6533b7dbfe1ef96bd127003f
RESEARCH PRODUCT
Approaching sales forecasting using recurrent neural networks and transformers
Iván Vallés-pérezEmilio Soria-olivasMarcelino Martínez-soberAntonio J. Serrano-lópezJuan Gómez-sanchísFernando Mateosubject
FOS: Computer and information sciencesComputer Science - Machine LearningComputer Science - Artificial IntelligenceGeneral Engineeringdeep learningUNESCO::CIENCIAS TECNOLÓGICASStatistics - ApplicationsComputer Science ApplicationsMachine Learning (cs.LG)Artificial Intelligence (cs.AI)Artificial Intelligencesequence to sequencetransformerApplications (stat.AP)sales forecastsupply chaindescription
Accurate and fast demand forecast is one of the hot topics in supply chain for enabling the precise execution of the corresponding downstream processes (inbound and outbound planning, inventory placement, network planning, etc). We develop three alternatives to tackle the problem of forecasting the customer sales at day/store/item level using deep learning techniques and the Corporaci\'on Favorita data set, published as part of a Kaggle competition. Our empirical results show how good performance can be achieved by using a simple sequence to sequence architecture with minimal data preprocessing effort. Additionally, we describe a training trick for making the model more time independent and hence improving generalization over time. The proposed solution achieves a RMSLE of around 0.54, which is competitive with other more specific solutions to the problem proposed in the Kaggle competition.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2022-01-01 |