FinBench: A Benchmarking Framework for Stock Market Prediction and Portfolio Allocation

Abstract

Research on stock market prediction relies on public datasets to develop and compare learning-based models. However, existing datasets are often limited to price-based information, cover a restricted set of assets or time periods, or provide only a subset of the heterogeneous signals required by modern prediction approaches. Moreover, differences in data preprocessing, task formulation, and evaluation protocols make experimental results difficult to reproduce and hard to compare across studies. To address these challenges, we present FinBench, a benchmarking framework designed to support reproducible evaluation of stock market prediction models using heterogeneous financial data. FinBench integrates historical prices, inter-company relations, macroeconomic indicators, and financial news within a unified data construction pipeline, and standardizes feature extraction and evaluation across classification, regression, and ranking tasks. Model outputs are evaluated both at the task prediction level and through portfolio-based strategies under consistent experimental settings. Using FinBench, we benchmark a range of existing models on European and US equity markets, analyzing their behavior across different prediction tasks, portfolio constructions, and investment universes with diverse liquidity and structural characteristics. FinBench provides a practical reference for systematic and reproducible comparison of stock market prediction methods.