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 document describes a custom indicator that compares price swings with the Awesome Oscillator (AO) to identify potential bullish and bearish divergences. It presents a bullish case when price makes lower lows while the oscillator makes higher lows, and a…
This report summary examines whether Chinese public mutual funds’ past risk-adjusted performance predicts future performance, with fund selection and fund-of-funds investing as the motivation. It evaluates managers using alpha from several asset-pricing…
This review describes a framework for separating portfolio returns into fundamental growth and changes in valuation. It applies the decomposition to value, momentum, quality, and a combined value-quality factor, using long-short portfolios formed from U.S.…
This review describes a framework for separating portfolio returns into fundamental growth and changes in valuation. It applies the decomposition to value, momentum, quality, and a combined value-quality factor, using long-short portfolios formed from U.S.…
This guide explains why a submitted end-to-end Transformer example can run out of memory before training or inference begins: the data-loading step materializes minute bars for many stocks across the full date range in one DataFrame. Although the eventual…
The Quick Fibonacci indicator derives retracement levels from the highest high and lowest low over a configurable lookback period. It plots the endpoints and intermediate levels at 23.6%, 38.2%, 50%, and 61.8%, along with trend lines connecting each extreme…
The document presents an implementation of John Ehlers’ Instantaneous Trendline, alongside a zero-lag exponential moving average. It estimates cycle phase from price-derived in-phase and quadrature components, adjusts phase changes for wraparound and extreme…
The document introduces AVL trees, a type of binary search tree that keeps the heights of each node’s left and right subtrees within one level of each other. It explains that this balance supports logarithmic worst-case lookup, insertion, and deletion, and…
This Chinese-language post describes an equity screen combining turnover, year-over-year net profit growth attributable to parent-company shareholders, and a ratio involving prior turnover, current auction volume, and previous volume. It selects stocks with…
Despite a title referring to Bollinger Bands, the body describes the Accumulation Swing Index (ASI). It outlines a calculation using open, high, low, and close prices, comparing the current bar with the previous bar. Intermediate terms measure price changes…
This tutorial outlines a preprocessing workflow for equity factor data. It filters out records without an industry classification, fills missing factor values with date and industry group means, and describes clipping outliers using percentile, standard…
This stock screen combines a turnover-rate band of 3% to 12% with an exclusion of Beijing-listed A shares and a parent-company net-profit growth condition. The final rule specifies year-over-year growth, on a trailing-twelve-month basis, above 20% and no…
This document is a job listing for a quantitative strategy researcher in Hangzhou. It outlines research responsibilities that include building quantitative models for financial markets, studying arbitrage approaches such as statistical and event arbitrage,…
The document discusses the prospects for quantitative investing in China after a period in which some quantitative private funds faced weaker performance and investor demand. It presents views from three investment firms: one frames market enthusiasm and…
This short BigQuant forum post shows an approach for visualizing correlations among several fields for a single Chinese stock. Its example queries a prefactor table for closing price, volume, and rolling turnover sums, retrieves the data as a dataframe,…
This tutorial illustrates how combining assets or strategies can smooth portfolio returns and raise the portfolio Sharpe ratio, even when individual components have weak risk-adjusted performance. It generates synthetic return series, builds equal-weight…
The document describes a script for comparing computer and terminal performance in MetaTrader 4 and MetaTrader 5. It combines 45 tests covering calculations, arrays, sorting, strings, procedural and object-oriented code, chart-object operations, canvas…
The article examines how training-window length can affect an AI stock-selection model. It compares longer historical samples with shorter windows using manual rolling training and a held-out backtest period. In the reported experiments, changing the…
The document introduces linear regression as a way to model the relationship between an explanatory variable and an observed value. In its trading example, the independent variable is the number of bars and the dependent variable is price. It describes…
This indicator tracks volume accumulated between price turning points identified by a ZigZag applied to closing prices. When it detects a peak or trough, it starts a new accumulation segment, records the segment’s direction, and draws a histogram whose…
The MA_Slope indicator represents the direction and strength of a moving average by comparing its current value with a value from a specified number of bars earlier. The user selects the moving-average period, calculation method, applied price, slope…
This brief discussion describes how to display a sector’s price-to-earnings ratio, using banking as an example. It points to a demonstration that builds an industry P/E using an arithmetic mean approach and notes that the calculation can instead use market…
The Average of ATR indicator compares the Average True Range with its moving average. Its suggested confirmation rule is to examine a price-action setup or act on an existing signal when ATR crosses above its average. The indicator presents this relationship…
This brief document introduces an implementation of John Ehlers’s FM Demodulation indicator, based on an article published in May 2021. It frames price movement as having an amplitude-modulated component associated with volatility and a frequency-modulated…