5.57 The Price Impact of Nothing: Rejected Orders Predict Returns
Hyperliquid post-only imbalance, from the last 100 submissions, forecasts the 10-second BTC perp mid after a rejection. The slope is a shared signal.
Independent research on systematic & quantitative trading
Aligrithm is an independent research publication on systematic trading, quantitative research, market microstructure, and adaptive systems. Long-form essays, code notebooks, and architecture breakdowns across eight pillars, built for traders who care more about how markets behave than about hype.
More about the publication →The ten pillars
Read in order. Each pillar walks you out of one trap with one new ability. The newest article is the worst place to begin.
- 1 The Scientific Trader Rebuild what you accept as evidence. Every rule becomes a hypothesis, every backtest an experiment you can falsify. 28
- 2 Indicator Engineering The input decides the ceiling. Build features with measurable properties that survive the tests. 82
- 3 Robust Systems Lab A strategy is not robust for surviving one friendly backtest. Here it survives hostile testing. 46
- 4 Market Structure Notes The same rule is edge on one instrument and noise on another. Read a market's personality before you deploy. 78
- 5 Microstructure Alpha The order-book layer. The same signal is worthless as taker flow and valuable as a maker improvement. 57
- 6 Portfolio Construction & System Death A real signal still loses if the size and correlations are wrong. Sizing is part of the signal. 59
- 7 Python Research Notebooks Stop taking results on faith. Re-run every claim on your own data and see whether it holds. 5
- 8 Physics, Geometry & Event-Driven Markets The frontier. Markets as event-driven nonlinear systems, not fixed-time price series. Read it last. 12
- 9 Prediction Market Arbitrage The cleanest money on Polymarket and Kalshi comes from prices that contradict each other, not prices that turn out wrong. 44
- 10 Cross-Sectional & Factor Investing Stop timing one asset. Rank the whole cross-section and let relative value, not direction, carry the return. 25
Latest articles
5.55 Bar Portion Beats MACD: A Directional Skew for Crypto Market Making
Crypto market making: bar portion is close minus open, divided by high minus low. A full up-bar mean-reverts, so shift the reference price down.
4.75 Commodity Currencies: Predictable Only Where They're Thin
Commodity export prices predict FX one month ahead only in thin currencies: a 1σ shock is +0.39%. The lag is gone in the Australian and Canadian dollars.
9.42 Crowd Wisdom or Informed Minority? The 3% Who Carry Polymarket
Polymarket sign-randomization skill test: flip each account's bets one event at a time, and about 3% still beat the scramble. Their volume cuts pricing error; crowd volume raises it.
9.48 Do Prediction Markets Match Option Prices? The Binary Benchmark
Bitcoin threshold binaries: invert a listed call into the discounted risk-neutral Yes price. Polymarket sits about six points above it, widest at low probability, and the gap halves in four hours.
5.53 Where Is Bitcoin's Price Actually Set? Unregulated Venues Win
Bitcoin price discovery squares the ratio of the Hasbrouck share to the component share, in a 10-millisecond error-correction model. The cheapest book takes the permanent move.
10.20 A Trend Factor for the Crypto Cross-Section (and Its Overfit Tell)
Crypto trend factor CTREND earns 3.87% a week, Sharpe 1.94. On 55,296 designs the median Sharpe is 1.34, and 1.94 sits at the top of the grid.
10.19 Crypto Has Fundamentals: A Seven-Factor Model (Read Skeptically)
Crypto factor model Q-7: on-chain quality posts a t-stat of 9.80 and a 245% annual long-short. The authors' survivor universe leaves that spread in the table.
3.47 The Real IS→OOS Sharpe Haircut (Closed Form, Not "50%")
Sharpe ratio haircut: a 10-year commodity momentum fit keeps about 30% out of sample. The flat 50% rule is one cell, and often the wrong one.
5.51 Better Inputs Beat Deeper Nets: Crypto LOB Direction
Crypto LOB direction: a logistic regression matches DeepLOB at 0.73 accuracy on one Bybit day. The Kalman filter drops the same call below a coin flip.
10.24 Learning to Rank, the Original: Pairwise and Listwise Cross-Sectional Momentum
Cross-sectional momentum keeps the order and throws the forecast level away. A pairwise loss trains which name outranks which. Squared error can tie and still swap the book.
3.40 Does Complexity Actually Help? (flagship)
Out-of-sample Sharpe: 12,000 features score 0.49 and lose to buy-and-hold at 0.55. Complexity pays only with more data, by 0.12%/month on a global cross-section.