<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>In recent decades, Fuzzy Time Series (FTS) has become a competitive, sometimes complementary, approach to classical time series methods such as that of Box-Jenkins. This study has two different purposes: a theoretical purpose, presenting an overview of the fuzzy logic and fuzzy time series models, and a practical purpose, which is to estimate and forecast monthly international coffee prices during the period 2000-2022. Analysing and forecasting the dynamics of coffee prices is of great interest to producers, consumers, and other market actors in managing and making rational decisions. The findings showed that international coffee prices exhibited significant fluctuations, with large increases and decreases influenced mainly by the level of top-ranked producers. The forecasted results revealed that a decrease in prices during the next six months (Jan 2023 to June 2023) is expected. Based on the results, it is also clear that the FTS models are more flexible and can be applied in forecasting time-series variables. At the same time, volatility and, sometimes, the unexpected swingsin coffee prices continue to draw more criticism and raise different issues regarding the roles of the markets and countries in ensuring food security.</p>
</abstract>

In recent decades, Fuzzy Time Series (FTS) has become a competitive, sometimes complementary, approach to classical time series methods such as that of Box-Jenkins. This study has two different purposes: a theoretical purpose, presenting an overview of the fuzzy logic and fuzzy time series models, and a practical purpose, which is to estimate and forecast monthly international coffee prices during the period 2000-2022. Analysing and forecasting the dynamics of coffee prices is of great interest to producers, consumers, and other market actors in managing and making rational decisions. The findings showed that international coffee prices exhibited significant fluctuations, with large increases and decreases influenced mainly by the level of top-ranked producers. The forecasted results revealed that a decrease in prices during the next six months (Jan 2023 to June 2023) is expected. Based on the results, it is also clear that the FTS models are more flexible and can be applied in forecasting time-series variables. At the same time, volatility and, sometimes, the unexpected swingsin coffee prices continue to draw more criticism and raise different issues regarding the roles of the markets and countries in ensuring food security.

Forecasting Models Based on Fuzzy Logic: An Application on International Coffee Prices

Econometrics

This work is licensed under the Creative Commons Attribution-ShareAlike 4.0 International License.

In recent decades, Fuzzy Time Series (FTS) has become a competitive, sometimes complementary, approach to classical time series methods such as that of...

Forecasting Models Based on Fuzzy Logic: An Application on International Coffee Prices

Publié en ligne: 15 févr. 2023

Pages: 1 - 16

DOI: https://doi.org/10.15611/eada.2022.4.01

Mots clés
fuzzy logic, time series, forecasting, coffee prices, FTS models

© 2022 Chellai Fatih, published by Sciendo

This work is licensed under the Creative Commons Attribution-ShareAlike 4.0 International License.

Forecasting Models Based on Fuzzy Logic: An Application on International Coffee Prices

Publié en ligne: 15 févr. 2023

Pages: 1 - 16

DOI: https://doi.org/10.15611/eada.2022.4.01

Mots clésfuzzy logic, time series, forecasting, coffee prices, FTS models

© 2022 Chellai Fatih, published by Sciendo

This work is licensed under the Creative Commons Attribution-ShareAlike 4.0 International License.

Mots clés
fuzzy logic, time series, forecasting, coffee prices, FTS models