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 an indicator that expresses current Average True Range as a percentile rank within its own recent history. It calculates ATR using a 20 period window, compares that reading with readings from the preceding 200 periods, counts how many…
The document asks why a historical price-to-earnings series for China’s pharmaceutical industry differs from a series calculated in code. The example selects constituents classified under the 2021 Shenwan industry scheme, joins them to daily stock valuation…
The article explains why a strategy can make money without winning more often than a coin toss. It contrasts high-win-rate approaches, which seek frequent small gains, with high reward-to-risk approaches, which tolerate more losing trades in pursuit of…
This research review examines whether a US equity mutual fund’s performance relates to other funds following its trades. It extends a herding measure to classify funds by how strongly their purchases or sales are followed in later quarters, then compares…
This review summarizes research on U.S. actively managed equity mutual funds during the acute COVID-19 market crisis. The study compares net fund returns with broad-market, style-matched, prospectus, and factor-model benchmarks, and examines investor flows…
This stock selection recipe combines three filters: a dividend payout ratio above 25% for 2019, a weekly five-period moving average crossing above the ten-period average, and ranking by descending capital-flow strength. The post describes capital flow using…
This research article examines whether lending activity in USDC, USDT, and DAI helps forecast Ethereum volatility. It describes time-series autocorrelation and partial autocorrelation analysis, then uses Granger causality tests to assess whether past…
This document introduces core combinatorics concepts through examples involving trading signals. It distinguishes combinations, where only the selected elements matter, from arrangements, where their order matters. It also describes versions that allow…
This overview compares common machine learning methods by their assumptions, strengths, and limitations. It introduces the bias variance tradeoff and explains how model complexity can lead to underfitting or overfitting. It then surveys naive Bayes, logistic…
This community thread discusses missing log output when running VeighNa version 4.10 in a VS Code environment, while version 3.94 reportedly logs normally in the example setup. Participants suggest checking whether the launch directory changed and whether…
The document describes pure factor portfolios as a way to test whether a given equity factor has explanatory or investment value while controlling exposure to other factors. A pure portfolio is constructed to have unit exposure to the factor under…
This short project note outlines a workflow for preparing data and fitting a predictive model. It divides SQL data construction into a base dataset, a normalized dataset, and a final feature-and-label stage. The note mentions cross-sectional factor ranking…
A Chinese-language forum exchange discusses long decimal values appearing in trading system displays, including a silver futures sell-to-open price. One participant attributes the extra digits to Python floating-point representation and suggests rounding…
This document defines an abstract data-formatting interface for experiments using the Temporal Fusion Transformer (TFT). Dataset-specific formatters are expected to define column names and roles, fit scalers, transform features, reverse prediction…
This report applies the Fama-French three-factor framework to China’s A-share market, examining monthly evidence from April 2010 through October 2022. It describes the market excess return factor, SMB for company size, and HML for book-to-market, with SMB…
The document compares simple systematic strategies, such as indicator rules applied to liquid developed markets, with advanced approaches that use specialist market knowledge, statistical testing, rigorous portfolio construction, and less liquid instruments.…
This Chinese equity screen combines three conditions: at least five moving averages clustered together, a stated concentration measure below 20%, and at least two limit-up sessions during the prior ten days. The post frames the combination as a way to find…
The notebook estimates crop prices from Malaysian GDP, population, and crop production data. It fits ordinary least squares models for comparison, then uses quadratic optimization to constrain the non-constant coefficients to be nonnegative. Production…
The post proposes screening Chinese stocks for daily turnover between 3% and 12%, year-over-year growth in net profit attributable to parent-company shareholders above 20% and at most 100%, and floating market capitalization between 5 and 10 billion yuan. It…
This report introduces gcForest, or multi-grained cascade forest, as a tree-based deep learning model proposed as an alternative to deep neural networks. It argues that the method may suit financial data because it is described as more robust to…
This report introduces an early-stage study of market microstructure signals in the IF equity index futures contract. It proposes examining the difference between midpoint and trade-price log returns, quoted depth, large trades, and signed volume. The…
This indicator plots projected support and resistance lines from the latest three swing highs and lows of a chosen indicator. Its example uses a smoothed RSI, but the indicator input can be replaced. Pivot detection is adjustable by changing how many bars on…
This ProRealTime indicator evaluates price performance between user-selected start and end dates. It calculates compound annual growth rate (CAGR) from the two closing prices and the estimated elapsed years, scans intervening bars for the largest percentage…
This Chinese equity selection rule screens companies classified in the metaverse industry. It requires the previous day’s actual turnover rate to fall between 3% and 28%, and year-over-year growth in net profit attributable to parent-company shareholders to…