Coffee price prediction: challenges and solutions with data science

Column

Data Science

Finance

Technology

February 06, 2025

Coffee price prediction: challenges and solutions with data science

Even with technological and methodological advances, the unpredictability of global markets continues to be an obstacle

On January 30, 2025, coffee prices reached records, hitting US$ 4 per pound, according to the Reuters news agency. This historic increase is the result of a combination of factors, such as unfavorable climatic conditions in major producing countries, such as Brazil and Vietnam, in addition to an insufficient supply to meet growing global demand. Financial speculation and high hedging costs also contributed to this price escalation.

This scenario highlights the complexity involved in forecasting coffee prices, a product highly sensitive to climatic, political, and economic variations. The forecasting of commodity prices, especially coffee, is a process that involves several interconnected factors. According to Yeshiwas & Berelie (2020), volatility in commodity prices can be analyzed through còvolatility models, which help understand the interaction between different markets, such as coffee and oil.

However, supply shocks, variations in global demand, and macroeconomic events make building predictive models a challenge. In this scenario, data science is gaining an increasingly relevant role, enabling the analysis of large volumes of historical data in real-time to improve prediction accuracy.

Statistical models, such as AutoRegressive Integrated Moving Average (ARIMA) and Generalized Autoregressive Conditional Heteroskedasticity (GARCH), are useful for predicting financial commodity prices, but still struggle to capture unexpected events (natural disasters and economic crises), as analyzed by Divisekara et al. (2020). This demonstrates that, despite advances in predictive modeling, uncertainty will always be present in the coffee market.

The impact of the climate

Climatic conditions are one of the main factors affecting production and, consequently, coffee prices. Kouadio et al. (2021) state that biophysical models (which combine climatic, physiological, and soil-related factors to estimate crop yield) are fundamental for calculating the productivity of robusta coffee species, especially in regions where the climate varies drastically. Dinh et al. (2022) reinforce this view by demonstrating that precipitation and temperature can be used to predict coffee productivity, allowing for an anticipation of price fluctuations.

Other studies, such as those by Thao et al. (2022), use remote sensing data to improve productivity forecasts, demonstrating that the combination of climatic variables and satellite data can offer important insights for producers and investors.

The influence of macroeconomic factors

Beyond climate, macroeconomic factors play an important role in commodity pricing. Makkonen et al. (2021) analyzed how temperature anomalies and macroeconomic variables influence agricultural futures returns, showing that the interaction between these factors can affect price stability. Nguyen et al. (2022) demonstrated that domestic consumption and global demand dynamics are equally important in predicting coffee prices.

The speculation in the financial market is another relevant factor. Nugroho et al. (2021) used the Vector Error Correction Model (VECM) to analyze the effects of the Covid-19 pandemic on robusta coffee prices in Indonesia, concluding that global uncertainty and exchange rate fluctuations had a significant impact. Furthermore, Deina et al. (2022) showed that models based on Extreme Learning Machines (ELM) can outperform traditional approaches, suggesting that the use of advanced techniques can help reduce the impacts of speculation. The use of artificial intelligence and machine learning models allows for the processing of large amounts of financial and market data, improving projections and making forecasts more assertive.

Government policies

Other essential factors in coffee pricing are government policies and geopolitical events. Furthermore, advances in remote sensing have been enabling a more precise analysis of agricultural supply. Van Viet & Thuy (2023) demonstrated how satellite-derived vegetation indices, such as the Normalized Difference Vegetation Index (NDVI) and the Enhanced Vegetation Index (EVI), can contribute to coffee productivity forecasting, assisting governments and producers in strategic decisions. These indices help estimate vegetation health, allowing for anticipation of impacts from climate on the harvest and adjustment of expectations for supply and demand. Motisi et al. (2022), on the other hand, propose a qualitative model to predict outbreaks of coffee rust, one of the most detrimental diseases to the crop, helping to mitigate agricultural risks that could lead to even greater fluctuations in market prices.

The future

With the global coffee supply pressured by climatic and structural factors, prices are expected to remain volatile in the short term. Although the El Niño climatic phenomenon is not active on the planet in 2025, as indicated by the Climate Prediction Center of the National Oceanic and Atmospheric Administration (NOAA), future climatic events may still impact the performance of major producers, such as Brazil and Colombia. Furthermore, issues such as changes in environmental regulation, sustainability practices, and production costs may play a relevant role in defining the market scenario.

Data science and the adoption of machine learning models to predict trends continue to evolve, enabling more robust analyses by processing large volumes of data and identifying patterns that previously went unnoticed. However, despite these innovations, the complexity of the coffee market continues to present significant challenges for long-term forecasts.

Thus, forecasting commodity prices is a dynamic and challenging process, requiring a multidisciplinary approach that combines statistical models, artificial intelligence, macroeconomic analysis, and environmental monitoring. Even with technological and methodological advances, the unpredictability of global markets remains a significant obstacle to accurate and reliable forecasts.

To access the references of this text click here

Who wrote this column

José Erasmo Silva

José Erasmo Silva é professor, formado em Matemática e Administração, com mais de 25 anos de experiência em gestão empresarial e de pessoas. É mestre e doutor em Administração, com foco em Finanças, e especialista em Data Science e Analytics e em Finanças e Controladoria. Realizou pós-doutorado na Universidade Federal da Bahia (UFBA). Atualmente, atua como professor orientador no MBA em Data Science, Inteligência Artificial e Analytics da USP/Esalq e leciona na EEP/FUMEP e na rede estadual de ensino de São Paulo.

You may also like

Economy, Investments And Banking

October 23, 2026

Financial Education, Behaviors and Biases in Financial Decision Making

Personal financial management represents a growing challenge, influenced by cognitive biases that affect decision-making, even in individuals with high knowledge. The present study analyzed the relationship between the level of financial education and the occurrence of behavioral biases in the financial decision-making of adults residing in Brazil. An applied, quantitative, and descriptive-correlational field survey was conducted by administering a structured questionnaire to 163 respondents. The instrument included sociodemographic variables, financial knowledge and habits, and hypothetical situations to identify cognitive biases. The results indicated that higher levels of financial education were associated with better financial control, saving, and investment practices, with significant correlations with income and schooling. However, the presence of behavioral biases (anchoring, loss aversion, scarcity, optimism/negativity, present bias, status quo, overconfidence, and mental accounting) persisted even among individuals with higher schooling and income, with no statistically significant association with the analyzed sociodemographic variables. It was concluded that financial education, although essential for financial organization and control, was not sufficient to neutralize the influence of cognitive biases. The incorporation of behavioral approaches into financial education programs is suggested.

Keywords: Financial behavior; Behavioral economics; Personal finance; Cognitive heuristics; Cognitive biases.

October 22, 2026

Consumer Journey in the Decision to Purchase Infoproducts in the Digital Environment

The expansion of e-commerce and technological transformation have driven the need to understand consumer behavior regarding infoproducts, whose perceived experience has become crucial for professional development. The study aimed to analyze the factors that influenced the purchase decision of infoproducts in the digital environment, considering the stages of the consumer journey. An applied, quantitative, and descriptive research was conducted through a field survey with 100 consumers from Serra Gaúcha. Data collection occurred via a structured questionnaire, using non-probabilistic sampling. The results revealed a qualified audience with strong “mobile-first” behavior. It was found that the availability of detailed information and social approval were the main attraction triggers in the pre-purchase phase. In the transactional and subsequent stages, the minimization of operational friction, the agility of immediate access, and system security proved crucial for conversion and satisfaction, although gaps in human support efficiency were identified. Retention was based on the trust generated by positive past experiences, overcoming the price factor. It was concluded that the infoproduct consumer journey operates as an integrated system, requiring alignment between technological infrastructure, content curation, and support humanization to ensure engagement.

Keywords: E-commerce; Consumer behavior; Consumer experience; Loyalty; Virtual business.

October 22, 2026

Forecast of Aggregate Default in the Brazilian Financial System by Sarimax Model with Macroeconomic Variables

Aggregate non-payment in the Brazilian financial system is a crucial indicator of credit risk, the prediction of which is regulated by CMN Resolutions n.° 4.557/2017 and 4.966/2021 for the prospective measurement of expected losses. Aggregate non-payment was modeled and predicted using the SARIMAX model, projecting its trajectory until December 2026 under optimistic, base, and pessimistic scenarios. 164 monthly observations (July/2012 to February/2026) and macroeconomic variables such as unemployment, Selic, IPCA, IBC-Br, and household debt were used. The specification with contemporaneous variables was selected based on information criteria and coefficient stability, and residual diagnostics confirmed statistical adequacy, with a MAPE of 3.12%. Historical non-payment ranged between 4.33% and 7.64%. The estimation identified unemployment (β = 0.2534; p < 0.001) and Selic (β = 0.2128; p < 0.001) as the main positive determinants, with strong temporal persistence (AR(1) = 0.8965). Selic showed increasing correlation with non-payment (r = 0.62 at lag 12), while unemployment demonstrated a contemporaneous effect (r = 0.33). Projections indicated non-payment between 6.30% and 7.98% in December 2026, with a range of 1.68 percentage points, highlighting direct implications for provisioning in financial institutions.

Keywords: Unemployment; Predictive modeling; Monetary policy; Loss provisioning; Time series.