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 review summarizes research testing whether small-cap stocks continued to outperform large caps across calendar effects in US equities. The underlying study forms portfolios from the smallest and largest size groups and examines the return spread around…
This chart script calculates minimum, maximum, and average sizes for candle bodies and shadows. It reports separate statistics for bullish candles, bearish candles, and the full set, displaying the results in the chart’s upper-left corner. The description…
This Chinese-language note proposes screening Shenzhen main-board stocks using three filters: price amplitude above 1, a shortening negative MACD histogram on a 15-minute chart, and price-to-earnings and price-to-book ranges of 0–29.01 and 0–3.11. The stated…
A BigQuant forum answer addresses why a stock selection strategy’s returns changed from positive to negative after neutralizing and standardizing its inputs. The reply explains that StockRanker uses a tree-based structure and, according to the respondent,…
This document describes a programming script for sorting arrays of decimal values in ascending or descending order. It lists bubble, selection, insertion, Shell, and Hoare-style quicksort methods, along with selection-based routines that use built-in minimum…
The Choppy Market Index (CMI) estimates directional movement by dividing the absolute change between the latest close and the close n bars earlier by the high-to-low range across that lookback, then scaling the ratio by 100. A low reading suggests that price…
KPrmSt is described as a stochastic oscillator calculated from pseudo-weekly bars. This defines its distinctive input: instead of applying the oscillator directly to standard chart bars, it derives the calculation from bars assembled to represent weekly…
This study examines whether generative adversarial networks can produce realistic multi-asset financial time series. It combines the convolutional architecture of DCGAN with the Wasserstein-distance loss used by WGAN: convolutional layers replace some…
The article explains the common U-shaped intraday volume pattern, with activity elevated near the open and close. It proposes that informed traders may prefer these liquid periods to act on information gathered before the open or to avoid overnight risk,…
The document outlines a small public-data pipeline that maps a stock ticker to a Central Index Key, retrieves the company's recent SEC submissions, and filters for 10-K, 10-Q, and 8-K filings. It explains that the submissions endpoint stores recent filing…
The document outlines a training program on cross-sectional multi-factor strategies, also described as alpha strategies. Its curriculum spans factor data preparation, supervised learning, model evaluation and interpretation, portfolio construction, and…
The document describes an adaptive Kalman trend filter as an indicator for reducing noise in market prices. It adjusts how quickly the filter responds as market conditions change, aiming to balance a smoother trend estimate with responsiveness to price…
The document describes a configurable Elliott oscillator, conventionally formed by subtracting a longer simple moving average from a shorter one and displaying the difference around a zero line. This version lets users choose the averaging method, periods,…
This Chinese equity screening rule selects stocks with turnover between 3% and 12%, a rising KDJ K value, and a volume condition based on the prior day's turnover and the relationship between current auction volume and prior volume. The post presents the…
This report summarizes stock-selection results for several machine-learning models across broad Chinese equity universes and constituent groups tied to the CSI 300, CSI 500, and CSI 800. It compares weekly, recent-month, and 2018-to-date excess returns, and…
This brief forum entry addresses an SQL error encountered while trying to neutralize a rolling turnover measure against total market capitalization. It points readers toward a regression-residual function as an alternative to a direct neutralization call.…
This short troubleshooting note explains why a pandas table may appear out of order after a sort. In the reported case, rows were first sorted by date and a field named double_low, then sorted again by index, which disrupted the intended ordering. The…
This tutorial walks through a basic Skip-gram word2vec training workflow. A center word is represented by an input vector, and the model predicts each word in its context window using a softmax output layer. The article describes calculating the prediction…
This study compares six cross-validation approaches for tuning machine-learning models on financial time series. It argues that ordinary shuffled K-fold validation can leak temporal structure and select overly complex models. Expanding-window time-series…
This stock-selection idea combines a technical condition, an industry filter, and recent positive returns. It proposes screening for Chinese beverage and alcohol import-export companies with a 14-period RSI below 65 and a positive return, while also…
The document gives a conversion procedure for obtaining forward-adjusted stock prices when a platform supplies backward-adjusted prices and their adjustment factors. The first step is to recover the unadjusted market price by dividing the backward-adjusted…
The document describes a variance calculation intended to avoid repeated loops after initial values are established, making it potentially useful where execution speed matters. It contrasts this approach with Welford’s method, which processes observations in…
The article organizes technical indicators into trend, momentum, volatility, and volume groups, describing the market data each uses and the questions it may help traders examine. Trend measures, commonly moving averages, smooth price fluctuations to show…
The article argues that identifying market turning points consistently is difficult and that missing a small number of the strongest up days can sharply reduce long-term returns. It contrasts steady index exposure with hypothetical timing outcomes in the US…