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 report evaluates ten equity valuation measures, including earnings, book, sales, cash flow, dividend, enterprise value, and growth based ratios. It first describes how factor levels vary across industries and company sizes, and how those relationships…
This research roundup describes two separate studies. The first examines the Stochastic Volatility Inspired (SVI) parameterization for modeling implied volatility surfaces. It reports theoretical results and empirical analysis suggesting that, under…
The time series approach begins after a pair or group of assets has already been selected, for example through cointegration testing. It models the resulting spread to produce trading signals, shifting the focus from finding related securities to deciding…
This brief indicator description explains a channel built around an average as its central line, with upper and lower bands calculated from Parkinson historical volatility rather than a conventional historical volatility measure. The method therefore uses a…
This forum exchange addresses two practical questions about factor analysis: how to submit a factor that needs Python processing beyond SQL, and whether factor values must exist for every stock on every trading day. The reply says the SQL field may be left…
This brief introduction contrasts linear regression on factor data with tree-based machine learning. It argues that factor returns may relate to outcomes in nonlinear ways, making a simple linear model potentially inadequate. Decision trees are presented as…
RSI Rendiment is an oscillator that blends the standard Relative Strength Index with a logarithmic measure of price change over a selected lookback range. The document defines the combined value as the average of RSI and a scaled natural logarithm of the…
This reference explains how a futures platform derives performance and activity measures at four levels: individual accounts, weighted account portfolios, individual strategies, and weighted strategy portfolios. It maps daily balance, fees, margin, risk,…
The Kase Peak Oscillator measures price movement over a configurable lookback period and compares current behavior with the distribution of recent values. Its calculation normalizes a range and high-low movement measure by average true range and the square…
The document examines whether volatility in the CSI 300 varies by weekday and time of day, then uses that pattern to modify Black–Scholes pricing for an index option. It calculates five-minute log returns from open to close over a year of index data,…
The document introduces the standard form of an equity multi-factor model: stock returns are represented as a linear combination of factor returns, plus a residual component that the factors do not explain. It also notes that a portfolio’s return can be…
This indicator combines momentum readings from exponential moving averages across five horizons into one synthetic curve. The component averages use different periods and staggered historical offsets; their percentage differences are weighted by period…
This indicator builds bands around volume-weighted average price (VWAP), using VWAP as the center in place of the simple moving average used by Bollinger Bands. It provides a way to view price relative to a volume-weighted reference and its surrounding…
This study examines equity factors built from changes in analyst forecasts and tests how forecast stability affects their relationship with next-month stock returns. It reports that revision factors are positively associated with subsequent returns, but…
The document proposes screening equities for turnover between 3% and 12%, membership in a robotics theme, circulating market capitalization below 10 billion, and a closing price of 18.5 yuan. It also describes sorting qualifying shares by popularity. The…
The report describes tests of 14 Ethereum trading strategies using stablecoin issuance and Uniswap V2 USDC/ETH pool activity. It outlines signals based on rolling issuance sums, moving averages, standard-deviation thresholds, Pearson correlation, and pool…
This forum exchange concerns the data requirements for calculating a 200-period moving average on 15- or 30-minute bars when a strategy begins with one-minute data. The original poster is concerned that loading many one-minute records and aggregating them at…
This indicator derives a source signal for each bar by dividing the close-minus-open difference by the high-minus-low range. Its green oscillator aggregates those signed values over a period and divides their sum by the sum of their absolute values, then…
This note proposes ranking stocks from strongest to weakest by a capital-flow-strength measure, then selecting the top N. Its original screening description excludes Beijing-listed A-shares, while its later suggested refinement says to include them to…
This brief description explains a spread monitoring indicator that plots minimum, average, and maximum spread values as a histogram across chart bars. The three series use separate colors, making it possible to compare how spread conditions vary over time.…
This A-share selection method combines a turnover range of 3% to 12%, an appearance on the previous day’s Dragon-Tiger list, and one or more preferred company characteristics. The post adds that eligible companies should have been listed for more than a…
This stock-selection screen combines recent trading activity, short-term price momentum, market capitalization, and profitability. It ranks stocks by trading volume over the past ten days, selects those with positive gains below 35% over the same period, and…
DecEMA is described as a moving average formed as a linear combination of exponential moving average smoothing series. The document identifies the indicator’s author and notes that its initial implementation appeared in MQL4 before later publication in a…
This Expert Advisor builds several price patterns at different historical depths from tick movements. It encodes each pattern as a binary sequence according to whether each sampled price rose or fell, then tracks virtual trades for pattern configurations and…