Summaries and key ideas, written by Stratmill's research agent, of the books, papers, articles and code our AI agents read. Each page links to its original.
16,761 documents
This product guide explains a redesigned strategy interface with two parts: a viewer for examining and comparing strategies, and a creator for configuring new tests. The viewer presents performance metrics, behavior over time, and individual trade details.…
This troubleshooting note addresses errors that arise after adding a rolling-training module to an AI strategy for convertible bonds. It points to a revised notebook and identifies two implementation changes associated with the fix. First, the rolling…
This study applies a factor-timing framework from a 2019 paper to China A-share data. It parameterizes factor weights using external variables and compares two approaches based on where the information enters: a time-series model and a cross-sectional model.…
This post describes a Chinese equity selection screen with three filters: price amplitude above 1%, a ten-day price gain greater than zero but below 35%, and circulating market capitalization between 5 billion and 10 billion yuan. Its accompanying Python…
This short forum post asks how to export a backtest’s daily returns to a CSV file and where to place a suggested calculation in the BigQuant workflow. The proposed approach reads a performance DataFrame, adds one to the cumulative algorithm return, computes…
This Expert Advisor uses the AFIRMA autoregressive finite impulse response moving average indicator to generate trade signals. It checks for a change in the indicator’s direction when a bar closes, then forms a signal. The document notes that the indicator…
This Expert Advisor combines ADX, CCI, RVI, and Williams %R indicators with a martingale sizing approach. Its suggested tuning sequence first optimizes the main signal and ADX settings with the WPR strategy disabled, then tunes WPR separately, and finally…
This MetaTrader 5 Expert Advisor description outlines a breakout scalping system that trades only when a set of filters align. It uses fast and slow exponential moving averages to define direction, an ATR-based threshold for trend strength, price location…
This strategy ranks the full Chinese A-share universe using two cross-sectional signals: circulating market capitalization and five-day price momentum. It ranks each factor, adds the scores, and selects the highest-ranked 50 stocks. The portfolio assigns…
The document describes a monthly allocation rule based on a yield gap: the difference between an earnings yield measure for the S&P 500 and the yield on a ten-year Treasury bond. It fits a linear regression using historical yield gaps and stock market…
The indicator maps the direction of Heikin Ashi candles from a chosen higher timeframe onto a lower-timeframe chart. It colors a histogram according to whether the higher-timeframe candle is rising or falling, marks new higher-timeframe bars, and emits a…
This document explains how to connect to BitMEX through Lumibot’s CCXT broker interface using an explicit exchange configuration and API credentials. It notes that BitMEX is not among the globally auto-detected credential paths, and identifies the exchange…
A BigQuant user reports that a simulated run fails at a missing-data cleanup step, even though the backtest sample contains two rows. The discussion distinguishes the historical backtest data from the prediction data used during simulation, which may be…
The document describes a stock screen that combines a daily amplitude threshold, appearance on the prior day's market leaderboard, and a weekly MACD condition above zero. It presents these as signals for short-term volatility, trading attention, and an…
This report summary presents a method for setting equity allocations across a retirement investment horizon when the investor has a specified terminal wealth goal. It works backward from that goal, optimizing allocations while controlling risk. Two objective…
This notebook demonstrates an Alphalens workflow for evaluating a daily stock factor based on the gap between the prior close and current open. It defines an example universe of large-cap equities with sector labels, calculates the gap, and aligns the factor…
This document describes a MetaTrader expert advisor built around signals from the Candels High Open indicator. The generated advisor can place market and pending orders and uses a Parabolic SAR based trailing stop. It requires both the signal module and the…
The article presents five claimed strengths of quantitative investing: building models from processed data and backtests, using machine learning to handle information, applying systematic rules to reduce emotional decisions, analyzing broad datasets, and…
This example outlines an end-to-end workflow for training and evaluating reinforcement learning agents for order execution. It covers preparing five-minute HS300 data and order files, configuring PPO and OPDS training tasks, saving checkpoints, and running a…
The document proposes a Chinese equity screen that combines a prior-day appearance on the market's notable-trading list with a price-range filter and ownership-concentration rankings. Its stated criteria are daily amplitude above 1%, a prior-day notable-list…
This research note explains how genetic programming can evolve mathematical formulas from market data to discover equity selection factors. Starting with randomly generated expressions, the algorithm evaluates their fitness against a target and applies…
The document reports a backtest of a Donchian strategy on Binance BTC-USDT six-hour candles spanning January 2019 to January 2021. It records 18 closed trades and one still-open position. The reported net profit was 45,194.35 from a starting balance of…
The example sketches a Python environment that connects a CTA backtesting engine to an agent-like training loop. It initializes a backtest, subscribes a strategy to five-minute bars, starts asynchronous execution, and advances the engine one step at a time.…
The document proposes a Chinese A-share stock screen focused on the metaverse theme. Its initial conditions are yesterday’s turnover above 8% and at least two limit-up events within 500 days. A later version adds a market-capitalization filter, described as…