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 forum post reports that a strategy based on a platform template runs, but simulation fails at a dropna step because of NaN values after the user adds factors. The author’s attempted fix was to fetch 90 calendar days of earlier daily index data,…
This MetaTrader 5 Expert Advisor uses signals from the CenterOfGravityCandles indicator. A signal is generated when a bar closes with a change in the indicator’s candle color. The description notes that the compiled indicator file must be installed for the…
The post reports a discrepancy between a backtesting platform’s monthly return for the CSI 300 benchmark and an external reference calculation. It attributes the difference to the platform using the first day of the month’s closing price as the starting…
The document argues that trading systems should be written so that changes to strategy logic require only localized code edits. It illustrates this with an R-Breaker example: if backtesting suggests that holding positions overnight adds risk without enough…
This short discussion outlines data-related challenges faced by quantitative investment teams as they develop and test strategies. It describes quantitative investing as turning historical market behavior into data, using statistics and programming to…
This Chinese-language post outlines an A-share screening idea that combines three conditions: reported position increases above 5%, a favorable company profile, and a gain below 6% at 9:25. The author interprets position increases as a possible sign of…
This note describes a short-term reversal strategy attributed to Larry Connors. For a long entry, price must be above its 200-period simple moving average and the two-period RSI must fall below 5; the position exits when price rises above its five-period…
This indicator combines five-candle fractal detection with a Commodity Channel Index filter. It displays a signal only when CCI meets a configurable threshold on the candle associated with the fractal, aiming to screen out some signals during sideways…
This Expert Advisor uses a price-extreme channel to generate trades. By default, a close above the upper channel boundary opens a long position, while a close below the lower boundary opens a short position. It checks signals on each new bar, closes opposing…
This ProRealTime indicator identifies support and resistance areas by grouping historical price pivots into price bands. Its settings control the pivot lookback, whether pivots use highs and lows or open and close values, the maximum band width, the number…
This brief BigQuant Q&A addresses whether to exclude stocks listed on China’s ChiNext and STAR Market boards when building an AI trading strategy. Its central recommendation is to apply the exclusion during both model training and prediction, so the model is…
The document presents Follow-the-Leader, a factor-based method for constructing a smaller portfolio that tracks a broad equity index. Instead of selecting stocks only by index weight or correlation with index returns, the method estimates the number of…
This document describes an automated trading system that uses a Trend Intensity Index oscillator. A signal is generated at the close of a bar when the indicator moves into an overbought or oversold zone, shown by a change in its color. The system is…
The discussion addresses adding five- and fifteen-minute intervals to VN.py version 3.4.0 for backtesting. One reply suggests that when the source data is already stored at those resolutions, importing and selecting it as one-minute data can work because…
This Expert Advisor uses the Parabolic SAR to determine a candidate trade direction, but only when ADX is below a chosen threshold. It then adjusts direction according to the previous trade: after a winning trade, it may enter in that trade’s direction;…
This document describes a stock screen intended to find possible trend changes. It looks for equities whose moving averages converge, using at least five averages as the selection condition, and also imposes a limit on the indicated pre-open gain. The…
The document describes an Expert Advisor that trades a trend signal from the AML moving average. A trade signal is generated at the close of a bar when the indicator changes direction while retaining its color. The example applies the method to XAUUSD on a…
This document outlines a Chinese equity screen based on an intraday amplitude threshold, exclusion of ST-designated stocks, a five-day high condition described as a limit-up method, and at least two limit-up events over a 500-day lookback. It supplies a…
This document presents a Chinese equity selection rule requiring MACD above zero, the current high to match a two-day high, and more than two limit-up events within ten days. It explains these conditions as indicators of positive momentum, a nearby price…
This document describes a MetaTrader workflow that records historical real ticks once, then replays them in mathematical mode for strategy testing. Sharing a tick file among optimizer agents is intended to avoid repeated data writes and reduce the time spent…
This study presents StockRanker, a supervised learning-to-rank method for selecting Chinese A-shares. It uses gradient-boosted trees to rank the market by expected future return. The input features are derived from seven basic price and volume series using…
This document describes an Expert Advisor that trades when a Kalman Filter indicator changes color. It generates a signal at a bar close, so the strategy responds to a change in the indicator’s direction rather than acting during the bar. The advisor…
The post raises a reproducibility question: two strategy templates reportedly use the same model, factors, parameters, and data, yet produce substantially different backtest results. The author asks which result is correct and whether one template contains…
This stock-selection proposal screens Chinese A-share listings in the metaverse industry, ranks them by the day’s opening-auction amount, and selects those with simultaneous bullish crossovers in MACD, KDJ, and RSI. The text gives example indicator settings…