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.
16,761 documents
This example describes a simple moving-average trend strategy for Apple shares. It calculates 20-period and 40-period exponential moving averages from a 40-day history of daily prices. When the shorter EMA is above the longer one and the algorithm is not…
Nevalyashka is a simple directional trading approach that opens each new position opposite to the previous one. The brief description identifies only three configurable inputs: stop loss, take profit, and minimum trade size. It says the stop-loss and…
This Chinese-language announcement outlines a community session devoted to building FinRL agents and comparing reinforcement-learning algorithms for quantitative investment. Its educational agenda covers how the DRLAgent class wraps different algorithms…
The document describes an expert advisor that uses three moving averages with ascending periods of 5, 25, and 125. It checks that the periods remain in ascending order and looks for the averages to align from highest to lowest, or lowest to highest. A signal…
The document describes a weekly long strategy based on an asserted pattern of weak Mondays and strong Fridays in the Nasdaq 100. It waits for Monday’s cash-market open, places a limit entry one percent below that open, and initially targets a return to the…
This Chinese-language account describes a learning project that builds a China stock selection strategy with five ranked factors and a two-day forward price label. It trains a Ridge regression model, standardizes the inputs, and periodically retrains before…
This module defines three return measures from a series of closing prices. Daily simple return is the percentage change from the previous close; daily logarithmic return is the difference between successive log prices; and cumulative return is the percentage…
This Expert Advisor trades on every tick within the current bar and allows only one open position at a time, making it suitable for either hedging or netting account modes. A sell signal occurs when the main Stochastic line on the current bar is below its…
This short platform discussion addresses why a strategy may appear to buy and sell on the same day despite China’s T+1 stock-trading convention. The suggested code adjustment is to make the sell conditions refer to currently held instruments rather than the…
This study examines the low-volatility effect in Chinese A-shares using price amplitude as a volatility proxy. The original amplitude factor has negative stock-selection ability, but its performance is unstable: the reported monthly IC and rank IC are…
This example shows how to compare two long-only signal strategies in Backtrader. One strategy enters based on a crossover between 10-period and 30-period simple moving averages; the other uses a crossover between the closing price and a 10-period simple…
This account summarizes a 2021 conference talk on using machine learning to price stocks. A simple example feeds market-wide daily open, high, low, close, and average prices into an LSTM time-series model. The speaker stresses preparing noisy financial data,…
The document presents a TradingView Pine strategy that combines a Vegas-style EMA filter with ADX and candle conditions. It enters long or short positions when the corresponding filter conditions are met, the ADX exceeds a threshold, and the candle condition…
The roadmap outlines planned upgrades to Hummingbot’s strategy framework, bot management tools, and core architecture. Its strategy plans include configurable scripts, reusable components for cross-exchange market making, dollar-cost averaging, statistical…
This introductory article explains cryptocurrency futures as contracts used to gain exposure to expected price movements without directly holding the underlying coins. It outlines long and short positioning, noting that short sellers aim to buy back at a…
This short Chinese-language forum exchange addresses how to preserve promising results from a quantitative strategy’s hyperparameter search. The example need is to save parameter sets whose score exceeds a chosen threshold. The poster reports that attempts…
The tutorial explains how to backtest a mean-reversion strategy on EUR/USD perpetual futures using TrueFX spot ticks as proxy data. It builds one-minute mid-price bars, then combines a 20-period Bollinger Band with a 14-period RSI: a lower-band touch with…
The document describes two measures of active fund manager ability based on whether a manager’s holdings or portfolio changes resemble those of historically capable peers. The holdings measure assigns stocks a quality score from the weighted skill estimates…
The document summarizes lifecycle fund design through human-capital theory and liability-driven dynamic asset allocation. Under stated assumptions, it says an optimal glide path can be derived analytically, and discusses how design factors affect the path.…
The document describes a stock screen that requires price amplitude above 1 and RSI below 65, then ranks candidates by capital-flow strength. It defines amplitude from the day’s high and low relative to the previous close, and describes a flow proxy that…
This brief research submission describes an experiment on stocks priced between zero and two yuan, using three five-day factors: momentum, reversal, and volatility. The author says the backtest results were weak and asks for ideas to improve the analysis.…
The document presents a quadratic regression indicator that fits a parabola to recent closing prices. It uses a configurable lookback window, set to 100 by default, and calculates the polynomial coefficients from rolling sums of the bar index, its square,…
This document describes an Expert Advisor that trades when a histogram indicator changes direction at a bar close. The direction change is represented visually by a change in the color of star markers. The strategy therefore uses a closed-bar indicator event…
This short BigQuant forum post concerns a modified XGBoost strategy whose equity curve and recent trade records appear unchanged despite adjustments to the data. The response offers two possible explanations: the backtest module may be reusing cached…