Google Trends como sinal antecipado no comércio internacional de flores
DOI:
https://doi.org/10.1590/2447-536X.v31.e312959Palavras-chave:
floricultura, dados online, importações, poder preditivoResumo
Este estudo investiga o potencial preditivo do Google Trends para as importações de flores dos EUA, examinando se as flutuações nos volumes de busca online podem antecipar mudanças nos padrões de importação. Dados mensais de importação de flores de 2004 a 2023 foram analisados em conjunto com quatro índices de busca do Google por meio de uma avaliação comparativa de modelos de séries temporais, incluindo ARIMA, ARIMAX e SARIMAX. A análise revela padrões preditivos claros, enfatizando a importância de incorporar a sazonalidade nas previsões.Os resultados indicam que o modelo SARIMAX, que considera explicitamente componentes sazonais, supera consistentemente modelos mais simples, alcançando um erro percentual ab- soluto médio (MAPE) de 7,04%. Entre os quatro índices de busca examinados, apenas o índice de distribuição — composto por termos relacionados a floriculturas e serviços de entrega — demonstrou poder preditivo estatisticamente significativo. Essa descoberta sugere que o interesse do consumidor na acessibilidade e entrega de flores influencia fortemente a dinâmica das importações.O estudo contribui com evidências originais que apoiam o uso do Google Trends como indicador antecipado no comércio internacional de flores. Ao integrar o comportamento de busca online aos modelos de previsão, os envolvidos podem obter insights oportunos sobre a demanda de mercado, potencialmente melhorando a gestão da cadeia de suprimentos, o planeja- mento de estoque e a capacidade de resposta operacional.No geral, esta pesquisa destaca o valor dos dados de busca digital como uma ferramenta prática e econômica para antecipar tendências nos mercados globais de flores e embasar decisões estratégicas.
Downloads
Referências
ARIZTON ADVISORY AND INTELLIGENCE. U.S. floral gifting market – Industry outlook & forecast 2025–2030 (Report No. ARZ19657053). United States: Arizton Advisory and Intelligence, 2025. Available at: https://www.arizton.com/market-reports/floral-gifting-market-in-united-states-2025 Accessed on: May 15, 2025.
BANTIS, E.; CLEMENTS, M.; URQUHART, A. Forecasting GDP growth rates in the United States and Brazil using Google Trends. International Journal of Forecasting, v.39, n.4, p.1909-1924, 2022. https://doi.org/10.1016/j.ijforecast.2022.10.003
BOONE, T.; GANESHAN, R.; HICKS, R. L.; SANDERS, N. R. Can Google Trends improve your sales forecast? Production and Operations Management, v.27, n.10, p.1770-1774, 2018. https://doi.org/10.1111/poms.12839
CASTELLACCI, F.; SANTOALHA, A. Does digitalisation affect the adoption of electric vehicles? New regional-level evidence from Google Trends data. Regional Studies, v.59, n.1, p.2358829, 2025. https://doi.org/10.1080/00343404.2024.2358829
CHAUDHADY, A.; CHOI, S. Forecasting fish import using deep learning: a comprehensive analysis of two different fish varieties in South Korea. Smart Media Journal, v.12, n.11, p.134-144, 2023. https://doi.org/10.30693/SMJ.2023.12.11.134
CHOI, H.; VARIAN, H. Predicting the present with Google Trends. Economic Record, v.88, n.1, p.2-9, 2012. https://doi.org/10.1111/j.1475-4932.2012.00809.x
CREDENCE RESEARCH. Flower delivery service market by product (rose, tulip, orchid, lily, gerbera, sunflower, carnations, others); by occasion (corporate event, wedding, personal & gifting, sympathy); by type (bouquets, flowers for vases, cut flowers, plants); by application (commercial, household) - Growth, share, opportunities & competitive analysis, 2024-2032. United States: Credence Research, 2025. Available at: https://www.credenceresearch.com/report/flower-delivery-service-market. Accessed on: 26 April 2025.
DE LUCA, G.; ROSCIANO, M. Google Trends data and transfer function models to predict tourism demand in Italy. Journal of Tourism Futures, v.10, n.1, p.1-17, 2024. https://doi.org/10.1108/jtf-01-2023-0018
DERA, P.; KLIMIUK, K.; KALINOWSKA-BESZCZYŃSKA, O.; BALWICKI, Ł. Digital smoke signals: Event-driven online search trends in Heated Tobacco Products in Poland. Tobacco Prevention & Cessation, v.10, n.May, p.20-18332, 2024. https://doi.org/10.18332/tpc/187280
DIAZ-BALTEIRO, L.; ALFRANCA, O.; VOCES, R.; SOLIÑO, M. Using Google search patterns to explain the demand for wild edible mushrooms. Forest Policy and Economics, v.152, p.102993, 2023. https://doi.org/10.1016/j.forpol.2023.102993
DRECHSLER, M.; HOLZAPFEL, A. Decision support in horticultural supply chains: a planning problem framework for small and medium-sized enterprises. Agriculture, v.12, n.11, p.1922, 2022.
GRAND VIEW RESEARCH. U.S. floriculture market size, share & trends analysis report by product (bedding & garden plants, potted plants), by distribution channel (offline, online), by end use (commercial, industrial), and segment forecasts, 2024–2030 (Report No. GVR-4-68040-395-2). United States: Grand View Research, 2025. Available at: https://www.grandviewresearch.com/industry-analysis/us-floriculture-market-report. Accessed on: April 26, 2025.
HUANG, H.; CUAN, X.; CHEN, Z.; ZHANG, L.; CHEN, H. A multiregional agricultural machinery scheduling method based on hybrid particle swarm optimization algorithm. Agriculture, v.13, n.5, p.1042, 2023. https://doi.org/10.3390/agriculture13051042
HODBOD, A.; HOMMES, C.; HUBER, S. J.; SALLE, I. The COVID-19 consumption game-changer: Evidence from a large-scale multi-country survey. European Economic Review, v.140, p.103953, 2021. https://doi.org/10.1016/j.euroecorev.2021.103953
HYNDMAN, R. J.; KHANDAKAR, Y. Automatic time series forecasting: the forecast package for R. Journal of Statistical Software, v.27, n.3, p.1–22, 2008. https://doi.org/10.18637/jss.v027.i03
JIAO, E. X.; CHEN, J. L. Tourism forecasting: A review of methodological developments over the last decade. Tourism Economics, v.25, n.3, p.469-492, 2019. https://doi.org/10.1177/1354816618812588
KANTASA-ARD, A.; NOUIRI, M.; BEKRAR, A.; AIT EL CADI, A.; SALLEZ, Y. Machine learning for demand forecasting in the physical internet: a case study of agricultural products in Thailand. International Journal of Production Research, v.59, n.24, p.7491–7515, 2020. https://doi.org/10.1080/00207543.2020.1844332
LESSOUA, A.; MUTASCU, M.; TURCU, C. Firm performance and exports: evidence from the romanian wine industry. Journal of Wine Economics, v.15, n.2, p.207-228, 2020. https://doi.org/10.1017/jwe.2020.28
LEWIS, C.D. Industrial and Business Forecasting Methods. Londres: Butterworths, 1982.
MANKIW, N.G. Principles of Economics. 6th edition. Mason: Editorial SA Ediciones Paraninfo, 2012. 705p.
NIÑO, G.; JANZEN, J. Valentine’s Day and the Gains from Agricultural Trade: Cut Flowers in the US. Farmdoc Daily, v.2025, n.2, p.1-8, 2025.
PITCHAYADOL, P. Farmer’s adoption intention towards eco-innovation in Thailand. ASEAN Journal of Management and Innovation, v.5, n.2, p.62–79, 2018. https://doi.org/10.14456/ajmi.2018.31
RAJPUT, D.; WANG, W.; CHEN, C. Evaluation of a decided sample size in machine learning applications. BMC Bioinformatics, v.24, 2023. https://doi.org/10.1186/s12859-023-05156-9
REN, S.; CHAN, H. L.; SIQIN, T. Demand forecasting in retail operations for fashionable products: methods, practices, and real case study. Annals of Operations Research, v.291, p.761–777, 2020. https://doi.org/10.1007/s10479-019-03148-8
ROMBACH, M.; DEAN, D. L.; OLYNK WIDMAR, N. J.; BITSCH, V. “Oh, you shouldn’t have!” Understanding key factors impacting cut flowers gifting preferences in Germany. Horticulturae, v.7, n.10, p.368, 2021. https://doi.org/10.3390/horticulturae7100368
SARI, M.; DURAN, S.; KUTLU, H.; GULOGLU, B.; ATIK, Z. Various optimized machine learning techniques to predict agricultural commodity prices. Neural Comput & Applic, v.36, p.11439-11459, 2024. https://doi.org/10.1007/s00521-024-09679-x
SILVA, E.S.; HASSANI, H.; MADSEN, D.Ø.; GEE, L. Googling fashion: forecasting fashion consumer behaviour using Google Trends. Social Sciences, v.8, n.4, p.111, 2019. https://doi.org/10.3390/socsci8040111
SPENCE, J.; KOLEVA, B.; BENFORD, S.; DARZENTAS, D.; FLINTHAM, M.; GLOVER, K.; WAGNER, H.; GIBSON, R.; THORN, E. “More than a cliché”: Experiencing Hybrid Gifting in the Wild. ACM Transactions on Computer-Human Interaction, v.30, p.1-31, 2023. https://doi.org/10.1145/3577015
SULLIVAN, E. Understanding from machine learning models. The British Journal for the Philosophy of Science, v.73, p.109-133, 2020. https://doi.org/10.1093/bjps/axz035
SUN, R. “You need to listen to the market!”: Making decisions through senses in China’s largest cut-flower market. American Behavioral Scientist, p.00027642241246684, 2024. https://doi.org/10.1177/00027642241246684
TAMASIGA, P.; ONYEAKA, H.; BAKWENA, M.; HAPPONEN, A.; MOLALA, M. Forecasting disruptions in global food value chains to tackle food insecurity: The role of AI and big data analytics – A bibliometric and scientometric analysis. Journal of Agriculture and Food Research, v.14, p.100819, 2023. https://doi.org/10.1016/j.jafr.2023.100819
THIRUMALAI, S.; SINHA, K.K. Customization of the online purchase process in electronic retailing and customer satisfaction: An online field study. Journal of Operations Management, v.29, n.5, p.477-487, 2011. https://doi.org/10.1016/j.jom.2010.11.009
TROMP, S.O.; VAN DER SMAN, R.G.; VOLLEBREGT, H.M.; WOLTERING, E.J. On the prediction of the remaining vase life of cut roses. Postharvest Biology and Technology, v.70, p.42-50, 2012. https://doi.org/10.1016/j.postharvbio.2012.04.003
VOSEN, S.; SCHMIDT, T. Forecasting Private Consumption: Survey Based Indicators vs. Google Trends. Journal of Forecasting, v.30, n.6, p.565-578, 2011. https://doi.org/10.1002/for.1213
WANG, S.; CHEN, T.; WANG, C.; LIU, Z.; JIA, L.; ZHAO, X. The effect of customer satisfaction on floral product purchase behavior, evidence from Shanghai, China. Scientific Reports, v.13, n.1, p.7945, 2023. https://doi.org/10.1038/s41598-023-35137-0
YANG, Y.; FAN, Y.; JIANG, L.; LIU, X. Search query and tourism forecasting during the pandemic: When and where can digital footprints be helpful as predictors? Annals of Tourism Research, v.93, p.103365, 2022. https://doi.org/10.1016/j.annals.2022.103365
YE, X.; YUE, P. What matters to reshaping consumption patterns in China? Digital inclusion and supply chain. Finance Research Letters, v.59, p.104804, 2024. https://doi.org/10.1016/j.frl.2023.104804
CHELLIAH, B. J.; LATCHOUMI, T. P.; SENTHILSELVI, A. Analysis of demand forecasting of agriculture using machine learning algorithm. Environment, Development and Sustainability, v.26, p.1731-1747, 2024. https://doi.org/10.1007/s10668-022-02783-9
Downloads
Publicado
Como Citar
Edição
Seção
Licença
Copyright (c) 2025 Carlos Fernando Osorio Andrade, Paula Andrea Lopez Herrera, Diego Alonso García Bonilla
Este trabalho está licenciado sob uma licença Creative Commons Attribution 4.0 International License.
