What question did this study set out to answer?

The research aims to forecast multidimensional liquidity in the Moroccan Stock Market using various deep learning architectures.

February 5, 2026Open Access

Liquidity’s Many Faces, Deep Learning’s Many Minds: Hybrid and Baseline Deep Networks for Multidimensional Liquidity Forecasting in the Moroccan Stock Market

Key Points

The research aims to forecast multidimensional liquidity in the Moroccan Stock Market using various deep learning architectures.
Utilized deep learning architectures including LSTM, CNN, and a hybrid attention model
Applied fixed look-back windows of 5 and 21 days for predictions
Employed out-of-sample protocols with metrics like MAE, MSE, and RMSE for evaluation
Conducted Diebold–Mariano tests for model comparison
The attention hybrid model achieved the highest accuracy compared to other models
The 21-day look-back window provided the most significant performance improvement
Findings support enhanced trading decisions and earlier alerts for liquidity risk

Abstract

This paper investigates multidimensional liquidity forecasting in the Moroccan Stock Market—an order-driven, less dynamic frontier venue—using deep-learning architectures (LSTM, CNN, LSTM–CNN, CNN–LSTM, and an attention-augmented hybrid). With fixed look-back windows (5 and 21 days) and a consistent out-of-sample protocol (scalers fit on Train; one-step forecasts), we evaluate MAE, MSE, RMSE, MASE, and R², and compare models via Diebold–Mariano tests based on MSE and QLIKE. The attention hybrid model delivers the best overall accuracy, and the 21-day window provides the most robust gains. These results support better trading decisions, earlier liquidity-risk aletrs, and supervisory calibration in pre-emerging markets.

Read Full Paperexternally

Mark Helpful

Bookmark

Relay

View Full Paper