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.
2,013 documents
This notebook describes DeePM, an end-to-end ETF portfolio policy designed to improve performance across varying market conditions. Its components include volatility-normalized return and trend features, an LSTM-based model, variable selection, conditioning…
The document turns a cross-asset momentum hypothesis into a monthly exploratory test using a 100-ETF universe. It constructs adjusted month-end prices, measures 12-to-1-month momentum, then ranks eligible ETFs into five equal-weight groups and compares their…
This notebook demonstrates a unified OHLCV interface across Yahoo Finance, WikiPrices, and FRED, then uses the sources for current ETF data, long-history equities, and macroeconomic series. It outlines a priority-ordered fallback approach for acquisition and…
This Freqtrade example uses a five-minute trading timeframe and adds RSI readings from 30-minute and one-hour charts, as well as one-hour readings for selected cross-market pairs. Its long-entry condition requires several of these RSI values to be low at…
This multi-market trend strategy combines Chaikin Money Flow, the Detrended Price Oscillator, and the Coppock Curve. Long entries require positive readings from all three indicators and a Coppock cross above zero; short entries use the corresponding negative…
This indicator finds pivot highs and lows on a user-selected timeframe and makes them available on a chart that may use a different timeframe. Pivot detection uses configurable numbers of bars to the left and right of a candidate turning point, with a…
This strategy combines several directional and momentum checks before opening a trade: Hull moving-average slope, comparison of daily prices across bars, the relative position of Ichimoku leading spans, and a MACD built from Hull averages. A long signal…
This document presents a configurable swing strategy for SPY based on a composite financial regime index. The visible script setup uses daily data by default and draws on US and global equities, high-yield and investment-grade bonds, volatility, currency,…
This algorithm demonstrates a VIX weekly call calendar spread paired with short positions in VXZ and SPY. It selects an at-the-money strike, sells the nearest-expiring call, buys the furthest-expiring call in the filtered chain, and submits the option and…
This document outlines a trend-following system that adapts indicator periods to the selected chart timeframe. It enters long when a fast EMA crosses above a slow EMA and RSI is above 50, and enters short when the fast EMA crosses below the slow EMA and RSI…
This document describes a multi-timeframe trend method that approximates weekly exponential moving averages with longer EMA periods on a lower-timeframe chart. It uses crossovers between the mapped 42- and 84-period averages to indicate a longer-term…
This strategy uses two bar intervals to set its direction and timing. It builds 15-minute bars and compares a fast and slow simple moving average; their relationship sets a bullish or bearish trend state. On 5-minute bars, it calculates RSI and considers an…
This MetaTrader strategy combines a 50-period fast moving average and a 200-period slow moving average with the Andean Oscillator to trade EUR/USD, EUR/CAD, and USD/CAD. A bullish setup requires the oscillator’s bullish component to cross above its signal…
The supplied script begins a long-only strategy framework that combines signals from SPY, QQQ, Bitcoin, and the chart's current instrument. It calculates daily moving averages and uses Bitcoin trend, price structure, and one-day momentum to form a bullish…
This document presents a multi-asset buy-and-hold portfolio method that assigns target weights either directly or through a selected metric. Available approaches include equal allocation, annualized Sharpe ratio, annualized return, standard deviation,…
This strategy uses a selected asset’s price relative to a simple moving average calculated at a chosen resolution. A cross above the average triggers a long position, while a cross below triggers a short position. The user can select long-short, long-only,…
This strategy combines KDJ readings from three configurable timeframes, defaulting to 1, 5, and 15 minutes. It computes a weighted average of each timeframe’s K, D, and J values, smooths them with exponential moving averages, and uses the smoothed total to…
The article presents an MQL5 implementation path for Extralonger, a Transformer framework that combines temporal patterns with relationships across instruments. Its architecture is described as having temporal, spatial, and mixed branches: temporal attention…
The article describes MetaTrader indicators that reconstruct and display trading across multiple symbols from HTML strategy tester reports or CSV signal histories. Its SubChart indicator draws another symbol’s OHLC data in a chart subwindow and synchronizes…
This article presents a file-based pattern for managing parameters in a multi-currency MQL5 Expert Advisor when a long list of inputs becomes difficult to maintain and the platform limits the number of inputs. A text file supplies the symbol list, while…
This concluding article presents Extralonger, a neural-network design for modeling market data across time and relationships among instruments. Its architecture processes temporal, spatial, and combined information through parallel routes, then uses global…
This notebook queries registries for multiple trading case studies and produces cross-dataset tables for signal, allocation, cost, and risk comparisons. It reports diagnostics on the validation-ranked configuration cluster, including the top-to-tenth Sharpe…
This notebook compares portfolio allocations from PyPortfolioOpt, Riskfolio-Lib, and skfolio using the same ETF return panel. It fits allocators on a training period, checks that equivalent objectives and aligned weights agree within solver tolerances, and…
This notebook constructs the long-only, fully invested Markowitz framework, including feasible portfolios, the efficient frontier, maximum-Sharpe and minimum-variance solutions. It explains how portfolio variance depends on the covariance matrix and how…