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 trading system uses changes in a CCI Histogram’s color to generate entries at bar close. A signal appears when the histogram switches from neutral gray to red or blue, which the description associates with the CCI oscillator entering an overbought or…
This overview introduces VeighNa’s alpha research framework as a linked workflow for equity research: organize local market and constituent data, build factor and label datasets, train prediction models, generate scores, and test portfolio strategies. It…
This practitioner account explains how to translate a stock ranking model into daily trade lists and manual orders. The model ranks the stock universe, buys higher-ranked names, and prioritizes lower-ranked holdings for sale. The author describes how the…
This course-page description outlines a workflow for developing multi-factor investment models, moving from factor testing to evaluation and combination. It highlights checking whether factors are effective and stable, standardizing and neutralizing them,…
This forum post asks how to choose among three paid equity strategies using platform rankings and reported performance figures. The examples contrast a highly ranked strategy with large cumulative gains but a substantial drawdown, a smoother strategy with a…
The discussion explains that weights in a multi-strategy portfolio can represent each strategy’s share of the combined allocation and can also be used to calculate a weighted portfolio return. Its example divides capital evenly among three strategies,…
This description outlines an Expert Advisor that trades from the FisherCGOscillator indicator. It forms a signal at bar close when the indicator's main and signal lines cross. The EA depends on a separately compiled indicator file installed in the platform's…
This study summary describes using recurrent neural networks, including long short-term memory cells, to forecast stock movements separately by industry. The rationale is that firms in one sector may share common influences, while industries can differ in…
This event outline introduces a planned series on quantitative options research and development, with later sessions covering ETF, gold, and iron ore options. The first session focuses on index options, contrasting options strategies with CTA strategies and…
This report summary describes using gene expression programming, a heuristic inspired by biological evolution, to discover price-volume factors from short-horizon data. Because many candidate factors had weakly monotonic group returns or no excess return in…
This Backtrader example demonstrates an order-entry workflow driven by a moving-average crossover. When the shorter-period average crosses above the longer-period average and there is no open position, it submits a limit buy below the current close. It pairs…
This Lumibot example demonstrates a daily cryptocurrency strategy using Bollinger Bands with historical data supplied through CCXT backtesting. It calculates a rolling mean and standard deviation over a configurable window, then derives upper and lower bands…
This page outlines an Expert Advisor built around the TrendValue indicator. It enters a trade when a diamond of the corresponding color appears at a bar close, making the indicator’s colored markers the system’s entry trigger. The page says the reported test…
This code module supplies plotting and summary routines for quantitative factor research. It formats tables for factor returns, turnover, rank autocorrelation, quantile statistics, and information coefficients. Its chart functions visualize information…
This Chinese-language guide describes a manual VeighNa setup on Ubuntu. It recommends using pyenv to select a Python version for the project and a virtual environment to isolate its package dependencies. It then outlines installing the project and several…
The article outlines a Chinese stock-screening idea that selects shares with amplitude above one and rising troughs, using 2021 as the reference year. It describes the approach as purely technical and provides example implementations in a market-platform…
The document explains how a continuous futures series joins expiring contracts by applying cumulative price adjustments at caller-supplied roll transitions. It compares backward and forward additive spread adjustments with multiplicative ratio adjustments,…
This Expert Advisor uses signals from the ColorXTRIX_Histogram indicator. A signal is generated when a bar closes and the histogram changes direction, so the described system responds to a shift in the indicator rather than acting on an intrabar movement.…
This strategy note selects stocks with turnover between 3% and 12%, a positive ten-day price increase below 35%, and prior-day auction turnover above 0.26. It presents the rules as a way to find actively traded stocks with recent positive movement. A formula…
This Chinese-language strategy note describes a screen for Shanghai-listed A shares whose 14-period RSI is below 65 and whose year-over-year growth in net profit attributable to parent-company shareholders is between 20% and 100%. Its example also requires…
The document introduces nonlinear regression as fitting observations with a mathematical function, often a curve, rather than a straight line. It describes minimizing the sum of squared deviations as a way to assess fit and names logarithmic, trigonometric,…
The Trend Balance Point (TBP), attributed to J. Welles Wilder, is presented as a momentum-based system for taking long or short positions. It derives separate threshold levels from recent closing-price changes; crossing those levels determines the direction…
This document describes an Expert Advisor that generates a signal when a bar closes and the FRASMAv2 moving-average indicator changes color. It requires the compiled indicator file to be installed in the platform’s indicator folder. A supporting library is…
The article proposes screening mainland Chinese main-board stocks for turnover between 3% and 12%, a robot-related theme, and circulating market value below 10 billion yuan. Its initial version uses a 2019 dividend payout threshold above 25%; the revised…