In the age of information overload, customers are overwhelmed with the number of products available for sale. Search engines try to overcome this issue by filtering relevant items to the users’ queries. Traditional search engines rely on the exact match of terms in the query and product meta-data. Recently, deep learning-based approaches grabbed more attention by outperforming traditional methods in many circumstances. In this work, we involve the power of embeddings to solve the challenging task of optimizing product search engines in e-commerce. This work proposes an e-commerce product search engine based on a similarity metric that works on top of query and product embeddings. Two pre-trained word embedding models were tested, the first representing a category of models that generate fixed embeddings and a second representing a newer category of models that generate context-aware embeddings. Furthermore, a re-ranking step was performed by incorporating a list of quality indicators that reflects the utility of the product to the customer as inputs to well-known ranking methods. To prove the reliability of the approach, the Amazon reviews dataset was used for experimentation. The results demonstrated the effectiveness of context-aware embeddings in retrieving relevant products and the quality indicators in ranking high-quality products.

Texture is a fundamental characteristic of many types of images, especially those with significant rotation, scale illumination, and viewpoint change. Texture image classification is one of the challenging problems that have various applications such as remote sensing, material recognition, and computer-aided medical diagnosis, etc. Various Computer vision techniques have been used. More recently, Deep learning architectures demonstrated impressive results. This paper aims to investigate combining two feature extraction methods: Handcrafted-based and CNN-based in a two-stream neural network architecture. We believe that Statistical features could enhance the performance of the CNN architecture, especially in the case of small datasets. To test our approach we used two challenging datasets, the Describable Textures Dataset (DTD) and Flicker Material Database (FMD). Results showed that our two-stream neural network which has an image as a first stream and a statistical feature vector as a second stream achieve better results than a Convolutional neural network achieved with just the RGB image as input. The Xception network [9] combined with SIFT-FV demonstrated an accuracy superiority for both datasets.

In recent years Natural language processing is one of the most active areas of research especially with the emergence of deep learning algorithms. More attention has been given to Latin descendent languages e.g English, French, and Spanish given the availability of high-quality datasets and compute resources. In this paper, we present a moroccan News Articles Corpus collected from four of the major moroccan news websites. The corpus contains more than 418k news articles corresponding to 19 different categories, thus considered to be one of the largest Arabic news articles corpora. A description of the collection and processing steps were presented and exploration analysis was performed. To prove the utility of the dataset. An evaluation step was conducted in the context of text classification using four different Machine Learning baselines: Random Forest (RF), Multinomial Naive Bayes (MNB), Support Vector Machine (SVC), and Gradient Boosting (GradBoost) Classifiers. The experimental results are presented in terms of accuracy, F1-score, and confusion matrix.

This study examines the transformative impact of artificial intelligence (AI) on tax auditing through a PRISMA-compliant systematic literature review and textometric analysis. By analyzing literature published between 2015 and 2025 using IRAMUTEQ, we uncover a nuanced perspective on AI’s evolving role. The results reveal a scholarly discourse highlighting significant advances in tax fraud prediction and financial risk assessment via deep learning and neural networks. This technological shift extends beyond operational efficiency to broader macroeconomic governance, simultaneously raising challenges regarding taxpayer equity and trust. Our findings underscore a transition in academic focus from purely technical applications to the ethical and psychological dimensions of AI. Finally, we propose the AI-Driven Tax Audit Model (ATAM), a framework designed to guide tax authorities in integrating these technologies by balancing algorithmic efficiency and financial risk mitigation with vertical equity and explainability.