Pregled bibliografske jedinice broj: 1186343
Prediction of Store Demands by Decision Trees and Recurrent Neural Networks Ensemble with Transfer Learning
Prediction of Store Demands by Decision Trees and Recurrent Neural Networks Ensemble with Transfer Learning // Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART / Rocha, Ana Paula ; Steels, Luc ; van den Herik, Jaap (ur.).
Beč, Austrija: SCITEPRESS, 2022. str. 218-225 doi:10.5220/0010802500003116 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 1186343 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Prediction of Store Demands by Decision Trees and
Recurrent Neural Networks Ensemble with Transfer
Learning
Autori
Perić, Nikica ; Munitić, Naomi-Frida ; Bašljan, Ivana ; Lešić, Vinko
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
/ Rocha, Ana Paula ; Steels, Luc ; van den Herik, Jaap - : SCITEPRESS, 2022, 218-225
ISBN
978-989-758-547-0
Skup
14th International Conference on Agents and Artificial Intelligence (ICAART)
Mjesto i datum
Beč, Austrija, 03.02.2022. - 05.02.2022
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
multi period VRP ; prediction of delivery capacities ; gradient boosting decision trees ; recurrent neural networks ; transfer learning
Sažetak
Simple vehicle routing problem (VRP) algorithms today achieve near-optimal solution and solve problems with a large number of nodes. Recently, these algorithms are upgraded with additional constraints to respect an increasing number of real-world conditions and, further on, adding a predictive character to the optimization. A distinctive contribution lies in taking into account the predictions of orders that are yet to occur. Such problems fall under time series approaches that are most often obtained using statistical methods or historical data heuristics. Machine learning methods have proven to be superior to statistical methods in most of the literature. In this paper, machine learning techniques for predicting the mass of total daily orders for individual stores are further elaborated and tested on historical data of a local retail company. Among the tested methods are Gradient Boosting Decision Tree methods (XGBoost and LightGBM) and methods of Recurrent Neural Networks (LSTM, G RU and their variations using transfer learning). Finally, an ensemble of these methods is performed, which provides the highest prediction accuracy. The final models use the information on historical order quantities and time-related slack variables.
Izvorni jezik
Engleski
Znanstvena područja
Elektrotehnika, Računarstvo, Informacijske i komunikacijske znanosti
POVEZANOST RADA
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb
