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.
21,023 documents
This tutorial explains how to use Python notebooks for quantitative research, from collecting and saving exchange candlesticks to plotting price and trading-activity measures and testing strategies across symbols. It demonstrates paginated retrieval of…
The article presents a notebook-based workflow for quantitative research: obtain exchange candlestick history through an API, store and inspect it with pandas, plot price and trade-flow measures, and build a Python backtest for multiple spot or perpetual…
This research summary examines Shanghai–Hong Kong and Shenzhen–Hong Kong Stock Connect, comparing northbound and southbound trading and describing the traits associated with northbound holdings. It reports that flows did not reliably anticipate market…
This module constructs a continuous futures series by identifying contract roll dates and calculating the price gap between the expiring contract and the next contract. It accumulates those gaps through time and can align the adjusted series at its end. A…
This Qlib documentation describes visual reports for evaluating intraday portfolios and prediction models. Portfolio reports display benchmark and portfolio cumulative returns, returns with and without transaction costs, turnover, drawdowns, and cumulative…
The Simple Decycler adapts John Ehlers’s high-pass filtering method to identify broad price trends while reducing short-wavelength fluctuations. It calculates a high-pass filter from the price series and subtracts that output from price, leaving a smoothed…
This document outlines an event-driven study of how MSCI inclusion announcements affected the prices of Chinese A-shares. It describes estimating CAPM parameters from a historical period, using those parameters and subsequent market index returns to…
This tutorial compares three ways to train an XGBoost model for stock selection: ranking securities by a score, classifying outcomes into categories, and predicting a numeric target through regression. It frames these choices within a broader modeling…
This tutorial compares three ways to train an XGBoost model for stock selection: ranking securities by a score, classifying outcomes into categories, and predicting a numeric target through regression. It frames these choices within a broader modeling…
The document explains the Crank–Nicolson implicit finite-difference scheme for solving the one-dimensional heat equation. It contrasts this approach with an explicit method that requires small time steps, describing Crank–Nicolson as averaging spatial…
This document describes a MetaTrader 5 class for rebuilding closed trades from their opening and closing deals in account history. The history is selected over a time range and organized by close time; callers can then enumerate reconstructed trades or…
This tutorial explains how to use Seaborn to explore financial data through matrix plots, plot grids, regression plots, and style settings. It uses stock financial statement data to demonstrate correlation heatmaps, including annotations and color maps, and…
This Chinese-language question and answer explains why a strategy’s apparently strong later years in a long backtest may not reproduce the same pattern when tested over those years alone. It identifies several possible causes rather than prescribing a single…
This document describes a simple indicator that expresses an asset’s recent high-low price range in points. For each averaging period, it sums the maximum prices and subtracts the sum of the minimum prices; the result is averaged using a selectable…
The page reports a user’s concern that the Chinese stock 600256 had incorrect values for the total-liabilities factor fs_total_liability_0 over a historical interval in 2021. The user says values for other periods agreed with Eastmoney data, while the…
The post questions whether the minimum option price checks used before implied volatility calculations are correct in the Black–Scholes and Black–76 models. It observes that the two implementations use the same expressions, even though Black–76 uses a…
This report introduces a quantitative research approach that combines behavioral finance with trading indicators. It centers on George Soros’s theory of reflexivity and the author’s use of volume measures, with the stated aim of developing an indicator…
This analysis classifies bars by whether their highs and lows rise or fall relative to prior bars, then splits each configuration by candle color. The resulting eight groups cover rising-range and falling-range patterns, wider-range engulfing bars, and…
The article tests whether a convolutional neural network can classify stock direction from chart-like images generated from OHLC data. Each sample uses 32 time steps, normalized to a 128-by-128 binary image: groups of columns mark open, high-low range, and…
This forum post raises an implementation question about deploying BigQuant StockRanker models for live trading through a brokerage server. The author believes StockRanker includes a gradient boosting decision tree model and asks whether deployment transfers…
This indicator description defines a moving average built from Heiken Ashi candle values. It exposes two settings: the calculation period and the averaging method. First, it calculates a moving average of the Heiken Ashi close; it then applies the same…
This indicator measures weekend price gaps for a selected instrument and timeframe to assess whether fading a gap may be viable. It divides observations into recent gaps, the last twelve months, and the full available history. For each period, it reports gap…
The report describes a CTA approach for Chinese stock index futures that combines weekday return patterns with intraday effects. Its analysis notes higher return probabilities overnight and during the first half hour after the open, and different weekday…
This developer note explains two ways to inspect and work with a trading bot’s strategy tests. It says historical candles collected for backtesting are stored in SQLite files, which can be opened in a database browser to examine the available market data.…