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 example describes a concentrated long-only stock portfolio built through a sequence of AI agents. A research agent ranks companies for understandable businesses, cash generation, and attractive prices. A second agent challenges each idea by examining…
This code excerpt implements three filters intended to support spread trading and risk adjustment. The correlation filter calculates rolling correlation between the first two series, rescales it to a zero-to-one range, and uses changes in that measure to…
This post proposes screening A-share stocks for turnover between 3% and 12%, market value below 10 billion yuan, scale above 200 million yuan, and no losses. It presents the screen as a way to combine trading activity, company size, and profitability, then…
This document is a historical intraday dataset for the Dalian Commodity Exchange iron ore futures contract. Its rows report timestamped five-minute open, high, low, and close prices, along with volume, turnover, and open interest. The visible entries cover…
This stock-selection idea targets Chinese beverage and alcohol companies with turnover between specified bounds and at least five overlapping moving averages. The accompanying explanation treats the turnover range as a way to focus on moderately active…
This Backtrader example demonstrates a simple moving average crossover strategy and how cheat-on-open mode changes the timing of order decisions. It builds two moving averages, with configurable periods and moving-average type, then uses their crossover as…
This article explains why trend-following systems often endure repeated small losses in pursuit of occasional large gains. It advises traders to select a trend horizon that fits their tolerance, comparing possible timeframes through backtests, and to define…
This post proposes selecting stocks with a daily range threshold, substantial prior-day trading activity, and a pattern described as an engulfing reversal. The range and turnover filters are presented as ways to focus on actively traded, volatile shares,…
This document explains the Simple Harmonic Oscillator (SHO), a bounded indicator intended to estimate market-cycle periods over short and intermediate horizons. It describes a centerline as a balance between bullish and bearish periods, with outer levels…
The document describes a basic workflow for evaluating a trained quantitative model. After fitting the model on training data, apply it to a validation set, then compare its predictions with the observed values to assess performance. This separates model…
This expert-advisor design turns four RSI readings into a single weighted perceptron score. It uses RSI periods of 12, 36, 108, and 324, rescales each indicator around zero, and combines them with weights selected through optimization. The trading threshold…
This research summary explains how to build a machine-learning stock-selection process using historical factor values to predict subsequent returns. In the training stage, a supervised model learns the relationship between inputs and returns; in the testing…
This MQL5 demonstration illustrates supervised classification with a support vector machine (SVM), using a fictional animal-recognition task to explain labeled examples and learned decision boundaries. It generates seven-feature observations with rule-based…
The document describes a price gap indicator that displays gaps as a histogram. It assigns red bars to upward gaps, which it suggests may fill downward, and blue bars to downward gaps, which it suggests may fill upward. The proposed gap-filling direction is…
This helper prepares spread changes and their lagged values as inputs for a regression model. It can expand the lag features with pairwise products, split a chosen in-sample period into ordered training and test sets, and keep a separate out-of-sample…
This example turns a CAPM regression into a monthly stock-selection process. It takes a recent window of daily returns for eligible constituents, adjusts stock and benchmark returns by a stated daily risk-free rate, and regresses each stock’s returns against…
This short platform discussion explains that an adjust factor is used to convert a stock’s real price into an adjusted price. Adjusted prices, including forward- and backward-adjusted series, are intended to keep price charts continuous across corporate…
This short forum exchange explains how to configure BigQuant’s trading engine to rebalance on a weekly or monthly schedule. For weekly scheduling, it specifies the weekly trading-day mode and a day value of 5; for monthly scheduling, it specifies the monthly…
The document introduces Temporal Routing Adaptor (TRA), a model designed to learn multiple trading patterns from stock market data. It describes using TRA with Qlib datasets and workflows, and notes that the paper’s reproduction setup first trains a backbone…
The document describes an Expert Advisor that trades when the i-KlPrice histogram crosses an overbought or oversold level. A signal is confirmed at bar close, so the strategy acts on completed-bar threshold breaks rather than intrabar movement. The advisor…
The document proposes a Chinese equity screening approach that selects robot concept stocks with daily amplitude above 1%, float capitalization below 10 billion, and no ST designation. It specifies screening before 10 a.m. and says a five-step limit-up…
This article compares five platforms for automating cryptocurrency trades: OctoBot, CryptoHero, 3Commas, Cryptohopper, and Pionex. It describes available approaches such as grid trading, dollar-cost averaging, signal following, market making, and AI-assisted…
The document describes an Expert Advisor that trades signals from the AMkA indicator. It checks for a newly colored point when a bar closes and requires the latest point and the two preceding points to have different colors. The text indicates that this…
This Expert Advisor generates signals from intersections of TDI-2 indicator lines, evaluated when a bar closes. It follows the direction of the signal and adds to an existing position when the profit from the most recent trade, measured in points, exceeds a…