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 describes a buy-sentiment factor built by distinguishing aggressive purchases, which execute against sell orders already on the book, from passive purchases, which wait as limit orders for incoming sells. It argues that finer-grained market data…
This research review describes a dynamic, out-of-sample process for selecting US active equity mutual funds from observable fund characteristics. It compares elastic net, random forests, gradient boosting, and linear regression. Each year, models are trained…
The document describes an Expert Advisor that trades signals from a Hans indicator cloud system. A signal is generated when a bar closes after breaking through a channel, so the stated entry trigger depends on a completed bar rather than an intrabar move.…
The post argues that factor research can use information from later minutes within the same trading day when constructing a daily-frequency factor, provided the factor does not use data from the following day. It proposes examining relationships between…
This study tests whether investors can improve a diversified global equity factor portfolio by adjusting factor weights with time-series signals or cross-sectional characteristics. It applies parameterized portfolio policies to twenty long-short equity…
This research summary compares seven ways to identify active mutual funds with positive, negative, or zero risk-adjusted performance. It explains a factor-model benchmark and methods that adjust for multiple testing, including bootstrap and false discovery…
This article reviews seven methods for classifying active mutual funds as skilled, unskilled, or zero-alpha, with emphasis on how their accuracy changes when return histories are short. It describes a four-factor alpha benchmark, multiple-testing…
The document explains FMZ’s simulation-level backtest, where a strategy runs through repeated polling and receives market data through platform API calls. It distinguishes this approach from real market-level testing, which uses recorded tick data, and says…
The post describes a Chinese stock-selection screen based on daily amplitude above 1, a turnover-based measure between 0.5 and 2 that combines the prior day's turnover with the current auction volume relative to the prior day's volume, and a stated price…
This beginner post presents a small script for counting runs of consecutive rising or falling market observations from candlestick data. Its example compares each candle’s high with neighboring highs, resets the run counter when direction changes or prices…
This MetaTrader expert advisor places buy limit and sell limit orders when its conditions are checked at the start of a new bar. If one order triggers, it removes the remaining pending orders. The description also says position trailing is checked on every…
This notebook demonstrates a portfolio optimization workflow using FinRL’s PortfolioOptimizationEnv and the EIIE policy architecture. It downloads data for ten Brazilian stocks, scales each stock’s series, trains a policy-gradient agent on an earlier period,…
This A-share stock screen combines daily price range, relative trading volume, and recent limit-up activity. It selects stocks whose high-to-low range is at least 1% of the low, whose volume is between 1.5 and 6 times its five-day average, and whose recent…
This personal account traces a progression from speculative cryptocurrency trading to learning systematic futures trend trading and eventually writing an EMA-based strategy. The author describes early gains followed by losses from discretionary trading and a…
This tutorial presents a workflow for evaluating a factor on Chinese equities, using the lower Bollinger Band as an example. It introduces factor analysis as a way to summarize variables and derive composite scores, then describes building daily factor data,…
This documentation page explains how to run Freqtrade backtests on historical OHLCV data, select a strategy, timeframe, date range, trading pairs, starting balance, stake settings, fees, and output format, and compare multiple strategies in one run. It…
This research summary tests whether splitting stock volatility into components yields useful selection signals from high-frequency returns. The reported system-versus-idiosyncratic volatility split performs poorly at the one-minute sampling interval; its…
The document explains why MetaTrader’s TimeGMT function can give misleading results in the strategy tester: there, it matches simulated trade-server time. It describes a library that estimates the broker’s GMT offset from historical hourly bars and subtracts…
This code module implements three neural-network architectures that could be applied to quantitative prediction tasks: a feed-forward multilayer perceptron, an LSTM-based recurrent network for sequential inputs, and a Pi-Sigma network that multiplies…
This stock-selection example screens within the metaverse theme for shares that had a limit-up event during the prior twenty-five days and were marked as controlled by major funds on the previous day. The article presents these conditions as a way to find…
This expert advisor uses the Color Schaff Trend Cycle indicator to form trades when its histogram breaks through configured overbought or oversold levels. Signals are taken after the bar closes, so the method waits for confirmation rather than acting on an…
The article describes a stock selection rule requiring turnover between 3% and 12%, appearance on the previous day’s trading leaderboard, and an opening price near the 10-day moving average. Its formula example defines “near” as within 2% of that average.…
This report examines listed Chinese securities firms as a cyclical, high-beta equity sector and presents a securities-company index as a way to track them. It describes the index as market-cap weighted, concentrated in its largest constituents, and composed…
The document describes an Expert Advisor built around the T3_TRIX indicator. It can trigger trades when the indicator histogram changes direction, crosses the zero line, or when the signal-line cloud changes color; an input selects the entry mode. The EA…