3260 papers • 126 benchmarks • 313 datasets
This task has no description! Would you like to contribute one?
(Image credit: Papersgraph)
These leaderboards are used to track progress in short-observation-new-product-sales-forecasting-10
Use these libraries to find short-observation-new-product-sales-forecasting-10 models and implementations
No subtasks available.
Several novel attention-based multi-modal encoder-decoder models are proposed and empirically evaluated to forecast the sales for a new product purely based on product images, any available product attributes and also external factors like holidays, events, weather, and discount.
The main message that is delivered is that the use of image data with deep networks boosts performances obtained when using the time series in long-term forecasting scenarios, ameliorating the WAPE by 8.2% and the MAE by 7.7%.
Adding a benchmark result helps the community track progress.