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.
79,386 documents
This Chinese stock selection strategy combines four filters: daily high-to-low amplitude above 1%, a robot-related industry concept, circulating market capitalization below 10 billion yuan, and appearance on the previous day’s trading activity list. It also…
This document describes an expert advisor that trades signals from the MAOscillatorHist indicator. It enters a trade when the indicator histogram changes direction, with the signal evaluated at the close of a bar. The advisor depends on a compiled indicator…
This example implements a tick-driven futures or securities strategy using the wtpy framework. It estimates a theoretical price from the best bid and ask, weighted by the quantities resting on the opposite sides of the book, then compares that estimate with…
This Chinese-language post describes a short-term stock selection rule combining three filters: RSI below 65, share price below 12 yuan, and more than two limit-up sessions within the prior ten days. It frames the screen as a way to find relatively…
The document introduces tokenized equities as blockchain-based tokens representing traditional shares, exchange-traded funds, or other investments. It describes fractional ownership and broader geographic access as potential benefits, and says smart…
The article argues that trading researchers should judge machine learning papers by simplicity, reproducibility, and generality, alongside reported empirical results. A method that performs well on a benchmark may not transfer to financial prediction, and a…
This overview argues that no programming language is best for every algorithmic trading system. The choice depends on strategy frequency and volume, data needs, performance targets, development and maintenance costs, and the functions the system must…
This Chinese-market stock screen combines an amplitude threshold, a measure of institutional participation, exclusion of ST-designated shares, and a multi-part limit-up approach. It is intended to select stocks before 10 a.m. The description also refers to…
This indicator marks a candle’s midpoint and colors the marker according to whether the candle is bullish or bearish. It offers two midpoint definitions: the center of the full candle range, calculated from the high and low, or the center of the candle body,…
This study compares ARIMA, a multilayer perceptron, an LSTM, and an ARIMA-GARCH combination for next-day NVIDIA share-price forecasts. It describes ARIMA as a model for linear time-series structure, neural networks as ways to capture nonlinear patterns, and…
The N Reversal Detector is a configurable chart indicator that combines reversal patterns with an optional trend filter. Users can define the prevailing trend with a fast and slow moving-average comparison, an ATR-based Supertrend, or Donchian Channel highs…
This A-share stock screen combines a 14-period RSI below 65 with an external-to-internal trading volume ratio above 1.3 and positive net buying by major participants during the opening auction. The page also gives example implementations and adds filters in…
Corrected JMA is described as a variation on the Jurik Moving Average. It uses the JMA as a reference for measuring price deviations, then flattens the indicator’s value when those deviations are judged insignificant. This is intended to make directional…
This interview discusses how artificial intelligence, large datasets, and cloud computing support one another: AI methods analyze data, while cloud infrastructure supplies scalable storage and computing. It maps the data industry across collection, storage,…
EMAPredictive3 is described as a moving-average indicator built from the exponential moving average algorithm. Its defining construction is a linear interpolation between two EMAs calculated over different periods. The document attributes the indicator to…
This Chinese equities screening idea combines several filters: exclude stocks marked ST, require an amplitude above one, apply a five-session closing-price high condition, and select stocks whose intraday low is down within a narrow four-to-five percent band…
This post describes a Chinese equity screen for stocks associated with the metaverse theme, with a close above the previous day’s low and a code beginning with 60. It combines a thematic classification, a simple price condition, and an exchange-listing code…
This post outlines an equity screen requiring MACD above zero, upward divergence among current moving averages, and a positive price-to-earnings ratio. The stated rationale is to combine a bullish technical condition with rising price trends and a basic…
This post describes a Chinese equity screen combining a daily high-to-low amplitude threshold, a minimum circulating market capitalization, and a positive weekly MACD histogram. It presents the conditions as a way to focus on larger listed companies with…
The report proposes improving traditional liquidity factors for Chinese A-share stock selection by incorporating information about intraday trading structure. It frames the approach as a reusable factor research method: identify market information omitted by…
This report presents a short backtest of a strategy labeled “momentum-news-generic” against SPY, using Yahoo data. Over the stated period, the strategy had a slightly negative total return, negative annualized return, negative Sharpe and Sortino ratios, and…
This guide explains how to construct, monitor, and trade synthetic spreads in the VeighNa SpreadTrading module. A spread can combine several contract legs using a formula, including pricing legs that are not traded, which supports relationships involving…
This Chinese-language strategy post outlines a mainland China equity screen combining capital strength, upward divergence of moving averages, and a profitability filter. The initial title specifies companies with market capitalization below 10 billion yuan…
The Inverse Distance Weighted Moving Average (IDWMA) is presented as a price-smoothing indicator. Its calculation is described qualitatively: the line initially moves away from the average price, then approaches the price. The document says it is somewhat…