Skip to content

Knowledge library

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.

Quant Q&A
20,364 documents
SuperMind
12,226 documents
OKX Learn
8,431 documents
Strategy library
7,910 documents
MQL5 code base
7,090 documents
BigQuant
3,481 documents
Bitget Academy
3,298 documents
MQL5 articles
3,012 documents
TradingView scripts
1,976 documents
ProRealCode
1,507 documents
Deribit Insights
1,232 documents
Machine Learning for Trading
1,124 documents
arXiv papers
1,033 documents
Amberdata research
766 documents
FMZ forum
682 documents
FMZ digest
662 documents
vn.py community
560 documents
QuantInsti blog
511 documents
Galaxy Research
340 documents
QuantStart
246 documents
Stratmill research code
219 documents
Robot Wealth
195 documents
NautilusTrader
191 documents
Hummingbot docs
181 documents
Paradigm research
175 documents
Lumibot
164 documents
Kraken Learn
163 documents
Quant course library
157 documents
OctoBot
152 documents
Cryptohopper blog
144 documents
Systematic trading blog (Rob Carver)
132 documents
Qlib
116 documents
TqSdk
86 documents
Quantpedia
86 documents
Hyperliquid docs
79 documents
Freqtrade
68 documents
Hudson & Thames
62 documents
Awesome Systematic Trading
61 documents
backtrader
54 documents
vn.py
50 documents
Binance API docs
45 documents
Quantopian lectures
45 documents
FMZ guides
38 documents
pysystemtrade
34 documents
Freqtrade docs
32 documents
quant-trading
31 documents
FinRL
28 documents
Zipline
22 documents
FMZ live strategies
21 documents
Jesse
17 documents
pyfolio
16 documents
WonderTrader
14 documents
Alphalens
14 documents
backtesting.py
11 documents
Technical Analysis
9 documents
QTPyLib
8 documents
Lumibot strategies
7 documents
QuantRocket
7 documents
Awesome Quant
1 documents

Search the library

64 documents

vn.py community

This brief forum exchange answers whether VeighNa, also known as vn.py, requires Tushare as the sole source of historical A-share data for backtesting. The response says the framework supports multiple data services and points readers to its documentation…

China marketsEquitiesBacktesting
vn.py community

This release overview describes VeighNa 4.0 and its new vnpy.alpha module for developing machine-learning, multi-factor strategies. The module is organized around feature datasets, model training, strategy research, workflow management, and example…

Machine learningFactor investingEquitiesBacktesting
vn.py community

A VeighNa forum user asks how to keep a displayed value C synchronized with inputs A and B. C is initially calculated as the difference between A and B, but editing either input leaves C at its previous value. The user also wants C to remain editable like…

Equities
vn.py community

The post asks why Alpha158 labels use different forward-return horizons in two implementations. It compares a label spanning the close at T+1 to the close at T+3 with a Qlib label spanning T+1 to T+2, then relates those choices to China’s T+1 stock-trading…

China marketsEquitiesBacktestingMachine learning
vn.py community

This forum exchange clarifies a difference between ScriptTrader and VeighNa’s CTA strategy module. A user asks whether ScriptTrader supports stop orders, noting that the module is described as supporting multiple exchanges and instruments, hedging between…

ExecutionRisk managementFuturesEquities
vn.py community

This Chinese research summary examines whether intraday data can support sector rotation signals, focusing on realized skewness and the share of volatility attributable to downside moves. It describes constructing industry level factors inspired by high…

China marketsEquitiesHigh-frequency tradingVolatility
vn.py community

This post describes adapting VeighNa to use the GoldMiner market data service as a source of historical bars. It outlines the author's account of the free tier's available history, then highlights integration details: mapping bar intervals, reversing the…

FuturesEquitiesExecution
vn.py community

The article describes an integrated order flow imbalance factor built from changes in bid and ask quantities across five limit order book levels. It explains how each level’s imbalance can be normalized by typical depth, then combined with principal…

EquitiesMarket microstructureStatisticsFactor investing
vn.py community

This short forum exchange concerns choosing a broker or trading counter for automated stock trading in China. One participant reports that a broker had announced it would stop allowing personally developed software to connect through its CTP interface.…

EquitiesChina marketsExecution
vn.py community

This forum thread discusses installing vn.py on an Apple Silicon Mac, with a particular focus on launching its CTP gateway. Participants point to the gateway project's installation guidance and identify Python environment conflicts as one possible cause. One…

EquitiesExecutionChina markets
vn.py community

The article explains a WebSocket subscription workflow for delivering minute-level Chinese A-share market data to a VN.PY strategy. It contrasts a persistent server-push connection with repeated HTTP polling, then outlines connecting to a data source,…

EquitiesChina marketsExecutionMarket microstructure
vn.py community

This forum exchange clarifies a VeighNa configuration message seen when running the platform from PyCharm. A participant explains that the missing data-service configuration notice does not by itself prevent the application from running. However, attempting…

EquitiesFutures
vn.py community

This brief Chinese-language forum exchange asks whether a VeighNa strategy can subscribe to hundreds or thousands of stock instruments at once. A respondent says that subscribing to the whole market is possible, while the number of contracts a particular…

EquitiesExecution
vn.py community

This guide explains how to organize data for VeighNa’s AlphaLab research workflow. It describes the roles of its directories, daily and minute bar files, index constituent records, and contract settings, then shows how preparation notebooks supply data…

EquitiesFactor investingBacktesting
vn.py community

The forum exchange answers a practical question about how VeighNa Trader discovers a custom strategy when launched through its example runner. The response says to find the default runtime directory in the trader window’s title bar, then put strategy files…

Equities
vn.py community

This post presents a Chinese equity screening idea that combines a MACD value above zero with year-over-year net profit growth between 20% and 100%, framed around 2021. It explains the intent as pairing price momentum with a fundamental growth filter. The…

China marketsEquitiesMomentumTechnical indicators
vn.py community

A brief VeighNa forum exchange describes an order-timing problem in a strategy that constructs daily bars from intraday data. The user says the daily bar is completed at the 3 p.m. close, after which an order submitted by the strategy is canceled. They ask…

EquitiesExecutionMarket microstructure
vn.py community

This forum exchange explains a common execution issue in daily-bar backtests. A trader submits a sell order using the current bar’s closing price, but the order is evaluated for execution on the following day. Since the next opening price may differ from the…

BacktestingExecutionEquities
vn.py community

This tutorial explains how VeighNa’s backtesting engine replays historical daily bars to evaluate an equity strategy. It walks through configuring instruments, interval, dates, and initial capital; attaching a strategy and dated signal table; loading data;…

EquitiesBacktestingExecutionRisk management
vn.py community

The document describes a Chinese A-share screening rule for main-board stocks. It selects shares with turnover between 3% and 12%, a circulating market value between 5 billion and 10 billion yuan, and weekly MACD above zero. It explains that the screen…

China marketsEquitiesTechnical indicators
vn.py community

This event outline introduces advanced FinRL development topics, including the FinRL-Tutorials project, reinforcement-learning portfolio allocation, stock trading in China’s A-share market, and ensemble strategies. It distinguishes portfolio allocation from…

Machine learningEquitiesPortfolio constructionBacktesting
vn.py community

This forum post discusses a multi-timeframe CuatroStrategy implementation. Its five-minute handler updates a bar manager, waits for both five- and fifteen-minute data managers to initialize, then uses RSI and Bollinger Bands to place stop entry orders in the…

EquitiesTechnical indicatorsTrend followingVolatility
vn.py community

The report examines how factor evaluation can guide factor inclusion and, especially, factor weights in a multi-factor return model. It argues for evaluating single factors through optimized portfolios with controlled risk exposures, aiming to make measured…

EquitiesFactor investingPortfolio constructionRisk management
vn.py community

This brief forum exchange answers how to fill in the vt_symbol field when adding a strategy in VeighNa. The reply gives two examples of the required convention: a futures contract identifier paired with its futures exchange suffix, and a stock code paired…

FuturesEquitiesExecution