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 Expert Advisor strategy combines two indicator signals. ColorX2MA_Digit defines the slower trend direction, while ColorDM_361 identifies a change in the faster trend. It enters at bar close when the fast and slow directions agree and the fast trend has…
This Qlib documentation describes a workflow for generating, storing, training, and collecting multiple research tasks. A task can include a model, dataset, and recorded outputs. Task generators such as RollingGen can create tasks for different date…
This essay argues that traders can accelerate learning by studying experienced practitioners’ actual trade records and decision patterns instead of relying only on abstract explanations or repeated personal trial and error. It recommends choosing examples…
This article proposes a Chinese stock screen combining a morning-star candlestick pattern, daily amplitude above a stated threshold, market capitalization below a stated ceiling, and positive adjusted net profit. It presents the screen as a blend of…
The document describes an expert advisor that runs two independent trading systems based on BrainTrend2 and AbsolutelyNoLagLWMA indicators. Each system generates an entry signal when a bar closes and its indicator shows a trend change through a color change.…
The report examines how fundamental factors predict stock returns differently across groups defined by market capitalization, profitability, and volatility. It argues that factor weights should vary by group rather than applying one set of weights across the…
This tutorial develops a spot-style cryptocurrency grid strategy by extending a finite set of price levels as the market moves beyond its upper or lower boundary. It tracks the current and previous ticker prices to detect upward and downward crossings. At an…
This release note describes new features and fixes in OctoBot 1.0.4. Users can download strategies from OctoBot Cloud into a self-hosted bot, then configure them for different exchanges or assets and use the platform’s backtesting or strategy design tools to…
This document describes an Expert Advisor that makes trade decisions when the The_20s_v020 semaphore indicator displays an arrow with the appropriate direction and color. It requires the compiled indicator file to be installed in the platform’s indicator…
This module outlines an out-of-sample forecasting workflow built around Auto-ARIMA. It first applies an Augmented Dickey-Fuller test at a five percent significance level, repeatedly differencing the training series until the test indicates stationarity or a…
The document describes an Expert Advisor that generates a signal when a bar closes and the i4_DRF_v2 indicator histogram changes color. It therefore uses a confirmed bar-close signal rather than reacting to an unfinished bar. Running the advisor requires the…
This document lays out a sequence of practical exercises for learning quantitative trading with VN.PY. The projects cover market data retrieval and database storage, vectorized indicator calculations, CTA strategy development, cleaning futures data, and…
This Chinese-language research summary examines how differences between reported macroeconomic data and consensus forecasts may relate to returns in Chinese equities, bonds, and commodities. It compares forecast data sources, noting that Bloomberg records…
This Expert Advisor design runs separate long and short systems based on ColorSchaffJCCXTrendCycle signals. Each side has its own settings and magic number, allowing the trader to configure or test them independently. The document emphasizes that the two…
The proposed Chinese stock screen combines a weekly moving-average trend condition, a minimum price-range threshold, and the presence of an outstanding convertible bond name. The post also gives example formulas and a Python outline for filtering…
This reference describes a Python toolkit for calculating technical indicators and analyzing trading returns on pandas time series. Its functions cover lagged values, rolling standard deviation and simple averages, exponentially or linearly weighted…
The document explains Bayesian optimization as a way to search expensive black-box objectives, such as portfolio return or risk-adjusted performance. It describes using a Gaussian process as a probabilistic model: observations update the model’s posterior,…
The document proposes screening Chinese A-share stocks for a daily high-low range greater than one percent of the prior close, positive large-order net volume, and ranking by the day’s auction turnover to select the top five. It frames these conditions as a…
This community post reports a failure in a VeighNa CTA backtest on Windows with a Tushare data service. Historical one-minute futures data downloads successfully and the strategy loads, but the run fails when the backtesting engine calculates performance…
This article collects practical advice for building and debugging deep learning models, using a generative adversarial network for manga coloring as its motivating example. It recommends beginning with a small working baseline, visualizing predictions and…
The study outlines China’s convertible bond market and develops a screening factor intended to identify bonds with relatively low embedded-option valuations. It decomposes convertible bond value into a discounted bond component and an option component. Under…
The study examines timing the basis between Chinese equity indices and their futures, motivated by persistent futures discounts and uncertainty for market-neutral funds. To reduce the influence of carry components such as rates, dividends, and time to…
This Freqtrade strategy framework uses sets of generated buy and sell rules, called spells, assembled from technical indicators, operators, and numeric thresholds. Its documentation describes deriving the rules through hyperoptimization, then assigning…
This Qlib documentation explains why historical strategies need the versions of financial data that were available at each past decision time. Financial statements can be revised after publication; using only the latest value in a historical simulation can…