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
The document builds a long-only stock strategy around Heikin-Ashi candles, which transform open, high, low, and close prices to smooth price movement. A long signal requires a bearish candle whose open equals its high, a larger body than the previous candle,…
The article explains support vector machines (SVMs) as classifiers that seek a separating boundary between classes. It introduces the geometric intuition of mapping observations into a higher-dimensional feature space, where a nonlinear boundary in the…
This guide describes a workflow for managing Hummingbot trading bots through its Dashboard: connect exchange credentials, review portfolio holdings, configure a strategy controller, backtest the configuration, and deploy and monitor bot instances.…
This expert advisor is presented as a research tool for testing an Inside Bar continuation hypothesis. It identifies a signal candle fully contained within the preceding main candle's range. A bullish main candle triggers a buy stop above its high; a bearish…
The note warns that exceptionally high win rates and smooth profit curves can conceal risks, especially in strategies that add to losing positions. It argues that evaluating a strategy requires tracking total account value against a relevant baseline. For a…
This strategy example sets an initial stop from the entry candle’s closing price minus twice the average true range. It measures the initial risk as the distance between entry price and that stop, then defines a profit threshold by multiplying the risk by a…
This code describes a deterministic replay process for trading on congressional disclosures. It uses each disclosure’s public publication time to decide whether the information was available, explicitly avoiding the transaction date as the signal timestamp.…
This Chinese-equity screening proposal combines alignment among at least five moving averages with a condition that the 20-day average exceeds the 120-day average. It also calls for considering company characteristics, including industry context,…
This notebook outlines a machine learning workflow for daily CSI 300 constituent stocks. It loads historical bars and changing index membership filters, constructs an Alpha101 dataset, and divides the sample into training, validation, and test periods. The…
This article argues that LSTM models trained on historical prices can appear to forecast stocks accurately because predicted daily prices often remain close to the previous day’s price. When plotted against actual prices, this persistence can look…
This documentation explains how to use Polygon as a historical price-data source for LumiBot backtests across stocks, options, forex, and cryptocurrencies. It describes supplying an API key, selecting a backtest date range, and running a simple example…
This Chinese-language post proposes screening stocks with at least five moving averages converging, an outstanding convertible-bond name, and a price gain below 6% at 9:25. It describes the moving-average condition as a way to find stocks with a potentially…
The article explains backtesting as a way to replay trading rules on historical data, check whether signals and logic behave as intended, and expose strategy defects before deployment. It emphasizes that historical simulation can test market assumptions, but…
This indicator presents Bear-Bulls-Power calculations as colored candlesticks derived from open, high, low, and close price series. Candle color distinguishes rising from falling bars, while brighter and paler shades distinguish whether the close has risen…
The report uses Hong Kong Exchange disclosures on holdings associated with northbound Stock Connect trading seats to estimate stock positions and sector-level additions. It argues that aggregate flows can obscure differences among market participants, then…
The document explains how to form and evaluate long-short stock portfolios, focusing on pairs trading. It compares hedge-ratio methods: ordinary least squares minimizes portfolio variance under a correlated random-walk and Gaussian framework, while total…
The document describes an Expert Advisor built around a dynamically calculated moving average whose period grows from a price-line intersection until the next intersection, then resets. A long signal occurs when a signal bar closes above the line after the…
This article outlines a reproduction of a research approach that predicts whether a stock’s closing price will rise or fall over a future horizon. It applies exponential smoothing to Apple daily price data, then builds a binary target from the price change…
This tutorial introduces bias, variance, and irreducible error as sources of prediction error. It relates model complexity to underfitting and overfitting: overly simple models tend to perform poorly on both training and test data, while overly complex…
This document describes a bootstrap test for judging whether a strategy’s average closed-trade result appears distinguishable from chance. It repeatedly resamples the observed trades with replacement, computes the average for each resample, and uses the…
The article argues that mean and variance alone may miss information when market returns depart from a stable Gaussian pattern. It describes higher moments, especially odd-order moments, as potentially useful timing signals: their values reportedly expand…
This strategy ranks commodity futures by an empirical measure of return asymmetry. At each monthly rebalance, it counts daily returns over the previous 260 trading days that exceed the mean by more than two standard deviations, then subtracts the count below…
This guide explains how long-short equity portfolios combine stocks expected to rise with stocks expected to fall. It discusses possible return sources, including security selection, market timing, and exposure to factors such as value, growth, momentum, and…
This tutorial introduces the FMZ quantitative trading platform’s core workflow for writing automated strategies. It explains how REST requests differ from WebSocket subscriptions, how platform APIs are wrapped into a common interface, and how to choose among…