Blog

Articles and interviews

How a proprietary high frequency trading firm prices its quotes, moves its orders and tests its ideas. Every piece explains work we did, through the mechanism and a worked example.

Pinned / Research paper

Autocorrelation of returns in major cryptocurrency markets

Do past returns in major crypto markets predict the next ones? We tested BTC/USD, ETH/USD and ETH/BTC on Bitfinex and XBT/USD on BitMEX. Significant autocorrelation showed up on 5-minute and hourly bars in every market.

  • Research paper, 11 pages and 12 figures
  • Eugene Tartakovsky, Ksenia Plesovskikh, Anastasiia Sarmakeeva and Alexander Bibik
  • arXiv 2003.13517, March 2020
Pinned / Video interview

Hummingbot interview with Eugene Tartakovsky

Eugene explains how 3Jane runs proprietary trading with its own capital. The team started on Hummingbot, then added custom pricing models, faster execution and hedging across exchanges.

  • Video interview, 45 minutes
  • Hummingbot Community Spotlight
  • Published 19 August 2021

Trading strategies

How each strategy earns, and how a quote, the inventory it creates and the hedge that offsets it form one decision.

Topic overview

Market making, inventory and cross-exchange hedging

Every quote is also a decision about inventory. The hedge-aware maker prices each quote from the cost of offsetting a fill on other venues.

Spot and Liquidity Swap arbitrage: rewards, impact and execution

How fees and pool impact are priced before trading, how quotes are sized by pool capacity, and how BNB rewards stay visible beside trading PnL.

Triangular arbitrage: executable cross-prices and three-leg execution

A cross-price gap has to survive bid and ask sides, three fees and three books. One passive order is priced from the cost of two taker hedges.

Statistical arbitrage with Kalman-based cross-pricing

A BTC/EUR book tracks BTC/USDT perpetual futures through EUR/USDT. A scalar Kalman trend of the price ratio, estimated separately for bid and ask, sets the quotes.

Grid trading as inventory rebalancing

Our grid sets a target split between base and quote at each level and places whichever order restores it. Partial fills and price gaps can't break its view of its own balances.

Trading technology

The software that carries exchange data into orders and back into reporting.

Topic overview

From Hummingbot to our own Python trading system

External fair prices, reactions to individual book changes and hedges on other exchanges led us to an event-driven runtime on asyncio and CCXT Pro.

Inside the Chronicle trading engine: queues, orders and latency

Our Java engine records order intent before anything leaves the process and times each leg of an order separately.

Trading data infrastructure: normalization, instruments and observability

A research library for normalized history, an instrument service for current market rules, and model output stored beside market and account data.

Quantitative research

How we turn market data into testable hypotheses and evaluate them.

Topic overview

Building a quantitative research pipeline: data, features and event labels

The fixed, reproducible stages that take raw market observations to event labels, and where each stage's output goes next.

Cross-validation for overlapping financial observations

How purging and embargo stop labels from leaking across the train/test boundary, worked through with real indices from our test suite.

Bootstrap methods: visual comparison

From the IID bootstrap to block methods for serially dependent data. Each method gets a plain explanation and a picture of one iteration.

From model predictions to backtests and position size

Probability checks, costed simulation, and Kelly and Monte Carlo limits on exposure. One scenario runs from probability to net PnL.