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 article introduces convolutional neural networks and explains how one-dimensional convolutions can extract local patterns from financial time series. It describes convolution as applying learned weights across sequence windows, while pooling summarizes…
The article explains how Bollinger Bands can help traders assess crypto volatility and possible market direction. The bands are described as a moving average with upper and lower boundaries typically set two standard deviations away. Narrowing bands indicate…
This note describes a double-smoothed adaptive moving average intended to address frequent slope changes in an adaptive moving average. It places the method in the context of Kaufman's adaptive moving average and a modification that also accounts for where…
This MetaTrader expert advisor detects bullish and bearish inside-bar patterns and opens corresponding long or short positions. It offers three position-handling modes: open a position at every signal with stop-loss or take-profit exits; reopen positions in…
This configuration describes a Qlib workflow for training a binary LightGBM model on one-minute CSI 300 data from China. It uses the Alpha158 feature handler, robust feature normalization, missing-value filling, and cross-sectional label ranking. The label…
This article outlines an equity screen combining membership in the Metaverse theme, positive net buying by large participants during the auction, and a moving-average trend condition. Its formula expresses the trend condition as the 30-day average above the…
This note describes a stock screening rule that combines a positive MACD reading, a company or concept filter, and a stochastic K value below 20. The intended logic is to select shares with an upward trend signal while looking for an oversold condition that…
This stock selection method filters Chinese equities in the metaverse industry using the previous day’s actual turnover rate and the current opening auction return. It selects stocks with turnover between 3% and 28% and auction returns between -2% and 5%.…
This page identifies itself as a reproduction of a Chinese multi-factor stock-selection research report about information contained in moments of unusually high trading volume. It also references related research on converting intraday minute-level spike…
This document describes an Expert Advisor that uses the PFE oscillator to generate trades. It forms a signal when a bar closes and the indicator changes direction. The system therefore relies on a direction turn in the oscillator rather than a threshold or…
This document describes a Chinese equity screening rule combining daily range, a reversal condition, three consecutive down days, and a comparison of recent highs with a longer lookback period. Its final version also requires the highest price over the last…
The document traces several ways to build moving average trading rules, using a 15-minute Chinese rebar futures index as its backtest example. It starts with price crossing a single average and short-period averages crossing longer ones, then adds…
The proposed equity screen combines intraday range, Bollinger Band position, and a specific opening-time price-change condition. It looks for stocks whose range exceeds its recent average, whose close lies between the middle and upper Bollinger Bands, and…
This report adapts Peter Lynch’s six company categories to China’s A-share market: slow-growing, stable-growing, fast-growing, cyclical, turnaround, and asset-rich companies. Its selection framework first screens for a positive price-to-earnings ratio and a…
This post presents a long-only DAX strategy on 15-minute bars. It looks for a prior lower low, a current high below the earlier rolling high, a bullish candle, a limited bar range relative to the recent high-low span, and a close above SuperTrend. The…
This guide explains how to run a Python trading strategy backtest with LumiBot, choose a historical data provider, configure dates and sources, and review generated output. It describes ThetaData, Yahoo Finance, Polygon, custom Pandas data, and Polymarket…
The proposed daily pre-market stock screen combines a positive MACD reading with positive trailing price-to-earnings, current volume above a stated threshold, and an opening price above the prior close. The article interprets these filters as signs of upward…
This stock screen targets Chinese shares associated with the metaverse theme and above a stated circulating-market-value threshold. It looks for recent limit-up activity, with the final selection rule requiring at least two limit-up sessions in the last five…
This expert advisor combines a moving-average price filter with RSI readings in overbought or oversold territory. It opens trades when the RSI reaches one of those zones and price is on the corresponding side of the moving average. The description says the…
This forum post describes an attempt to compare a platform’s single-factor analysis module with the open-source Alphalens package. The author uses the CSI 300 universe and the PE_TTM_0 factor, with a 22-day rebalancing interval. They aim to prepare…
This configuration defines a Qlib workflow that trains a PyTorch feedforward neural network on Alpha360 features for CSI 500 stocks. It uses a forward close-price return label, robust feature normalization, missing-value filling, and cross-sectional rank…
The article examines why sector-themed equity funds attract investors and which industries may suit them, then develops two portfolio design approaches. It links investor demand to the visibility of past winners on financial technology fund platforms and…
The post outlines a Chinese equity screening rule that combines metaverse-sector membership, positive institutional flow, and a condition based on rolling 20-period lows and closes. It describes the price condition as a way to find comparatively low prices,…
This MQL5 Expert Advisor uses a strict confirmation chain across five indicators: a moving average, MACD, Stochastic, OsMA, and Awesome Oscillator. A positive signal is accepted only when every indicator confirms it; failure at any stage discards the signal.…