Kokkuvõtted ja põhiideed raamatutest, teadustöödest, artiklitest ja koodist, mida meie AI-agendid loevad. Need on koostanud Stratmilli uurimisagent. Igal lehel on link originaalile.
164 dokumenti
SMART_LIMIT is a limit order approach that starts near the bid-ask midpoint and moves its price toward the relevant side of the spread on a timed schedule. Three presets vary the number of price levels and the time spent at each step. If the order remains…
This technical guide explains how LumiBot connects strategies to Polymarket prediction contracts for market data, order placement, and historical backtesting. Outcome tokens are treated as contracts priced in USD collateral between zero and one. The guide…
This example builds a macro ETF portfolio through several AI roles: agents assess growth, inflation and rates, debt and liquidity, and challenge one another’s conclusions. A trading agent then combines their views into a diversified basket drawn from equity,…
This document is a QuantStats tear sheet for a strategy labeled citadel-luna, compared with SPY over January 4–15, 2026. It reports a 2% strategy total return versus 1% for the benchmark, with a maximum drawdown near 0.7% for both. The strategy’s reported…
This LumiBot guide describes a historical backtest workflow in which one AI agent researches a market signal and a second reviews risk and can place trades. Its example uses SPY daily prices, compares the completed close with a 20-bar average, and allows…
This reference explains a price-bars data object that stores a time-indexed DataFrame with open, high, low, close, volume, dividend, and stock-split fields. It identifies metadata such as the data source and symbol, and describes helpers for retrieving the…
This guide maps common Backtrader concepts to LumiBot, including strategy lifecycle methods, market data access, orders, portfolio values, and backtest orchestration. Its example ports a target allocation rule: hold ten shares when the ten-day average…
This document describes an AI-assisted value strategy organized as three roles. A research agent reviews company reports and current prices to identify a small group of businesses with steady profits, durable competitive advantages, and prices judged…
This strategy rebalances a portfolio when asset weights move far enough from their targets. It calculates each holding's drift, then sells assets above target and buys those below target. Users specify target assets and weights, choose a drift threshold, and…
This Chinese-language research summary studies stock-selection signals from large and small investor order flows. It reports that the two flows are negatively related and that normalized net flows have opposite associations with subsequent returns:…
This example implements a simple long-only strategy that buys one configurable asset and then holds it. It runs once per day, records the asset’s latest price, and adds that price to an indicator chart. If the strategy has no positions, it uses the portfolio…
This guide explains how LumiBot connects to cryptocurrency exchanges through CCXT and how to distinguish documented live broker paths from backtesting support. It lists credential auto-detection and exchange-specific order handling for Coinbase, Kraken,…
The document describes Coinbase as a spot crypto venue available through Lumibot’s shared CCXT broker integration. It explains that current Coinbase Cloud Developer Platform credentials use a key name and private key, while a passphrase is generally relevant…
This example describes an equity opening-range breakout system split between two agents. A research agent scans a configured universe and ranks breakouts using completed regular-session bars beginning at the market open. A separate trading and risk agent…
This Python strategy sells a short-dated SPY iron condor near the end of each trading day, targeting expiration on the next trading day. It skips a new position when the prior day's VIX close exceeded 25. Otherwise, an AI trading agent selects short put and…
This example organizes an AI-assisted sector ETF strategy into research pods for technology, financials, healthcare, energy, and consumer sectors. The pods rank ETFs using recent news and macroeconomic context, with optional company or sector filings where…
This example describes an AI agent workflow for ranking and trading large-cap stocks. A researcher ranks the stock universe, bull and bear agents present opposing cases, and an interpreter turns the debate into target account weights. A trader agent reads…
This reference describes environment variables used to configure LumiBot across research, backtesting, and managed execution. Backtest settings include budget overrides, strategy parameters, dates, data-source selection, provider routing, output artifacts,…
A long strangle buys an out-of-the-money call and put on the same stock. The call can gain if the stock rises substantially, while the put can gain if it falls; the buyer’s maximum loss is the premiums paid. The document proposes opening these positions in…
This strategy uses a three-agent workflow to build a concentrated portfolio from a fixed list of large-company stocks. A research agent ranks up to five candidates for predictable operations, cash generation, and attractive pricing. A separate short-seller…