ARIMA model over the LSTM in both datasets. This was particularly evident within the lotus root forecasts, where the discrepancy in error metrics for LSTM was remarkably pronounced. The outcomes indicate that notwithstanding the sophisticated structure of LSTM, ARIMA models maintain their status as robust and precise tools for agricultural time series forecasting. This is especially pertinent in contexts demanding computational efficiency and model interpretability. This investigation evaluates the efficacy of ARIMA and LSTM models in forecasting time-series data for agricultural commodities.

Price volatility and demand of vegetables in three Brazilian Southeast supply centers between 2017 and 2021

Vegetable consumption has increased in recent years due to the predisposition of people to have a healthy diet, which includes the ingestion of fibers, vitamins, and minerals present in fruits and vegetables. In Brazil, lettuce, tomato, carrot, onion, and potato are the five vegetables with the highest consumption. In this study, the price volatility and the price elasticity measure (price elasticity of supply, price elasticity of demand, or price inelasticity) of lettuce, tomato, carrot, onion, and potato were evaluated in three supply centers (CEAGESSP, CEASAMINAS e CEASA/RJ) between 2017 to 2021. The results indicated that all the evaluated products had similar price volatility behavior between 2019 to 2021 in the three supply centers. Moreover, the years with higher instabilities of prices were 2020 for potatoes and carrots, 2019 for lettuce, and 2018 for onion. The price elasticity or inelasticity had independent behavior per supply center. However, there are some periods of inelasticity where the price does not influence the quantity demanded or supplied of the evaluated products. In conclusion, there is high variability of price and volume for tomato, potato, onion, lettuce, and carrot during the year. There was a negative in the price and volume of vegetables which indicates that the reduction of volume increases the price of vegetables. The prices of commercialized vegetables are strongly influenced by the forces of supply and demand, which configures a seasonal characteristic.