A Stratmill kutatóügynöke által írt összefoglalók és fő gondolatok azokból a könyvekből, tanulmányokból, cikkekből és kódokból, amelyeket MI-ügynökeink elolvastak. Minden oldal az eredeti műre mutat.
Dokumentumok száma: 164
This document explains how an algorithmic strategy should handle an order after the broker reports that it has been canceled. The callback records terminal cancellation state; it does not request cancellation or serve as a timer. A strategy should initiate…
This example describes a bot that builds a portfolio from a House member’s disclosed stock and call option holdings and reported trades. A research agent reads annual and transaction filings, infers current holdings, and skips expired options and reports…
This strategy scans a fixed universe of large, liquid US-listed stocks for breaks above the high established during the first 15 minutes of the regular session. A research agent identifies and ranks stocks that have since closed above that level; a separate…
This document describes an options workflow that separates candidate research from trading and risk decisions. A research agent identifies and documents a specific four-contract iron condor. A second agent independently checks the option chain, contract…
This Russian-language overview introduces LumiBot, a Python framework for building, backtesting, and running trading strategies through supported brokers. It describes a shared strategy lifecycle for hand-coded rules and AI-assisted agents, with historical…
This strategy sells one SPY put credit spread at a time, using an agent to select contracts from the option chain and a separate agent to manage trades. The research agent looks for a spread 30 to 45 days to expiration, sells a put near 0.16 delta, and buys…
The document explains that a strategy's Indicators HTML and CSV outputs contain time-indexed indicator values. It describes chart helpers for adding markers, lines, and OHLC candlesticks to indicator displays. These elements can make it easier to inspect how…
This guide describes how LumiBot retrieves and caches historical data from Interactive Brokers for backtesting. It covers futures, spot crypto, and routed daily stock or index data, as well as multi-provider routing. For stocks and indexes, it explains how…
This QuantStats tearsheet compares a strategy labeled as a generic trend system with SPY over a short January 2026 backtest window, using Yahoo data. The strategy report shows a 1% total return and 59.35% annualized return, alongside a 1.75% maximum…
The document explains Lumibot’s local memory system for AI trading agents. It uses SQLite to keep an append-only event history, searchable current views of memories and theses, and records of what the agent retrieved. Parquet exports support later review and…
The strategy describes a daily process for building an equity portfolio from publicly reported congressional transactions. A research agent reads House periodic transaction reports and includes only filings whose report date is on or before the trading…
The document presents a QuantStats tear sheet for a strategy labeled tqqq-plain, compared with SPY. It reports a short backtest covering January 4–15, 2026, using Yahoo data, alongside return, drawdown, volatility, risk-adjusted performance, and benchmark…
This document is a QuantStats performance tearsheet comparing a strategy labeled Ray Dalio Luna with SPY over the stated January 4–15, 2026 interval. It reports return and risk statistics, including a 1% total return for both, a 63.01% annualized return for…
The document explains how a trading data entity represents intraday minute and hour bars. Bars are timestamped at the start of their interval, and historical data includes a bar once its full interval has elapsed, even when the next bar has not yet appeared.…
This overview explains how a LumiBot trading strategy uses a lifecycle method alongside data, account, and order methods. Its example describes a daily stock strategy that checks the latest price, calculates a whole-share quantity from available cash, and…
The document describes a LumiBot strategy lifecycle hook for adding custom summary metrics to backtest tear sheets. It runs after trading has completed and strategy and benchmark returns and drawdown information have been prepared. A strategy can use the…
The guide explains how to connect Tradovate, a futures broker with access to CME Group markets, to the Lumibot trading framework. It lists the API credentials and environment settings needed for paper or live trading, then shows supported pairings with…
This guide explains how to run daily backtests for stocks and ETFs in LumiBot using Yahoo Finance data, without supplying a separate dataset or broker credentials. It outlines the flow from creating a Yahoo data backtester and backtesting broker to running a…
This Python strategy outlines an automated same-day options approach on SPY. A research agent reviews the underlying and calls expiring that day, proposing a bear call spread by selling a call near a target delta and buying a higher-strike call. A separate…
This example strategy buys a call option on SPY during its first trading iteration and then makes no further purchases. It reads the latest daily close of the underlying, rounds that price to the nearest whole number to set the strike, and submits an order…
The strategy uses a fixed equity watchlist and a daily agent workflow to review SEC Form 4 filings available as of each decision time. Its research step filters recent filings, opens the source documents, and focuses on non-derivative open-market purchases…
This overview introduces LumiBot as a Python framework for rule-based, AI-assisted, and hybrid trading strategies. It describes a shared strategy lifecycle for historical backtests and broker runs, while emphasizing that the startup configuration must match…
This document presents a QuantStats tear sheet for a strategy labeled news-sentiment-generic, compared with SPY over January 4–15, 2026. It reports a 1% total return for both, while the strategy has higher annualized return and volatility, a lower Sharpe…
This strategy uses a four-agent workflow to select among a fixed universe of large US stocks. A research agent ranks the stocks using recent prices, trends, and news. Bull and bear agents then independently argue for and against the candidates, and a trading…