Inventory Demand Prediction Based on Gated Recurrent Neural Network and Fuzzy Time Series

Xin Wu

2023

Abstract

Current situation of auto parts inventory management based on VMI management mode, parts suppliers do not fully consider the influence factors of the parts themselves and the vague external influence factors such as environment, region and economy. To improve the forecasting accuracy of auto parts inventory demand, this paper proposed a combined forecasting model based on advantage matrix combined with gated recurrent neural network and fuzzy time series model (CRU_FTS_AM). Firstly, the gated recurrent neural network (GRU) is used to learn the multi-dimensional features of auto parts. Then, fuzzy time series model (FTS) is used to learn fuzzy and uncertain external factors that affects parts inventory demand. Finally, obtains the optimal weight coefficient of a single model by introducing the advantage matrix, and forecasts parts inventory demand through the weighted combined model. Compared with four models used in previous studies on three real data sets, the experimental results show that the proposed model improves RMSE by about 18%.

Paper Citation

in Harvard Style

Wu X. (2023). Inventory Demand Prediction Based on Gated Recurrent Neural Network and Fuzzy Time Series. In Proceedings of the 2nd International Seminar on Artificial Intelligence, Networking and Information Technology - Volume 1: ANIT; ISBN 978-989-758-677-4, SciTePress, pages 172-177. DOI: 10.5220/0012276800003807

in Bibtex Style

@conference{anit23,
author={Xin Wu},
title={Inventory Demand Prediction Based on Gated Recurrent Neural Network and Fuzzy Time Series},
booktitle={Proceedings of the 2nd International Seminar on Artificial Intelligence, Networking and Information Technology - Volume 1: ANIT},
year={2023},
pages={172-177},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012276800003807},
isbn={978-989-758-677-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Seminar on Artificial Intelligence, Networking and Information Technology - Volume 1: ANIT
TI - Inventory Demand Prediction Based on Gated Recurrent Neural Network and Fuzzy Time Series
SN - 978-989-758-677-4
AU - Wu X.
PY - 2023
SP - 172
EP - 177
DO - 10.5220/0012276800003807
PB - SciTePress