Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Younes Lahrichi has a total of 9 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Firm Financial Performance and Macroeconomic Aggregates Under a Progressive Floating Exchange Rate: Evidence from an Agent-Based Model of Morocco

    by Moutaib Nouhaila, Lahrichi Younès

    This paper analyzes Morocco's progressive transition toward a more flexible exchange rate regime using an agent-based modeling (ABM) framework. Nine simulations with three levels of flexibility (±20%, ±50%, and full float), capture the multi-layered interaction between exchange-rate fluctuations, firm-level behaviours, and macroeconomic dynamics. The results uncover that while greater flexibility can boost competitiveness, fiscal space, and export responsiveness, it also accentuates firm-level vulnerabilities, especially for import-dependent sectors. Exporters experience double exposure to both cost and financing volatility, while importers face liquidity constraints that grow under full float. Sectorial layers highlight the structural heterogeneity of Morocco's economy, and macroeconomic findings expose that only intermediate flexibility (±50%) could balance stability and adaptability. The study highlights the importance of gradual reform sequencing, developed hedging instruments, and stronger domestic value chains to guarantee that monetary flexibility translates into sustainable and inclusive growth.

  • Open Access

    Stock market liquidity: hybrid deep learning approaches for prediction

    by Mariam Ait Al, Said Achchab, Younes Lahrichi

    Predicting stock market liquidity especially in emerging or frontier financial markets, such as the Casablanca stock exchange (CSE), presents significant challenges given the relative narrowness and volatility of these markets. In this paper, we conduct a comprehensive study to address the predictions accuracy gaps between five main deep learning models: convolutional neural network (CNN), long short-term memory (LSTM), bidirectional LSTM (BiLSTM), and two hybrid architectures, CNN-LSTM and CNN-BiLSTM. The proposed methodology focused on training and testing these models on historical data from the CSE, with precision on capturing both spatial and temporal market dynamics. The models were fine-tuned using key hyperparameters and validated on 20% of the dataset to ensure reliable results. The evaluation of performance was conducted using error metrics such as mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE). The study demonstrates that the hybrid CNN-biLSTM model consistently outperformed all standalone and other hybrid models in predictive accuracy. This underscores the considerable promise of hybrid deep learning architectures for addressing the unique challenges of predicting stock market liquidity in volatile and emerging financial markets.

  • Open Access

    AutoML Driven LSTM and Stock Price Prediction Effectiveness: A New Frontier for Volatile Stock Markets.

    by Mariam Ait AL, Said Achchab, Younes Lahrichi

    Conventional prediction methods, whether derived from deep learning or statistical techniques, typically demand significant manual intervention, making full process automation challenging. This study investigates the comparative robustness of traditional Long Short-Term Memory (LSTM) models and automated machine learning (AutoML) techniques, specifically TPOT, in predicting stock market behavior. By conducting experiments on the Moroccan stock market, the results demonstrate that AutoML approaches not only enhance prediction accuracy but also simplify the modeling process, making advanced prediction techniques more accessible and effective in dynamic financial markets.

  • Open Access

    Predicting Stock Prices Based on Sentiment Analysis and Machine Learning Techniques: A literature Review

    by Abdelkhaleq El Haddad, Said Achchab, Younès Lahrichi

    This paper aims to develop a novel approach for predicting stock prices by leveraging sentiment analysis and deep learning techniques within a stochastic context. This approach aims to incorporate the impact of investor and market sentiment on stock prices, considering the inherent uncertainty and randomness in the financial markets. In today's fast-paced and unpredictable financial markets, the ability to accurately predict stock prices is a highly sought-after skill. Traders and investors are constantly seeking innovative approaches to gain an edge and make informed decisions. One such approach that has gained significant attention is the use of sentiment analysis combined with machine learning techniques. By analyzing social media sentiment, news articles, and other relevant data, researchers and analysts can uncover valuable insights into market trends and investor sentiment. Sentiment analysis involves the use of natural language processing and machine learning algorithms to determine the emotional tone of a piece of text.

  • Open Access

    Socially Responsible Portfolio Selection: An Interactive Intuitionistic Fuzzy Approach

    by Yahya Hanine, Youssef Lamrani Alaoui, Mohamed Tkiouat, Younes Lahrichi

    In this study, we address the topic of sustainable and responsible portfolio investments (SRI). The selection of such portfolios is based, in addition to traditional financial variables, on environmental, social, and governance (ESG) criteria. The interest of our approach resides in allowing socially responsible (SR) portfolio investors to select their optimal portfolios by considering their individual preferences for each objective and simultaneous definition of the degrees of acceptance and rejection. In particular, we consider socially responsible portfolio selection as an optimization problem with multiple objectives before applying interactive intuitionistic fuzzy method to solve the portfolio optimization. The robustness of our approach is tested through an empirical study on the top 10 Stocks for ESG values worldwide.