What question did this study set out to answer?

The aim is to improve retail sales forecasting accuracy using a meta-learning enhanced LSTM model that can adapt to various conditions.

May 27, 2026Scientific ReportsOpen Access

Meta-LLSTM: meta-learning enhanced learnable LSTM for retail sales forecasting

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates enhanced retail sales forecasting using Meta-LLSTM, indicating improved accuracy over existing models.

The aim is to improve retail sales forecasting accuracy using a meta-learning enhanced LSTM model that can adapt to various conditions.
Developed the Meta-Learning Enhanced Learnable Long Short-Term Memory network (Meta-LLSTM) for sales forecasting.
Utilized RFMD analysis, K-means customer segmentation, and Adaptive Inventory Correction (AIC) for improved forecasting.
Evaluated model performance using metrics like RMSE, MAE, and MAPE against state-of-the-art classifiers.
Achieved an RMSE of 1.003, outperforming AE, CNN, GRU, and RNN classifiers.
The Meta-LLSTM's RMSE is 16.97% lower than that of the RNN, establishing its superiority in forecasting.
Improvements in forecasting accuracy indicate potential for better inventory and business strategy management.

Suresh et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

May 27, 2026Scientific ReportsOpen Access

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates enhanced retail sales forecasting using Meta-LLSTM, indicating improved accuracy over existing models.

The aim is to improve retail sales forecasting accuracy using a meta-learning enhanced LSTM model that can adapt to various conditions.
Developed the Meta-Learning Enhanced Learnable Long Short-Term Memory network (Meta-LLSTM) for sales forecasting.
Utilized RFMD analysis, K-means customer segmentation, and Adaptive Inventory Correction (AIC) for improved forecasting.
Evaluated model performance using metrics like RMSE, MAE, and MAPE against state-of-the-art classifiers.
Achieved an RMSE of 1.003, outperforming AE, CNN, GRU, and RNN classifiers.
The Meta-LLSTM's RMSE is 16.97% lower than that of the RNN, establishing its superiority in forecasting.
Improvements in forecasting accuracy indicate potential for better inventory and business strategy management.

Suresh et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark