YASSINE SENHAJI

Mr. YASSINE SENHAJI

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 June 2025 in Mathematics
Verified
Journal Article
Open access
PDF file
MEMustapha Ez-zaiym
Mustapha Ez-zaiym
YSYASSINE SENHAJI
YASSINE SENHAJI
MRMeriem Rachid
Meriem Rachid
EKEl Moutaouakil Karim
El Moutaouakil Karim
Vasile PaladeVasile Palade
Vasile Palade
This study investigates the theoretical foundations and practical advantages of fractional-order optimization in computational machine learning, with a particular focus on stock price forecasting using long short-term memory (LSTM) networks. We extend several widely used optimization algorithms—including Adam, RMSprop, SGD, Adadelta, FTRL, Adamax, and Adagrad—by incorporating fractional derivatives into their update rules. This novel approach leverages the memory-retentive properties of fractional calculus to improve convergence behavior and model efficiency. Our experimental analysis evaluates the performance of fractional-order optimizers on LSTM networks tasked with forecasting stock prices for major companies such as AAPL, MSFT, GOOGL, AMZN, META, NVDA, JPM, V, and UNH. Considering four metrics (Sharpe ratio, directional accuracy, cumulative return, and MSE), the results show that fractional orders can significantly enhance prediction accuracy for moderately volatile stocks, especially among lower-cap assets. However, for highly volatile stocks, performance tends to degrade with higher fractional orders, leading to erratic and inconsistent forecasts. In addition, fractional optimizers with short-memory truncation offer a favorable trade-off between computational efficiency and modeling accuracy in medium-frequency financial applications. Their enhanced capacity to capture long-range dependencies and robust performance in noisy environments further justify their adoption in such contexts. These results suggest that fractional-order optimization holds significant promise for improving financial forecasting models—provided that the fractional parameters are carefully tuned to balance memory effects with system stability.

1 July 2026 in RAIRO - Operations Research
Verified
Journal Article
Open access
YSYASSINE SENHAJI
YASSINE SENHAJI
EKEl Moutaouakil Karim
El Moutaouakil Karim
Colorectal cancer is one of the leading causes of cancer death, and studies require advanced analysis methods to understand it more. This article proposes an automated end-to-end pipeline designed to systematically evaluate several established Knowledge Graph Embedding (KGE) models, such as TransE, RESCAL, ComplEx, and ConvE, to extend colorectal cancer research. Unlike most previous studies on isolated models, our approach examines their combined performance in biomedical applications in a comprehensive manner. In addition, we will introduce an enhanced triple classification framework, mentioning specifically the Threshold Calculation for Classification technique.Our pipeline performs efficiently on a medium-sized knowledge graph (28k triples), though scalability to larger-scale datasets remains to be tested in future work. The results indicate that ComplEx achieved the highest performance metrics for biomedical knowledge discovery among the models tested.

3 July 2026 in AppliedMath
Verified
Journal Article
Open access
PDF file
ANAhmed Nuino
Ahmed Nuino
OBOmar Bahou
Omar Bahou
YSYASSINE SENHAJI
YASSINE SENHAJI
MEMustapha Ez-zaiym
Mustapha Ez-zaiym
EKEl Moutaouakil Karim
El Moutaouakil Karim
Savin TreantaSavin Treanta
Savin Treanta
Complex-valued knowledge graph embedding (KGE) models like ComplEx effectively capture asymmetric relations but are fundamentally constrained by integer-order transformations. This restriction limits their ability to model multi-scale interactions, hierarchical correlations, and non-local semantic dependencies inherent in heterogeneous graphs. To address these limitations, this paper introduces FracComplEx, a novel fractional-order extension that embeds fractional calculus into the complex latent space. By leveraging fractional operators, the framework introduces non-local dynamics and memory-aware mechanisms to continuously generalize standard linear transformations. The core architecture employs a fractional-order parameter α as a controllable scaling mechanism that balances local relational details with global topology, optimizing representation smoothness and flexibility. We provide rigorous theoretical findings demonstrating that fractional transformations enhance the embedding’s expressive capacity, spectral characteristics, and perturbation robustness beyond conventional integer-order benchmarks. Extensive experiments on FB15k-237, WN18RR, and CoDEx-M establish the empirical superiority of FracComplEx, yielding significant improvements in Mean Reciprocal Rank (MRR) and Hits@K metrics over classical baselines, particularly under severe structural data sparsity.