Hedge funds (HF) are actively managed investment vehicles employing diverse and often complex strategies.Accurate returns forecasting is essential for optimizing their performance and managing risk.This paper investigates the application of nonlinear dimensionality reduction (DR) methods in forecasting HF strategy performance, building upon prior work in financial time series analysis.We evaluate the effectiveness of Kernel Principal Component Analysis (KPCA), t-Distributed Stochastic Neighbor Embedding (t-SNE), Uniform Manifold Approximation and Projection (UMAP), and autoencoders on predictive performance of machine learning models.The extracted features are fed into several forecasting models, Support Vector Machine (SVM) with linear and nonlinear kernels, Neural Network (NN), and Extreme Gradient Boosting (XGB), to predict returns of five diverse HF investment strategies: Commodity Trading Advisors, Equity Long Short, Equity Market Neutral, Fixed Income Arbitrage, and Global Macro.The results demonstrate that nonlinear DR methods, particularly autoencoders, and KPCA combined with NN, significantly outperform other techniques.Our findings highlight the value of nonlinear transformations in enhancing predictive accuracy for HF returns time series.

Predictive analytics aims to empower finance professionals to make data-driven decisions, anticipate customer behavior, and navigate the complexities of the financial landscape.One of the tasks in this domain is the prediction of stock trend movements.The goal of the FedCSIS 2024 Data Science Challenge was to build such predictive models based on the financial fundamental data.Such models could have a vital role in algorithmic or manual trading, providing trading signals for making decisions about the time and direction of stock trades.We describe the prepared dataset and challenge task.We also summarize the challenge outcomes and provide insights about the most successful machine learning techniques applied.