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 explains how to use ThetaData as a historical data source for LumiBot backtests covering stocks and options, as well as other asset types. It supports minute and daily bars directly; hourly bars can be built from minute data. Downloaded data is…
This post outlines a China A-share screening rule for stocks classified in the metaverse sector. It first describes selecting names with prior-day turnover above a threshold and positive institutional activity, then gives a final rule using prior-day…
This post reports a suspected mismatch in BigTrader v35 minute backtests after an ETF share split. The author says the strategy-visible position fields—quantity, cost price, last price, and market value—appeared to retain their pre-split values, while a…
The document presents a Chinese equity screening rule that selects stocks with amplitude above 1, circulating market capitalization above 10 billion yuan, and at least two limit-up events over the prior 500 days. It frames the combination as a way to find…
This BigQuant assignment asks learners to modify a classic quantitative strategy by adding an indicator, then search across hyperparameters. It directs them to collect the historical performance curve for every parameter configuration into a data frame, plot…
This post describes a EUR/USD and GBP/USD strategy that seeks entries during pullbacks within an established intraday trend. It uses 5-period and 8-period Wilder averages alongside an 89-period simple average. During an early-day window, the averages must be…
The document proposes a Chinese equity screen based on a daily price range above a stated threshold, a product combining the prior day's turnover rate with the ratio of current auction volume to prior volume, and a closing price below 12. It frames these…
The document describes a multi-asset cryptocurrency strategy that allocates capital across selected USDT pairs and places staged buy orders as prices fall through preset levels. Each level uses a specified share of the amount assigned to that asset.…
The tutorial describes a faster backtesting approach that precomputes fill conditions across intervals, reducing the need to replay every depth update or estimate queue position. It retains feed and order-entry latency but omits order-response latency.…
This research summary proposes measuring whether trading in a stock is unusually one-sided. It classifies five-minute candles by their bodies as consensus or non-consensus activity, then measures consensus volume as a share of daily volume. Splitting that…
This code example outlines a vn.py workflow for backtesting an ATR-RSI strategy on a Chinese equity index futures contract. It configures the instrument, minute interval, historical dates, commissions, slippage, contract size, tick size, and starting…
This document describes an indicator that measures the size of recent highs and lows over configurable lookback periods, using a calculation likened to a price channel. Its histogram separates high-range readings from low-range readings and colors bars…
This literature summary describes research on the historical characteristics and investment relevance of sentiment signals drawn from news and social media over a 20-year period. The underlying study compares the information in the two source types, examines…
This proposed GBP/USD strategy uses four-hour bars and seeks reversals around a 40-period exponential moving average. It adds a 30-period Fractal Dimension Index filter, permitting entries only when the calculated value is below 1.5. The entry conditions…
This A-share selection rule combines three conditions: a daily range above 1%, weekly MACD above zero, and at least two limit-up events within a 500-day lookback. The document presents repeated limit-up moves as a possible sign of strength, with the range…
This research summary surveys dynamic allocation methods for equity style factors. It organizes the approaches by whether they use return information, risk information, or both, adapting methods originally used in broad asset allocation. The study first…
This document explains how to combine absolute, time-series momentum with relative, cross-sectional momentum in a multi-asset portfolio. It describes a unified portfolio framework that treats each pair of instruments as a relative-momentum opportunity,…
This report compares several Chinese language models as assistants for discovering equity liquidity factors over a specified historical period. Each model proposes data inputs and a formula built from trading volume, turnover, amount, or price. The author…
This article proposes six checks to run before deploying a strategy that has performed well in historical backtests. It recommends perturbing data with delays, missing observations, and outliers; scanning core parameters for broad regions of acceptable…
This brief Chinese-language forum answer addresses how to use the data parameter in a quantitative trading workflow. It notes that scheduled functions receive both data and context as inputs, pointing readers toward the platform documentation for details.…
This document describes an event-driven long strategy that combines corporate repurchase announcements with upcoming earnings dates. It screens US-listed stocks, excludes the smallest market-cap quartile, and looks for buyback announcements of at least 5% of…
This study proposes a stock-selection factor derived from intraday volume patterns. It defines a daily volume “tide” by smoothing minute-level volume with a nine-minute neighborhood, locating its peak, and identifying low-volume points before and after that…
This indicator description presents a version of the instantaneous trend line that uses self-adjusting levels to filter signals. The stated motivation is that relying directly on the trend line’s slope can produce too many signals; adaptive levels are…
This report examines industry exposures in an existing multi-factor stock-selection portfolio, tests how the model performs across sectors, and constructs industry-neutral long and short portfolios. It identifies sectors where the model appeared unsuitable…