L’objectif de cette recherche était d’évaluer l’efficacité du paramètre de classification pour prédire suivre les tendances boursières. Les méthodes traditionnelles basées sur la prévision, qui ciblent l’immédiat pas de temps suivant, rencontrent souvent des défis dus à des données non stationnaires, compromettant le modèle précision et stabilité. En revanche, notre approche de classification prédit une évolution plus large du cours des actions avec des mouvements sur plusieurs pas de temps, visant à réduire la non-stationnarité des données. Notre ensemble de données, dérivé de diverses actions du NASDAQ-100 et éclairé par plusieurs indicateurs techniques, a utilisé un mélange d'experts composé d'un mécanisme de déclenchement souple et d'une architecture basée sur les transformateurs. Bien que la méthode principale de cette expérience ne se soit pas révélée être aussi réussie que nous l'avions espéré et vu initialement, la méthodologie avait la capacité de dépasser toutes les lignes de base en termes de performance dans certains cas à quelques époques, en démontrant le niveau le plus bas taux de fausses découvertes tout en ayant un taux de rappel acceptable qui n'est pas zéro. Compte tenu de ces résultats, notre approche encourage non seulement la poursuite des recherches dans cette direction, dans lesquelles un ajustement plus précis du modèle peut être mis en œuvre, mais offre également aux personnes qui investissent avec l'aide de l'apprenstissage automatique un outil différent pour prédire les tendances boursières, en utilisant un cadre de classification et un problème défini différemment de la norme. Il est toutefois important de noter que notre étude est basée sur les données du NASDAQ-100, ce qui limite notre l’applicabilité immédiate du modèle à d’autres marchés boursiers ou à des conditions économiques variables. Les recherches futures pourraient améliorer la performance en intégrant les fondamentaux des entreprises et effectuer une analyse du sentiment sur l'actualité liée aux actions, car notre travail actuel considère uniquement indicateurs techniques et caractéristiques numériques spécifiques aux actions. / The objective of this research was to evaluate the classification setting's efficacy in predicting stock market trends. Traditional forecasting-based methods, which target the immediate next time step, often encounter challenges due to non-stationary data, compromising model accuracy and stability. In contrast, our classification approach predicts broader stock price movements over multiple time steps, aiming to reduce data non-stationarity. Our dataset, derived from various NASDAQ-100 stocks and informed by multiple technical indicators, utilized a Mixture of Experts composed of a soft gating mechanism and a transformer-based architecture. Although the main method of this experiment did not prove to be as successful as we had hoped and seen initially, the methodology had the capability in surpassing all baselines in certain instances at a few epochs, demonstrating the lowest false discovery rate while still having an acceptable recall rate. Given these results, our approach not only encourages further research in this direction, in which further fine-tuning of the model can be implemented, but also offers traders a different tool for predicting stock market trends, using a classification setting and a differently defined problem. It's important to note, however, that our study is based on NASDAQ-100 data, limiting our model's immediate applicability to other stock markets or varying economic conditions. Future research could enhance performance by integrating company fundamentals and conducting sentiment analysis on stock-related news, as our current work solely considers technical indicators and stock-specific numerical features.

The aim of this study is to investigate the possibility to improve the investment model defined in Piotroski (2000) and the subsequent research carried out on this model. Our model builds further upon the original fundamental score put forth by Piotroski. This further developed model is tested in two different contexts; firstly, a weighted fundamental score is developed that is updated every year in order to control for any changes in the predictive ability of fundamental signals over time. Secondly, the behavior of this score is analyzed in context of recession and growth cycles of the macro economy. Our findings show that high book-to-market portfolio consist of poor performing firms, as shown by Fama and French (1995) and is thereby outperformed by both Piotroski's F_score and our own developed scores. The score based on a rolling window correlation is performing a little better then F_score, but the score based on correlations for prior Up and Down periods is not. The conclusions we draw from the results are that improvements have to be made, both to F_score and our own developments, to sort winners from loser to get an even more profitable zero-investment hedge strategy.

In this paper, market participants’ tendency to form investor herds in the stocks listed on Nasdaq First North Growth Market of Sweden is examined for the period from 2018 to 2023. The models used in this study to detect herd behavior in stocks consist of two measures of dispersions, Cross-Sectional Standard Deviation of returns (CSSD) and Cross-Sectional Absolute Deviation of returns (CSAD), which were proposed by Christie and Huang (1995) and Chang, et al. (2000), respectively. An equally-weighted index consisting of all of the stocks that have traded on this market during the period is created and a quantitative analysis is conducted. Evidence showed absence of herd behavior when using both models, as well as when accounting for robustness tests consisting of small, mid-and large cap portfolios. Our results also support the prediction of rational asset pricing models, which suggest that stock return dispersions around the market returns increase during periods of market stress.