[논문]Forecasting performance and determinants of household expenditure on fruits and vegetables using an artificial neural network model

Kim, Kyoung Jin; Mun, Hong Sung; Chang, Jae Bong

doi:10.7744/kjoas.20200064

Forecasting performance and determinants of household expenditure on fruits and vegetables using an artificial neural network model 원문보기

Korean journal of agricultural science, v.47 no.4, 2020년, pp.769 - 782

Kim, Kyoung Jin (Department of Livestock Business and Marketing Economics, Konkuk University) , Mun, Hong Sung (Department of Livestock Business and Marketing Economics, Konkuk University) , Chang, Jae Bong (Department of Food Marketing and Safety, Konkuk University)

Abstract ▼ AI-Helper

Interest in fruit and vegetables has increased due to changes in consumer consumption patterns, socioeconomic status, and family structure. This study determined the factors influencing the demand for fruit and vegetables (strawberries, paprika, tomatoes and cherry tomatoes) using a panel of Rural Development Administration household-level purchases from 2010 to 2018 and compared the ability to the prediction performance. An artificial neural network model was constructed, linking household characteristics with final food expenditure. Comparing the analysis results of the artificial neural network with the results of the panel model showed that the artificial neural network accurately predicted the pattern of the consumer panel data rather than the fixed effect model. In addition, the prediction for strawberries was found to be heavily affected by the number of families, retail places and income, while the prediction for paprika was largely affected by income, age and retail conditions. In the case of the prediction for tomatoes, they were greatly affected by age, income and place of purchase, and the prediction for cherry tomatoes was found to be affected by age, number of families and retail conditions. Therefore, a more accurate analysis of the consumer consumption pattern was possible through the artificial neural network model, which could be used as basic data for decision making.

주제어

표/그림 (8)

표 Table 1. Summary statistics of expenditure prices and demographics for strawberry and paprika.
표 Table 2. Summary statistics of expenditure prices and demographics for tomato and cherrytomato.
그림 Fig. 1. Structure of artificial neural network for strawberry. O1, output node; B1-B2, bias node; H1-30, hidden node; I1-29, input node.
표 Table 3. Relative importance of independent variable (Zi, %).
표 Table 4. Result of Hausman test.
표 Table 5. Result of fixed effect model for strawberry and paprika.
표 Table 6. Result of Fixed effect model for tomato and cherrytomato.
표 Table 7. Result of mean squared error (MSE) and Diebold and Mariano (DM) test for Artificial neural network model (ANN) and Fixed effect model (FEM).

참고문헌 (28)

Bell A, Jones K. 2015. Explaining fixed effects: Random effects modeling of time-series cross-sectional and panel data. Political Science Research and Methods 3:133-153.

상세보기
Byeon HW. 2017. Exploring influence factors for peer attachment in Korean youth based on multi-layer perceptron artificial neural networks. Journal of the Korea Convergence Society 8:209-214. [in Korean]
Cho SH, Byeon HW. 2015. A prediction modeling fore endocrine disorders in Korean elderly. Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology 5:213-222. [in Korean]
Diebold FX, Mariano RS. 1991. Comparing predictive accuracy I: An asymptotic test. Institute for Empirical Macroeconomics. Federal Reserve Bank of Minneapolis, Minnesota, USA.
Galeshchuk S. 2016. Neural networks performance in exchange rate prediction. Neurocomputing 172:446-452.

상세보기
Garson GD. 1991. Interpreting neural-network connection weights. AI Expert 6:46-51.
Jeong KS. 2018. Application of artificial neural network model to an analysis of the factors affecting the intention of the vulnerable class to move to Hangbok housing in Incheon. Housing Studies 26:55-78. [in Korean]
Kaya T, Aktas E, Topcu I, Ulengin B. 2012. Modeling toothpaste brand choice: An empirical comparison of artificial neural networks and multinomial probit model. International Journal of Computational Intelligence Systems 5:674-687.
Kim HY, Won CH. 2018. Forecasting the volatility of stock price index: A hybrid model integrating LSTM with multiple GARCH-type models. Expert Systems with Applications 103:25-37.

상세보기
Kim JU, Kim SY, Lee YS. 2016. An analysis of substitution relationships between domestic and imported fruits using cyclical function approach. Korean Journal of Agricultural Management and Policy 43:305-327. [in Korean]
Kim SY, Jeon SG, Kim TY, Lee GS. 2017. Analysis of the factors influencing consumers' visit frequency and food expenditures across the retail food channels. Korean Food Marketing Association 488-507. [in Korean]
Kim SY, Kim JU, Lee YS. 2015. An analysis on seasonality and substitution in the demand for fruits. Journal of Rural Development 38:1-24. [in Korean]
Le XH, Ho HV, Lee GH. 2018. River steamflow prediction using a deep neural network: A case study on the Red River, Vietnam. Korean Journal of Agricultural Science 46:843-856.
Lee CS, Yang SB. 2017. Development of yield forecast models for vegetables using artificial neural networks: The case of chili pepper. Korea Journal of Organic Agriculture 25:555-567. [in Korean]
Lee GI, Choi JH. 1999. Seasonal fruit demand analysis with AIDS. Journal of Rural Development 22:19-34. [in Korean]
Lee HS, An H, Kim HD, Lee JJ. 2018. Prediction of pollution loads in the Geum River upstream using the recurrent neural network algorithm. Korean Journal of Agricultural Science 46:67-78. [in Korean]
Min IS, Choi PS. 2010. STATA panel data analysis. Jiphil Media, Seoul, Korea. [in Korean]
Mun HS, Chang JB. 2019. Household demand for fruits and vegetables using the QUAIDS model. Journal of Agriculture & Life Science 53:141-155. doi.org/10.14397/jals.2019.53.6.141 [in Korean]

상세보기
Moon TS, Choi JH, Kim SH, Cha JH, Yeon HS, Kim CW. 2008. Prediction of influent flow rate and influent components using artificial neural network (ANN). Journal of Korean Society on Water Environment 24:91-98. [in Korean]
Noh SJ, Lee SH, Cho JH. 2012. Estimates of price and expenditure elasticities of demand for imported orange and domestically produced fruits in Korea. Journal of Rural Development 35:81-96. [in Korean]
Pao HT. 2008. A comparison of neural network and multiple regression analysis in modeling capital structure. Expert Systems with Applications 35:720-727.

상세보기
Park MS, Lee MS, Park HU. 2017. Changes in fruit consumption trends and countermeasures of the fruit industry. Korea Rural Economic Institute, Naju, Korea. [in Korean]
Park YS, Kwon OS. 2020. An analysis of household fruit and vegetable demands using the MDCEV model. Korean Journal of Food Marketing Economics 37:55-79. [in Korean]
Terzi S. 2007. Modeling the pavement serviceability ratio of flexible highway pavements by artificial neural networks. Construction and Building Materials 21:590-593.

상세보기
Tukey JW. 1977. Exploratory data analysis. Exploratory data analysis Addison-Wesley Publishing Company, Boston, USA.
Yun SJ, Lee CS, Yang SR. 2016. Development of price forecast models for international grains using artificial neural networks. The Korean Journal of Agricultural Economics 57:83-101. [in Korean]
Yu SH, Li Z. 2018. Forecasting stock price index volatility with LSTM deep neural network. Recent Developments in Data Science and Business Analytics 2018:265-272.
Zhu YH, Kang JH, Park SH. 2015. The industry-specific determinants for export performance in Korean manufacturing industries: Fixed effect vs. random effect model. International Area Studies Review 19:43-59. [in Korean]

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증