I am an independent researcher working on systematic-trading methodology, walk-forward evaluation, and the statistical structure of strategy populations. The work here is published under Daru Finance, a sole-author imprint, not a fund and not a sales platform.
Background
I am a candidate in Economic Sciences at UNIP. Most of what I know about quantitative finance came from outside the curriculum: years of building backtesters, running thousands of walk-forward experiments, and trying to falsify my own results harder than anyone else would.
In parallel, I work as a Quantitative Systems Consultant for a firm I cannot name (under NDA). The role is research-side: building filters, stress-testing strategy populations, evaluating signal robustness, and production-grade backtester engineering.
What this site is for
Daru Finance is where the public-facing portion of my research lives. The aim is simple:
- Publish empirical work with real receipts, code, data aggregates, reproducible figures.
- Resist the temptation to oversell. Most strategies don’t work; that finding is the work.
- Surface methods that survive real out-of-sample tests, and show the regimes where they fail.
Everything you see here is a one-person build: the twelve open-source models, the working paper and its reproducibility package, the long-form article and its interactive simulations, the figures and data pipeline, and the site itself, design and code. Independent doesn’t just mean unaffiliated; it means accountable for every line.
What you’ll find
The flagship article Edge is in the Process walks through my central empirical claim on a reproducible 12-market crypto corpus: across 533,638 strategies and 44 million walk-forward strategy-windows, the rank correlation between a strategy's profit factor in one window and the next is ρ ≈ 0.02, no individual strategy carries credible out-of-sample edge. But the same pool, ranked by past profit factor and held in its top few, closes 72% of the gap to break-even and turns profitable on 8 of 12 markets, net of costs. Selection on the population is the lever, and the rule is arithmetic on realised daily PnL.
The Research section hosts the SSRN paper landing and links to its reproducibility package. The Lab lists open implementations of the firm’s public models, random matrix theory, Higher Criticism + knockoffs, topological data analysis on strategy populations, tail-EVT cross-asset coupling.
Publications by Daniel Gatto
- Gatto, D. V. (2026). Predictive Value of Within-Strategy Permutation Tests for Forward Selection: Evidence from Over 6 Billion Strategy-Level Permutations Across Three Asset Classes. SSRN Working Paper 6636018. papers.ssrn.com
- Gatto, D. V. (2026). No Edge Without Information: An empirical study of tradeability in decentralized-exchange-only cryptocurrencies. SSRN Working Paper 6858778. papers.ssrn.com
- Gatto, D. V. (2026). The Reach of the World Cup Distraction Effect: Evidence from global trading venues. SSRN Working Paper 6955879. papers.ssrn.com
- Gatto, D. V. (2026). Adverse Selection Consumes the Touch: A true-aggressor-signed maker-P&L decomposition across 13 CME futures. SSRN Working Paper 7022599. papers.ssrn.com
- Gatto, D. V. (2026). Liquidation Without Loss: A Live-Book Decomposition of Aave v3. SSRN Working Paper 7157638. papers.ssrn.com
Posture
None of this is investment advice. I publish so that other researchers can replicate, poke holes, and improve the methods. If something here contradicts a result you have, the right response is to email me.