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 guide describes an FMZ tool for evaluating trading ideas with time-series expressions modeled partly on publicly available Alpha101 calculations. It lists arithmetic and logical operators, transformations such as moving averages and differences,…
This Expert Advisor enters trades when the i-SpectrAnalysis_WPR indicator changes color at a bar close, treating the color change as a shift in direction. It depends on a separately compiled indicator file, so the strategy cannot run without that component.…
This example demonstrates a portfolio-strategy backtest for a pair trading strategy on two Dalian Commodity Exchange continuous contracts. It configures minute data over a specified historical interval and supplies commission rates, slippage, contract sizes,…
This review examines whether market, macroeconomic, sentiment, valuation-spread, and momentum signals can forecast equity factor returns. It explains why factor premia can vary as risk compensation, investor behavior, and market frictions change. The…
This post describes an A-share stock screen that selects names with turnover between 3% and 12%, excludes Beijing-listed A-shares, and requires weekly MACD to be above zero. Its Python example also checks that MACD exceeds its signal line and excludes names…
This Chinese-language post proposes screening A-shares for a daily price range above 1%, a newly formed KDJ crossover, a robot-related classification, and circulating market value below 10 billion yuan. It presents the screen as a candidate-stock selection…
The article describes a China-focused stock screen. It selects shares with turnover between 3% and 12% and a reversal-style price pattern, then applies a filter based on the previous day’s turnover multiplied by today’s auction volume relative to the…
This short forum exchange explains how to save order and trade records produced by the VeighNa CTA backtester. The response says users can open the corresponding record table after a backtest, then use its context menu to save the displayed data as a CSV…
This document describes a weekly-chart indicator that signals staged long or short positions for an index strategy. Long entries require price above a 50-period average, a low short-period RSI measure, and price below a five-period average; a second long…
This introduction presents FinRL as an open source framework for applying deep reinforcement learning to financial trading. Its stated design aims include modular components that can accommodate different markets and data sources, configurable rather than…
The code implements a time-series prediction model paired with a TRA component that can combine predictions across multiple states. A base model, such as an LSTM, produces hidden representations and state-specific predictions. When multiple states are…
This report summary describes the risk-prediction component of a multi-factor investment framework. It outlines adjustments to factor covariance estimates, including Newey–West autocorrelation correction, eigenvalue adjustment, and volatility-bias…
The document explains how TqSdk’s wait_update loop drives data subscriptions, background tasks, and trading requests. Call get_* methods once and keep their returned objects as live references; subsequent update calls refresh them. Use is_changing to respond…
This article presents a long-only stock strategy that buys pullbacks while short- and longer-term moving averages remain ordered upward. Its simulated rules define an uptrend as the 5-, 10-, 20-, and 60-day averages descending in value, and define a pullback…
This article explains a contrarian rebalancing strategy that maintains a target allocation between cash and Bitcoin. When Bitcoin’s value rises enough to move the portfolio away from its target balance, the strategy sells some BTC; when it falls enough, it…
This post warns readers to scrutinize performance claims for automated trading strategies. It alleges that some public track records may omit fees, conceal liquidation events through repeated failed orders, or include referral rebates as though they were…
This short VeighNa community exchange asks whether the platform can run the same strategy separately across multiple instruments and report each instrument’s profit and loss. A respondent suggests implementing the batch process in a Jupyter notebook with a…
The 20PRExp-3 Expert Advisor is described as an intraday volatility breakout system for five-minute charts. It combines volume filters with the Parabolic SAR indicator and manages exits with a trailing stop. The advisor draws three horizontal reference…
This Expert Advisor opens positions when a Pin Bar indicator signals a setup. Its filters seek candles with sufficient high-to-low range, a small body relative to the candle, a body near the prior candle’s range boundary, and a dominant shadow compared with…
This document explains how to build an expected dividend yield factor for equity selection. Traditional measures use recent annual or trailing cash dividends, but they can jump when dividends leave the trailing window and may not reflect future payouts. The…
This study examines whether broad market conditions affect the profitability of buying Chinese stocks when they hit their daily price limit. It distinguishes two parts of the trade: whether the stock stays limit-up on the entry day, and whether it rises…
This report summary examines how to select timing variables and forecast equity factor returns within a multi-factor strategy. It proposes Lasso and Elastic Net regression for screening predictors and estimating factor returns. It also describes extensions…
This legacy platform tutorial outlines a workflow for predicting stock direction with a hybrid convolutional and recurrent neural network. It labels each observation according to whether the following ten-day return is positive or negative, builds rolling…
This guide describes a workflow for exploring crypto investments: select a themed basket, compare available strategies, review each strategy's stated idea, and inspect its historical profit chart. Baskets group cryptocurrencies by a shared theme or…