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.
14 documents
The Range Action Verification Index (RAVI) is described as a trend-detection indicator based on the percentage difference between current and past prices. The document gives threshold-crossing rules attributed to its developer: an upward cross of a 3%…
This note proposes screening Chinese metaverse-sector equities using two signals: rank by the day’s opening-auction value and retain the leading five, then require at least two limit-up events within a stated 500-day lookback. It includes platform-specific…
The document contains reusable strategy calculations for price returns, volatility scaling, trend following, and MACD signals. Its intermediate trend strategy combines the signs of one-month and one-year returns, weighted by a parameter, and applies that…
This Chinese equity screening proposal combines three conditions: daily price amplitude above 1%, a dividend ratio above 25% for 2019, and a 15-minute MACD histogram that is shortening while below zero. The rationale is to find volatile shares with a history…
This code excerpt implements neural-network components for a momentum forecasting model based on a temporal fusion transformer design. It includes feed-forward layers, gated linear units, gated residual networks with skip connections and normalization, and…
This note proposes a short-term Chinese equity screen that selects stocks with a price amplitude above one, an appearance on the prior day's trading list with buying greater than selling, and a rising DEA indicator. The rationale is to combine elevated…
This data-preparation workflow builds model inputs for a momentum strategy from asset closing prices. It clips prices using bounds based on an exponentially weighted mean and standard deviation, derives daily returns and volatility, and creates a next-period…
This code describes a deep learning approach for turning sequential market features into position signals. Its example model uses an LSTM layer followed by dropout and a time-distributed output constrained through a hyperbolic tangent activation. Training…
This code manages backtest outputs for momentum experiments. It reads results from multiple train and test intervals, aggregates captured returns, and can rescale those returns to a target volatility. It calculates performance summaries that include return,…
This Chinese stock-selection note combines three filters: MACD above its zero axis, a 2021-to-2018 revenue ratio above 1.1, and a gain below 6% at 9:25. The rationale is to pair positive technical momentum and multi-year revenue growth with a limit on the…
This data-preparation module builds time-series inputs for a deep-learning momentum model. It reads close prices, clips extreme values using an exponentially weighted mean and standard deviation, then derives daily returns and volatility. The target is a…
The document implements an H-construction approach for analyzing price series, based on a cited study of statistical variability in spreads. It converts a series into Kagi-like turning points or Renko-like threshold steps. The H-inversion statistic counts…
The H-strategy uses Renko or Kagi turning points to study how far a price or spread typically moves before reversing. It defines an H threshold, marks extrema and the later times when a move of that size confirms a turn, then measures the count of reversals,…
This code describes a data formatter for a momentum model. It defines target returns, normalized returns over several horizons, MACD features, and optional change-point, calendar, and ticker identity inputs. It also assigns columns roles such as target,…