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
The article explains how to calculate the Resistance Support Relative Strength (RSRS) market-timing indicator more quickly. RSRS fits a rolling regression of highs against lows; its slope is used as a measure of the relationship between resistance and…
The Freedom of Movement oscillator is presented as a way to measure price movement while removing the trend component. It standardizes a volume-to-movement measure against its own moving average and standard deviation over a configurable period. Its inputs…
This document describes an indicator that averages the outputs of 18 moving-average methods into one value. It uses two inputs: the calculation period shared by the averages and the price series applied to them. The listed methods include simple,…
The document introduces an indicator concept that treats price movement as speed: distance covered per unit of time. It then proposes averaging a set of speed observations with the arithmetic mean, calculated by summing the observations and dividing by their…
This expert-advisor description outlines a tick-driven scalping system that compares short-window price returns with a rolling statistical baseline. It enters only when the move’s z-score exceeds a configurable threshold, then lets the user choose either…
This implementation describes a pairs-trading method based on modeling the log price relationship between two stocks as an Ornstein–Uhlenbeck process. It constructs the spread as the difference between the stocks’ log prices, fills missing observations…
The Deviation Trend Profile combines a simple moving average (SMA), ATR-scaled bands, trend-turn markers, and a histogram of closing prices. It calculates an SMA and a 200-bar ATR, then plots three deviation levels above and below the average using…
The document presents exchange limit order data as a way to monitor large crypto traders. It distinguishes resting limit orders from market orders, then describes tracking unusually large orders by price, size, direction, and duration. Its central premise is…
This document introduces a pivot indicator that uses high and low prices together with left- and right-strength parameters. It describes locating local lows and highs within a rolling window whose size depends on those settings, then comparing how recently…
This article discusses recruiting and interviewing in China’s quantitative trading industry. It argues that candidates need not come from finance: people trained in fields such as chemistry, mathematics, statistics, and computer science may bring useful…
The document describes a momentum ratio oscillator that compares a current value with a previous value and smooths the resulting series through multiple exponential moving average calculations. It says the repeated smoothing creates a step-like response when…
The document presents a variant of RSI that uses ADX to attenuate overbought and oversold readings when trend strength is rising. Its motivation is that classic RSI reversal signals can be unreliable in strong trends, while RSI is described as more useful in…
JMACandle_Chl is a chart indicator that displays two colored channels around indicator candles. The channel boundaries are based on standard deviations calculated from the candles’ high and low values. Its configurable inputs include a smoothing method and…
This brokerage report reviews Chinese equity style behavior during the week of April 13–17, 2020, then outlines a style outlook using macroeconomic conditions, historical calendar patterns, cross-sectional dispersion, fund flows, valuations, and macro event…
This article explains why a strategy with a positive arithmetic average return can still lose money when returns compound. It illustrates the point with alternating gains and losses, showing that the geometric return better reflects long-run account growth.…
This article describes an equity selection approach centered on smaller profitable companies listed on the Shenzhen main board. Its stated filters combine stronger money-flow readings with moderate price-to-earnings and price-to-book ratios, a market…
This technical reference implements the bivariate Joe copula, a dependence model with a parameter theta in the range from 1 upward. It provides formulas for the copula cumulative distribution, density, and conditional probability, along with a sampling…
This stock-selection rule filters for securities with turnover rates in a specified range, codes beginning with 60, and an area field that does not identify Beijing. The accompanying rationale is that the turnover range may help focus on stocks with a…
This indicator plots three standard deviation channels around price using a configurable lookback period. Its inputs let the user set the number of candles used in the calculation, choose the deviation levels for each of the three channel bands, and shift…
The article presents a quantitative way to compare two candlestick price series, motivated by the technical-analysis idea that historical price patterns may recur. It defines each candle by its open, high, low, and close, and notes that comparisons depend on…
This document describes a recursive moving average attributed to Dennis Meyers and outlines a trend oscillator formed by comparing that average with an exponential moving average of the same period. The proposed signal comes from watching for changes in the…
This implementation builds a committee of neural network regressors, trains each member on the same training data with validation data and early stopping, then averages their predictions. The model class and parameters, committee size, training epochs, and…
This introductory overview explains ten practical principles of machine learning. It emphasizes that data quality and representativeness matter more than algorithmic complexity, and recommends simpler models when data is limited to reduce overfitting. It…
The article describes inferring a fund’s constituents and weights from its total value time series. It compares Extended Linear Cloning (ELC), which uses regression coefficients as asset importance scores and retains the highest scoring candidates, with…