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 compares six programming-language options for building quantitative trading strategies: visual programming, EasyLanguage, Python, MATLAB/R, C++, and Java/C#. It evaluates them by capability, speed, extensibility, and learning difficulty, then…
The strategy compares two portfolios drawn from a basket of cryptocurrencies: one is rebalanced daily to equal weights, while the other starts equally weighted and is left to drift. It takes a long position in the rebalanced portfolio and a short position in…
This document describes an automated strategy that trades changes in the KWAN_RDP indicator’s direction. A signal occurs when the indicator changes color at a bar’s close, providing the entry trigger for the expert advisor. The indicator file must be…
The proposed rule buys Gold Mini on Friday afternoon and closes the position later that day. The description identifies the instrument as Gold Kasse Mini, gives a one-hour timeframe, and says the strategy was tested with IG Markets data dating from 2006. The…
This expert advisor runs two NRTR signal systems, one for long positions and one for short positions. Each side has its own settings, including separate identifiers, position sizing, and switches for allowing entries and exits. The separation lets a trader…
The document presents a daily Nasdaq adaptation of the Universal XBody Strategy and gives optimized settings: a lookback period of 878, mode 1, positive signal orientation, and filters of 41 and 0. It calculates each candle’s body as close minus open, takes…
This guide explains how to run trading strategies against historical market data in OctoBot. The workflow is to select a profile, download data for the desired pairs and timeframes, run the backtest, and review the report. It describes how starting funds and…
The document explains a forex scalping system based on price briefly crossing a confirmed swing high or low, then closing back through it. The system marks the sweep candle as a potential order block and waits for a later candle to break back through its…
The author recounts moving from manual trading to automated strategies. An early setup sent TradingView entry signals to FMZ for take-profit and stop-loss handling; the author reports that unreliable signals, unstable profits, platform rental, and trading…
The document describes a forex strategy that combines the Awesome Oscillator, Accelerator Oscillator, and Parabolic SAR. It enters long after price crosses above the SAR and both oscillators rise, or short after price crosses below the SAR and both fall. A…
The discussion describes a proposed rolling evaluation in which training and testing periods are kept separate. Its example uses successive annual training windows and test windows offset into later years, with each test period’s results concatenated to form…
The post proposes a Chinese stock-selection screen combining price movement, trading activity, and company size. Its stated rules require amplitude above 1, a product involving the previous day’s turnover rate and today’s auction volume relative to the prior…
The post describes a strategy adapted from another approach and characterized by its author as a moving-average method that takes long positions. The author reports a four-year backtest with a total return of 120 times the starting value and a maximum…
The example builds a single-stock daily strategy from trend and momentum conditions. Entry requires the 21-period simple moving average to exceed the 60-period average, price to be above both averages, and daily and weekly MACD histograms to be positive. It…
This article offers a checklist for choosing strategies from a trading community. It first asks investors to set their capital, acceptable drawdown, and return expectations, then distinguishes conservative from aggressive choices. The conservative profile…
This document outlines a common set of measures for evaluating trading performance: cumulative and annualized returns, annualized volatility, the Sharpe ratio, and maximum drawdown. It gives mathematical definitions for the return, volatility, and Sharpe…
This report studies whether stocks that suffer sustained, sharp declines later rebound, and how to identify such episodes. It uses rolling-window local extrema with a 15-period parameter to mark turning points, then applies pattern conditions to select 2,048…
This article outlines an approach to improving a random forest stock-selection model through factor screening and parameter experimentation. It first limits the stock universe by excluding firms under special treatment and delisted stocks. Candidate…
This document summarizes experiments with a convolutional neural network (CNN) trading model called Deep Alpha. It reports that a seven-layer version performed better than a two-layer version in a same-period comparison, which the authors attribute to…
This Qlib documentation explains a workflow for preparing financial data for quantitative research. Users convert market data into Qlib’s binary format, derive features with its expression engine, apply more complex transformations through data handlers, and…
The document describes a short-selling rule set for equities and indices. It opens a short position when the close is below the 200-day moving average and closes have risen for four consecutive days. The position is exited when the close falls below the…
This expert advisor concept uses candle size as a trade filter: when a candle exceeds a configurable pip threshold, it opens a buy trade. If that trade loses, the next trade uses a larger lot, with the scaling factor controlled by the user. The author frames…
This overview introduces rules-based crypto trading and distinguishes discretionary decision-making from systematic strategies that use indicators, algorithms, or automation. It explains dollar-cost averaging as recurring purchases at fixed intervals, then…
This report compares AdaBoost, gradient boosting decision trees, and XGBoost as tools for selecting Chinese equities from factor data. Its workflow covers feature and label preparation, preprocessing, in-sample fitting, cross-validation, and out-of-sample…