London — KCL Computer Science
I build systems that read academic finance papers at scale and test whether their trading signals hold up in real data.
I am a Computer Science student at King's College London. For the past few months I have been building a research intelligence pipeline that systematically reads academic finance papers, extracts trading signals, and tests whether they survive at scale.
Most papers do not replicate without any changes. The gap between what a paper claims and what you find when you actually run it is the interesting part. That is what the briefs document.
The pipeline processes around 200 new arXiv q-fin papers per month at roughly $0.20 per paper. All market data is free which I used from Yahoo Finance, SEC EDGAR, Kenneth French's data library, FRED. No proprietary data sources since I don't have commercial access to ones such as Bloomberg though even with these sources, it is quite impressive and can be modified afterwards to include Bloomberg or WRDS later on, this brief acts like a MVP.