Reproduce “Global Merger-Arbitrage Forecasting with Language Models” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Hinal Jajal, Michal Mucha, Charles Sweat, Chris Pulman, Charlie Flanagan, Peter Anderson
The authors build a system to forecast announced M&A outcomes. Specialist agents assemble research from timestamped sources; a fine-tuned language model converts it into probabilities and reports, using hindsight-guided post-mortems without future information at forecast time. On 404 deals across 42 countries, it scores 0.151 versus XGBoost’s 0.186 on binary positive-versus-negative outcomes, in a backtest, not evidence of trading profits.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.