A Garlic-Price-Prediction Approach Based on Combined LSTM and GARCH-Family Model

The frequent and sharp fluctuations in garlic prices seriously affect the sustainable development of industry. Accurate prediction can facilitate correct evaluation scientific decision making by practitioners, thereby avoiding market risks promoting healthy To improve accuracy prices, this paper proposes a garlic-price-prediction method based on combination long short-term memory (LSTM) multiple generalized autoregressive conditional heteroskedasticity (GARCH)-family models for nonstationary nonlinear characteristics garlic-price series. Firstly, we obtain volatility characteristic information such as aggregation series constructing GARCH-family models. Then, leverage LSTM model to learn complex relationships between series, predict price. We applied proposed real-world dataset. experimental results show that performance combined containing price is generally better than those separate incorporating GARCH PGARCH (LSTM-GP) had best predicting terms indexes, mean absolute error, root mean-square percentage error. LSTM-GARCH provides provide support prediction.