Mitigating Overproduction of Perishable Commodities with Time Series Forecasting
Open AccessPerishable commodities make up a significant part of our global commerce, from the food we eat to the flowers we gift. Compared to conventional supply chains, the logistical operations involved in maintaining a cold chain for such perishables are appreciably more complex and costlier to execute, thus it’s crucial for organizations to correctly adjudge the dynamics of market supply and demand, in order to avoid exposure to significant financial loss. This research examines the supply side of the marketplace and considers how growers can avoid or mitigate the effects of overproduction of perishable commodities by applying an empirical approach to supply chain optimization. Using historical yield data of five commercial cut-flower varieties and local environmental predictors (temperature, humidity and cloud cover), the performance of two well-known time-series forecasting methods – ARIMA and ANN – was evaluated to determine the most appropriate method to use. A Yield Prediction software tool was developed to simplify and automate the prediction process for biosystems engineers and operations managers.
- All rights reserved
Notice to Authors
If you are the author of this work and you have any questions about the information on this page, please use the Contact form to get in touch with us.