01
Multi-strategy
Generally, a single strategy is hard to outperform the market consistently over a long period of time, so we use a multi-strategy approach to cover different market conditions.
Building on top of the foundation.
AlphaStone is a personal quantitative research project. It began with a goal of developing systematic strategies that could beat the market. The current question is whether AI can assist quantitative trading research, with approved strategies used for live trading.
Past AI trading experiments asked whether a model can look at a market and make a right trading decisions. AlphaStone asks a different question: can AI do the work of a quantitative researcher and help developing successful algorithmic strategies that remain consistent and testable?
AlphaStone began in 2021 as a personal attempt to build systematic strategies that could beat the market. After years of building the data and backtest infrastructure, test-time compute and reasoning-model breakthroughs made AI capable of doing meaningful generative research inside that framework.
Recent advances in AI capabilities have changed what software can do. AlphaStone is testing whether those capabilities can aid quantitative trading research by proposing and testing candidate ideas within the framework, while human review decides what advances.
Strategy philosophy
02
Absolute alpha
We aim for absolute alpha. The goal is to outperform the market, not to be a passive investment.
03
Consistency in profits
We like having strategies that perform consistently across market conditions. We put extra care into ensuring our systems perform well consistently with low drawdown.
The work so far.
2021
FoundationAlphaStone began as a personal project to develop a systematic approach that could beat the market.
- June 3AlphaStone Technologies SP was founded by Thomas Lee.
2022
First live trading systemThe project moved from research into live testing. Model Ares and R&D framework V1 exposed the practical problems that do not appear in a backtest.
- January 7Development of Model Ares began.
- August 20R&D framework V1 was introduced and Model Ares entered live testing.
2023
Framework rebuiltNew model generations and a rebuilt R&D framework expanded the research system, while failed experiments narrowed what was worth pursuing.
- April 13Development began on Models 1 through 4.
- June 18R&D framework V2 began development from scratch.
- August 3Development of Model Ares was paused as research moved toward newer model generations.
- December 16Development of Model 5 began.
2024
Flagship Model 5 lineupModels 4 and 5 reached major development milestones. Model 5.2 became the working Model 5 line, and R&D framework V3 strengthened the foundation underneath it.
- March 29Major development of Model 4 was completed.
- July 25Major development of Model 5 was completed.
- July 26Development of Model 5.2 began as the next stage of the Model 5 research line.
- August 25Major development of Model 5.2 was completed. From this point forward, the name Model 5 refers to Model 5.2.
- September 4Major development of R&D framework V3 was completed.
2025
Improved framework V4R&D framework V4 and Models 5.3 through 5.4 were developed, followed by the start of Model 5.5.
- April 15Development began on R&D framework V4 and Models 5.3 through 5.4.
- July 20Development of R&D framework V4 and Models 5.3 through 5.4 was completed. Work then began on Model 5.5.
2026
AI-assisted researchModel 5.5 was completed, a Model 5.6 attempt failed to produce a version worth advancing, and the project returned to improving Model 5.5 as AI became useful for research.
- April 4Major development of Model 5.5 was completed, and development of Model 5.6 began.
- July 26The Model 5.6 attempt did not produce a result worth advancing.
- July 27Research returned to improving Model 5.5. This became a turning point as AI became materially useful for proposing, testing, and iterating on research ideas inside the existing framework.