Machine learning applied to understand perceptions, habits and preferences of lamb meat consumers in the Brazilian semi-arid region

被引:6
|
作者
Silveira, Robson Mateus Freitas [1 ]
Lima, Debora Fonteles [2 ]
Camelo, Beatriz Veloso [2 ]
Mcmanus, Concepta [3 ]
da Silva, Valdson Jose [4 ]
Ferreira, Josiel [5 ]
Costa, Helio Henrique Araujo [6 ]
Dias, Carlos Tadeu dos Santos [7 ]
Contreras-Castillo, Carmen Josefina [8 ]
Paveloski, Alessandro [9 ]
Vecchi, Laura Bertolaso De [1 ]
Sales, Arthur Pereira [10 ]
Sarries, Gabriel Adrian [7 ]
Landim, Aline Vieira [2 ]
机构
[1] Univ Sao Paulo, Luiz Queiroz Coll Agr ESALQ, Dept Anim Sci, Piracicaba, SP, Brazil
[2] Vale Acarau State Univ UVA, Ctr Agrarian & Biol Sci, Anim Sci Dept, Sobral, CE, Brazil
[3] Brasilia Univ UNB, Biol Inst, BR-70910900 Brasilia, DF, Brazil
[4] Fed Rural Univ Pernambuco UFRPE, Dept Anim Sci, Recife, Brazil
[5] Inst Zootecnia, Ctr Pesquisa & Desenvolvimento Zootecnia Diversifi, BR-13380011 Sao Paulo, Brazil
[6] Vet & Agro Anim Nutr, BR-62900000 Russas, CE, Brazil
[7] Luiz Queiroz Coll Agr ESALQ, Dept Exact Sci, USP, Piracicaba, Brazil
[8] Univ Sao Paulo, Luiz Queiroz Coll Agr ESALQ, Dept Agrifood Ind Food & Nutr, Piracicaba, SP, Brazil
[9] Univ Sao Paulo, Luiz Queiroz Coll Agr ESALQ, MBA Data Sci & Analyt, Piracicaba, SP, Brazil
[10] Univ Pecs, Fac Business & Econ, H-7622 Pecs, Hungary
关键词
Sheep meat; Semi-arid region; Survey; Multivariate analysis; SHEEP; QUALITY;
D O I
10.1016/j.smallrumres.2023.107088
中图分类号
S8 [畜牧、 动物医学、狩猎、蚕、蜂];
学科分类号
0905 ;
摘要
The objective of this study was to characterize the profile of the lamb consumer in the Brazilian semi-arid region using a machine learning approach. A total of 347 questionnaires with questions about socioeconomic aspects, consumption habits and preferences, meat preparation, and appreciation due to product quality were applied. A combination of cluster analysis (hierarchical and k-means), canonical discriminant analysis, neural network, and tree analysis were performed. The machine algorithms revealed three clusters: Traditional profile - Mature rural consumers, married or single, low level of education, low salary level, average consumption of meat, who do not pay for quality and do not know the benefits of lamb products; Emerging profile: Young men and women, single, with a high level of education, intermediate salary level, low consumption of meat, pay for quality, and do know the benefits of lamb meat; and Conventional profile: Mature urban consumers who live in the city, married and single, with a high level of education and salary, low consumption of meat, pay for quality and do not know the benefits of lamb meat The neural network confusion matrix for classifying consumers in the profile determined that 75.5% were classified in their group of origin, which validates the construction of the typology of consumers by the cluster analysis algorithms. Age was the main variable to segregate the nodes of the decision tree (P < 0.001): Node 1- < = 22; Node 2 > 22 < 29 and Node 3 > 29 years The use of a machine learning approach was able to reveal three types of consumers and defined patterns that could serve as strategies for increasing consumption and greater insertion of lamb in the meat market, as well as analyzing the perception of Brazilians in relation to the meat quality, where these findings may have implications for labelling schemes, marketing and sales strategies for cooked lamb products.
引用
收藏
页数:9
相关论文
共 38 条
  • [31] Effects of different sources and spatial resolutions of environmental covariates on predicting soil organic carbon using machine learning in a semi-arid region of Iran
    Garosi, Younes
    Ayoubi, Shamsollah
    Nussbaum, Madlene
    Sheklabadi, Mohsen
    GEODERMA REGIONAL, 2022, 29
  • [32] Determining Actual Evapotranspiration Based on Machine Learning and Sinusoidal Approaches Applied to Thermal High-Resolution Remote Sensing Imagery in a Semi-Arid Ecosystem
    Reyes Rojas, Luis A.
    Moletto-Lobos, Italo
    Corradini, Fabio
    Mattar, Cristian
    Fuster, Rodrigo
    Escobar-Avaria, Cristian
    REMOTE SENSING, 2021, 13 (20)
  • [33] Head-cut gully erosion susceptibility mapping in semi-arid region using machine learning methods: insight from the high atlas, Morocco
    Baiddah, Abdeslam
    Krimissa, Samira
    Hajji, Sonia
    Ismaili, Maryem
    Abdelrahman, Kamal
    El Bouzekraoui, Meryem
    Eloudi, Hasna
    Elaloui, Abdenbi
    Khouz, Abdellah
    Badreldin, Nasem
    Namous, Mustapha
    FRONTIERS IN EARTH SCIENCE, 2023, 11
  • [34] Farming systems monitoring using machine learning and trend analysis methods based on fitted NDVI time series data in a semi-arid region of Morocco
    Lebrini, Y.
    Benabdelouahab, T.
    Boudhar, A.
    Htitiou, A.
    Hadria, R.
    Lionboui, H.
    REMOTE SENSING FOR AGRICULTURE, ECOSYSTEMS, AND HYDROLOGY XXI, 2019, 11149
  • [35] Evaluating the Performance of Machine Learning and Deep Learning Techniques to HyMap Imagery for Lithological Mapping in a Semi-Arid Region: Case Study from Western Anti-Atlas, Morocco
    Hajaj, Soufiane
    El Harti, Abderrazak
    Jellouli, Amine
    Pour, Amin Beiranvand
    Himyari, Saloua Mnissar
    Hamzaoui, Abderrazak
    Hashim, Mazlan
    MINERALS, 2023, 13 (06)
  • [36] Mapping clay mineral types using easily accessible data and machine learning techniques in a scarce data region: A case study in a semi-arid area in Iran
    Shahrokh, Vajihe
    Khademi, Hossein
    Zeraatpisheh, Mojtaba
    CATENA, 2023, 223
  • [37] New machine learning approaches to improve reference evapotranspiration estimates using intra-daily temperature-based variables in a semi-arid region of Spain
    Antonio Bellido-Jimenez, Juan
    Estevez, Javier
    Penelope Garcia-Marin, Amanda
    AGRICULTURAL WATER MANAGEMENT, 2021, 245
  • [38] Long-term monitoring chlorophyll-a concentration using HJ-1 A/B imagery and machine learning algorithms in typical lakes, a cold semi-arid region
    Ren, Jianhua
    Zhou, Haoyun
    Tao, Zui
    Ge, Liu
    Song, Kaishan
    Xu, Shiqi
    Li, Yong
    Zhang, Lele
    Zhang, Xiyu
    Li, Sijia
    OPTICS EXPRESS, 2024, 32 (09): : 16371 - 16397