Building CetaResearch. Data analysis for policy, research, and startups.
backtests
Germany produced the smallest excess return of the four European markets in our 13-exchange study: 9.41% CAGR, +4.22% vs DAX. What it does deliver is a beta of 0.693, a 59.70% down capture and a shallower drawdown than the index. Technology held a top-2 slot in 35 of 104 quarters.
analyst ratings
We tested analyst upgrade clusters on 14 exchanges with next-day MOC execution. No immediate alpha, and the US 3-week window fails the direction test: downgrades beat the index too. What survives is US T+63. UK, Canada and Taiwan look strong but have too few downgrades to test.
P/E mean reversion
A sector-relative P/E screen on 25 years of XETRA-listed data returned 10.37% annually vs 4.45% for the DAX, the best Sharpe of 13 exchanges (0.413) and 43% down-capture. The universe is companies listed on XETRA, not German-domiciled ones, and that distinction changes the answer.
momentum
We tested the 52-week high proximity strategy on Thai stocks (SET) from 2000 to 2025. 10.47% CAGR, +6.71% vs SET Index, 49.3% down capture. In 2022, the strategy returned +5.6% while the SET rose just 0.5%.
GARP
We ran the GARP strategy on 17 stock exchanges from 2000 to 2025. Against local benchmarks, Germany (+4.40% vs DAX) and Hong Kong (+4.36% vs Hang Seng) clearly outperform. India barely beats the Sensex (+0.63%). Here's the full comparison.
backtests
Canada ranked second for excess return in our 13-exchange sector momentum study: +11.51% annually over 26 years vs the TSX Composite, driven by Basic Materials (38q) and Energy (37q) in the top two. It also posts the study's highest Sharpe ratio at 0.591. C$10K grew to C$562,372.
P/E mean reversion
We tested a sector-relative P/E mean reversion screen on 25 years of UK stock data. Stocks trading at a 40%+ discount to sector peers, filtered for quality, returned 10.87% CAGR vs 0.86% for the FTSE 100. The highest local excess return of any exchange tested: 10.00%. Win rate: 80%.
ai
Three ways to use your existing AI subscription with Ceta Research: generate SQL queries, fetch data via API, or run and customize 85+ backtesting strategies.
ai
Run and customize 85+ trading strategy backtests with your AI. Clone the open-source framework, modify strategies with natural language, or run on cloud compute via the Projects API.
ai
Use your AI to generate Python code that queries the Ceta Research API. Give it the endpoint docs, ask a question, run the code locally.
value investing
We screened JSE-listed stocks for low price-to-sales ratios with qualifying margins and profitability, then backtested the resulting portfolio from 2000 to 2025. After data-quality fixes (removing price-oscillation artifacts and capping extreme single-period returns from bad adjusted-close data), the strategy returned 6.24% annually vs 8.02% for the S&
backtests
We tested 52-week low stocks filtered by Piotroski F-score on US markets from 2002 to 2025. The strategy returned 6.64% annually vs 9.67% for the S&P 500. Down-capture of 112.6% explains the gap.