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 configuration describes an order-execution backtest using five-minute market data and an order file. The main strategy uses a recurrent network with a PPO policy, a categorical action interpreter, and a state interpreter that supplies recent intraday…
This MetaTrader 5 tutorial explains how to instrument an Expert Advisor so an optimization workflow can save balance and equity data and attach custom criteria to each test pass. It describes adding calls in tick and tester lifecycle functions, recording…
A trader reports that the same strategy produces different results across backtest runs and simulated trading, including differences in selected securities, order quantities, and execution prices. The discussion offers possible explanations: randomness or…
This report outlines a framework for researching quantitative commodity signals in iron ore. It groups inputs into fundamental factors covering supply, demand, and inventories, plus a separate sentiment category. Because fundamental data updates less…
This research summary examines generalized linear models as ways to combine stock factor exposures into forecasts of future returns. Its workflow includes extracting features and labels, preprocessing features, forming training sets, and retraining on a…
The document describes an Expert Advisor that trades signals from the BBands_Stop_v1 indicator. A transaction signal is generated when a bar closes and the indicator changes position and color. The advisor depends on the compiled indicator being available in…
This tutorial shows how to test a long-only strategy using signals from daily and weekly data. It resamples daily price bars to weekly bars to calculate weekly RSI, then aligns that indicator with the daily series. Entries require both RSI readings to be…
This Expert Advisor strategy uses color changes in XDPOCandle indicator bars to trigger trades. A signal forms at bar close when the indicator changes from orange to light green or in the reverse direction. The document identifies the required compiled…
This stock selection approach combines three filters: daily amplitude above 1%, afternoon large-order net inflow, and circulating market value between 5 billion and 10 billion yuan. From stocks that pass, it proposes selecting the one with the highest gain.…
This document outlines an Expert Advisor that trades from the ColorXMACDCandle indicator, evaluating signals when a bar closes. A configurable trend mode chooses between two approaches: detecting an intersection between the XMACD signal line and histogram…
This research report explains reinforcement learning concepts, including Markov decision processes, state and action values, reward design, and value-based and policy-based algorithms. Its applied example uses a deep Q-network to time long positions in the…
This broad practical guide introduces machine learning in quantitative investing, covering supervised, unsupervised, and reinforcement learning. It explains data preparation, missing values, categorical features, scaling, train and test splits,…
This stock-selection proposal combines three filters: daily amplitude above a threshold, a price and short moving-average condition intended to capture upward dispersion, and a minimum listing age. The document provides a formula-style expression and a…
This indicator description presents a step-chart version of RSX, the Relative Strength Quality Index, intended to reduce the number of signals and make changes easier to interpret. The user sets a step size as a percentage of RSX; changes smaller than that…
The document describes a Chinese stock-selection example that represents daily buy signals as a factor value of one and sell signals as zero. It proposes processing those values and using them to filter and rank stocks. The stated data source is daily stock…
This document describes a position-sizing calculator that converts a cash risk budget, entry price, and stop price into a trade volume using the broker's symbol specifications. It uses tick size and tick value to estimate the loss per lot, then rounds the…
This assignment outlines a workflow for creating a visual machine learning stock strategy using BigQuant’s StockRanker course and strategy template. The participant is asked to modify the model’s input features by adding personal factors, then backtest the…
This expert advisor runs separate long and short systems using signals from the ColorMaRsi-Trigger indicator. The two directions can be configured independently, including how trade volume is set and how recent trade outcomes affect the next position. When a…
The post describes a feature-data issue in a quantitative research workflow. A request failed with an error indicating that no observations remained after missing values were removed. Changing the feature lookback period, as suggested by common…
The document explains why a high-frequency trading backtest should account for delays between exchange activity and a trader’s system. It separates latency into feed latency, order-entry latency, and order-response latency, distinguishing when market data…
The note describes a workflow for handling large datasets or repeated data requests during quantitative research. Such requests can slow backtests or cause errors, so it recommends downloading the required data into the research environment first and then…
This document contrasts MQL’s built-in MathRand generator with a class wrapping a 32-bit PCG pseudorandom number generator. It characterizes MathRand as a limited linear congruential generator and says its statistical flaws make it unsuitable for large Monte…
The document examines how benchmark choice affects mutual fund performance estimates. It contrasts return-based evaluation, which is sensitive to benchmark selection, with holdings-based evaluation, which can be more precise but depends on infrequently…
This indicator identifies ascending triangles, with rising lows under flat resistance, and descending triangles, with falling highs above flat support. It records major and minor swing points using separate lookback periods, then matches those pivots to form…