Algorithmic & AI Trading

A ranking loss and a profit threshold

A convolutional model scores 0.6316 on area under the curve for a seven-day Bitcoin move — and the paper is more interesting for how it is judged.

2026-08-28·2 min·Source: arXiv

When going first is worth something

Three authors work out when a constant-function market maker is at rest, and when the order of two traders decides who gets the better fill.

2026-08-26·2 min·Source: arXiv

When to move the range, and what it costs

Five authors model concentrated liquidity provision as impulse control and learn the rebalancing policy, reporting a compressed lower tail rather than a higher mean.

2026-08-21·2 min·Source: arXiv

Quoting at several levels at once

A reinforcement learning market maker places orders across the book rather than at the touch, and is tested against three kinds of counterparty.

2026-08-18·2 min·Source: arXiv

An agent that reads the chain and the news

CryptoTrade pairs on-chain metrics with off-chain signals and reflects on its own past trades before deciding the next one.

2026-08-17·2 min·Source: arXiv

Two in a thousand graduate, eight times more with a channel

A survival analysis of 832,941 token launches puts a number on something the market treats as folklore.

2026-08-17·2 min·Source: arXiv

Generating order books in ten solver steps

A flow-matching model produces limit order book trajectories at a fraction of the sampling cost of diffusion, and transfers to instruments it never saw.

2026-08-13·2 min·Source: arXiv

Language models are poor traders and useful analysts

Given execution authority they underperform. Given a research task they save hours. The distinction is not subtle.

SpansAISECFIN

2026-08-11·10 min

The ordering supply chain professionalised

Extraction moved from opportunistic scripts to an industry with tiers and contracts.

SpansAISECFIN

2026-08-07·7 min

Backtests on model-driven strategies leak more than usual

The model was trained on the period you are testing. That is not a detail.

SpansAISECFIN

2026-08-03·6 min

Latency arbitrage moved to inference time

When two desks run similar models, the edge is who answers first.

SpansAISECFIN

2026-07-30·8 min