딥러닝 기법을 활용한 양식산 조피볼락 산지가격 예측 연구 －LSTM(Long-short Term Memory)과 GRU(Gated Recurrent Units) 모델을 중심으로－

Abstract

This study is aimed to forecast the producer price of aquaculture seafood using LSTM(Long-short Term Memory) and GRU(Gated Recurrent Units) models, a type of deep learning model. Since the producer price is directly related to aquacultural farm’s profitability, accurate forecasting of the producer price is essential to establish an effective production and management plan for aquaculture and stabilize supply and demand of farmed seafood. Korean Rockfish(Sebastes schlegelii) is a commercially important fish species that ranks second in domestic farmed fish production and is the main breed of fish farms in Tongyeong region. As the volatility of the producer price of Korean Rockfish has recently intensified, the importance of forecasting the producer price is increasing. In the analysis, total 19 variables were used, including producer prices in other regions, production-related variables, consumption-related variables, alternative farmed fish variables, water temperature, and COVID-19 dummy variables. Total 189 monthly data from October 2006 to June 2022 were used. In this study, the producer price of farmed Korean Rockfish was forecasted by LSTM and GRU models, a type of RNN(Recurrent Neural Network) model specialized for time series forecasting and the accuracy of models was compared with MAPE(Mean Absolute Percent Error). Results showed that MAPEs of LSTM and GRU were 4.66% and 6.27%, respectively. In addition, when comparing the accuracy by the number of independent variables, it was found that the accuracy of the multivariate LSTM model was better than that of the univariate LSTM model.