Approaching sales forecasting using recurrent neural networks and transformers
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.
Code (1)
Similar Papers 제목 키워드 기반
Demand Forecasting in Supply Chain Management for Rossmann Stores Using Weather Enhanced Deep Learning Model
Demand forecasting is one of the essential aspects of supply chain management, as it is linked with the financial performance of the organization. In the retail industry, it is essential to have more accurate forecasts t…
Demand ForecastingManagementTime SeriesAn XGBoost-Based Forecasting Framework for Product Cannibalization
Two major challenges in demand forecasting are product cannibalization and long term forecasting. Product cannibalization is a phenomenon in which high demand of some products leads to reduction in sales of other product…
Demand ForecastingImproving Sales Forecasting Accuracy: A Tensor Factorization Approach with Demand Awareness
Due to accessible big data collections from consumers, products, and stores, advanced sales forecasting capabilities have drawn great attention from many companies especially in the retail business because of its importa…
Decision MakingManagementMarketingRecommendation SystemsTiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning
In-context learning, the ability of large language models to perform tasks using only examples provided in the prompt, has recently been adapted for time series forecasting. This paradigm enables zero-shot prediction, wh…
In-Context LearningState Space ModelsTime SeriesTime Series ForecastingETSformer: Exponential Smoothing Transformers for Time-series Forecasting
Transformers have been actively studied for time-series forecasting in recent years. While often showing promising results in various scenarios, traditional Transformers are not designed to fully exploit the characterist…
Time SeriesTime Series AnalysisTime Series Forecasting