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 document explains a composite band indicator built around a linear regression curve. Unlike Bollinger Bands, which are commonly centered on a moving average and scaled by price variability, these bands use estimates of regression error. When prices track…
This indicator description explains a visual method for locating support and resistance from ZigZag turning points. Low pivots are used to mark support, while high pivots mark resistance. Users can adjust the analysis lookback and the ZigZag depth,…
This research summary examines whether analyst earnings forecast errors can help select stocks. It reports that realized forecast errors are strongly negatively associated with subsequent returns: stocks with smaller errors performed better in the described…
The document describes a Chinese stock selection screen combining turnover, parent-company net profit growth, market capitalization, and a non-loss condition. It selects stocks with turnover between 3% and 12%, year-over-year net profit growth above 20% and…
This document proposes a Chinese equity screen for stocks associated with the intelligent robotics concept. It requires the intraday high-low range, measured relative to the low, to exceed 1%, and float market capitalization to fall between 5 billion and 10…
StockRanker is a tree-based learning-to-rank tool for ordering stocks from supplied features. Its listwise approach optimizes the quality of a stock list’s ranking, and the guide connects the method to the RankNet, LambdaRank, and LambdaMART line of work.…
This document describes an indicator that uses price action and volume to label sixteen Wyckoff events and classify recent activity as accumulation, distribution, or neutral. It detects events from rolling highs and lows, volume compared with its average,…
This MetaTrader 5 indicator adapts an earlier MetaTrader 4 tool that searches price history for candle sequences resembling a selected recent pattern. It uses dynamic time warping (DTW) to identify candidate matches and presents possible future price paths…
ColorMFI_X20 is a chart indicator that displays twenty Money Flow Index lines in one window, using sequential periods that begin at a configurable starting period and advance by a configurable step. Each line can be colored according to its position relative…
The document identifies logarithmic Garman–Klass volatility as one possible method for estimating volatility. It offers no derivation, formula, input requirements, comparison with other estimators, or empirical results, so it serves only as a brief pointer…
This document describes a modified variable moving-average indicator that can replace its averaging method, display the latest value as a price label, and round channel levels to a chosen number of digits. Its main analytical feature is a three-level…
The article explains how to inspect market-order results from a simulated BTC/USDT account using an exchange debugging tool and the Wex order history. In its examples, the standard average-price field is zero, while the first fill detail contains the…
The document explains a correlation indicator for comparing price changes in two symbols. It describes values from positive one to negative one: positive values indicate prices tending to move together, negative values indicate movement in opposite…
This analysis examines whether unusually strong net fund flows coincide with investors switching between small-cap and large-cap equity styles. It defines net inflow by subtracting active selling from active buying across large, medium, and extra-large…
This Chinese stock screen selects shares with turnover between 3% and 12%, first-level bid volume greater than first-level ask volume, and a listing date more than ten years earlier. It then takes up to 30 names, with the formula example also restricting the…
FreqAI is presented as an open source framework for training machine learning models to forecast market targets from user defined indicators. Users supply features and future looking labels; the framework trains a model for each listed trading pair and…
This document presents a chart indicator that draws vertical lines when the bar series crosses calendar boundaries. Separate display switches control daily, weekly, monthly, quarterly, and yearly markers, with distinct colors and line styles used to…
This report summarizes tests of equity factors across industries, covering cash flow, valuation, company size, momentum, liquidity, volatility, beta, and alpha. It compares factor performance using portfolio net value and ranking differences, and discusses…
The author argues that strategies depend on market behaviors that are not stable over time. Arbitrage is presented as relying on price differences between venues tending to converge; trend following, grid trading, martingale approaches, and news trading each…
The document explains an indicator that applies Ehlers’ Fisher Transform to the Chaikin Oscillator, which tracks changes in accumulation and distribution using bar closes and volume. The transform normalizes the oscillator over a rolling range and expands…
This function creates a synthetic binary classification dataset for studying feature importance and redundancy in an asset-management machine-learning context. It first generates informative and noise features, then constructs additional redundant features…
This review describes a model in which equity factors move through normal conditions, periods of value weakness, and subsequent reversals. The value drawdown may reflect a rally in growth stocks or a collapse in value stocks; reversals then differ according…
This introductory explanation asks why variance squares deviations from the mean and whether raising deviations to another power would work instead. It uses small sets of shooting scores to show that equal averages can conceal different levels of…
The Channel Balance indicator measures where the median price, defined as the average of the high and low, sits within the highest-to-lowest price range over a chosen period. It first normalizes that position: subtract the period low from the median price…