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 short-term Chinese equity screen targets stocks in the metaverse sector that had at least one limit-up event during the prior 25 days and performed well during 2021. The example rules use recent limit-up activity as a signal of short-term attention and…
This overview compares common machine learning methods by their assumptions, strengths, and limitations. It introduces the bias variance tradeoff and explains how model complexity can lead to underfitting or overfitting. It then surveys naive Bayes, logistic…
This report summarizes a two-year simulation of a Donchian strategy on NEO-USDT using six-hour candles from Binance, covering January 2019 through January 2021. It reports 18 closed trades, all long, with no open positions at the end. The strategy shows a…
This trading system uses the ColorFisher_m11 oscillator histogram to generate entries and exits. It opens a position at a bar’s close when the histogram changes to blue or pink, which the description associates with the oscillator entering an overbought or…
This document describes an Expert Advisor that trades breakouts using the Color_PEMA_Envelopes_Digit_System indicator. It generates a signal when a bar closes with a color different from the preceding bar, or when the preceding bar has no color. The strategy…
CazaGaps is presented as an analysis tool for identifying and measuring upward and downward opening gaps in an index or other instrument. It marks a positive gap when the open is above both the previous close and previous high, and a negative gap when the…
This short project note outlines a workflow for preparing data and fitting a predictive model. It divides SQL data construction into a base dataset, a normalized dataset, and a final feature-and-label stage. The note mentions cross-sectional factor ranking…
This weekly report compares three Huatai fundamental stock-selection portfolios during a market pullback: a high-dividend-yield model, a low price-to-sales model, and a relative price-to-earnings model. It reports absolute returns, benchmark-relative…
This document defines an abstract data-formatting interface for experiments using the Temporal Fusion Transformer (TFT). Dataset-specific formatters are expected to define column names and roles, fit scalers, transform features, reverse prediction…
This tutorial introduces a workflow for inspecting market data and orders in HftBacktest. It shows how to configure an asset with historical tick data, an optional starting snapshot, contract and tick sizes, latency, queue position, exchange fill behavior,…
The document compares simple systematic strategies, such as indicator rules applied to liquid developed markets, with advanced approaches that use specialist market knowledge, statistical testing, rigorous portfolio construction, and less liquid instruments.…
This tutorial explains simple moving averages and their use in equity trend strategies. It outlines common short-, medium-, and long-term averaging periods, describes how a moving average is calculated from closing prices, and introduces Granville-style…
This monthly allocation report describes a strategic portfolio framework that maps broad asset holdings to underlying macroeconomic risks. It uses principal component analysis to define five factors—economic growth, interest rates, credit, term spread, and…
The article explains a confirmation approach that pairs MACD with one other technical indicator. MACD line and signal-line crossovers provide directional signals, while the Stochastic oscillator or RSI supplies overbought and oversold readings. With…
This article turns James O’Shaughnessy’s value-investing principles into a monthly Chinese equity screen. It favors companies larger than the market median in market capitalization and share capital, then ranks stocks using cash-flow yield, sales yield, and…
This document describes a Rust framework for developing high-frequency and market-making strategies in backtests and live trading. Its replay approach uses tick-level market data and reconstructed order books, including both market-by-price and…
This sample demonstrates how to configure a Backtrader run with a trading calendar and resampled market data. It defines a custom NYSE calendar for 2016, loads Yahoo Finance data either from a feed or a local CSV file, and resamples the input series to…
This report summary describes a growth-stock selection approach for Chinese equities that pairs an earnings-surprise signal with the next-day price gap after an earnings announcement. Rather than comparing reported earnings with a numeric consensus estimate,…
The notebook estimates crop prices from Malaysian GDP, population, and crop production data. It fits ordinary least squares models for comparison, then uses quadratic optimization to constrain the non-constant coefficients to be nonnegative. Production…
The document proposes a Chinese equity screen that combines a daily high-low range above one percent, a newly formed KDJ crossover, and a measure of today’s volume increase above five percent of its recent average. It provides example formulas in a…
This strategy trades the DAX on five-minute bars, requiring Ichimoku conditions to align across five-, fifteen-, and sixty-minute timeframes. Long and short signals require price to be on the corresponding side of the cloud and the lagging-span comparison to…
This report introduces gcForest, or multi-grained cascade forest, as a tree-based deep learning model proposed as an alternative to deep neural networks. It argues that the method may suit financial data because it is described as more robust to…
This report evaluates risk parity, an asset allocation approach that aims to equalize the risk contributions of assets in a portfolio. It tests the approach using two historical data window designs: rolling windows and expanding recursive windows. For each…
This ProRealTime indicator evaluates price performance between user-selected start and end dates. It calculates compound annual growth rate (CAGR) from the two closing prices and the estimated elapsed years, scans intervening bars for the largest percentage…