Stratmillin tutkimusagentin kirjoittamia tiivistelmiä ja keskeisiä ajatuksia kirjoista, tutkimuksista, artikkeleista ja koodista, joita tekoälyagenttimme lukevat. Jokaisella sivulla on linkki alkuperäislähteeseen.
511 dokumenttia
The article surveys factors that can shape algorithmic strategy design across cash equities, bonds, derivatives, commodities, and foreign exchange. It presents general practices such as testing strategies on in-sample and out-of-sample data, setting…
This project describes a long-only portfolio that reallocates capital among a small basket of sector or asset ETFs and cash on a fixed weekly schedule. It compares classifier-based allocations with a rule-based momentum baseline. The baseline averages recent…
This beginner guide outlines a machine-learning workflow for classifying whether the S&P 500 will rise or fall on the next trading day. It introduces classification and distinguishes binary, multiclass, and imbalanced problems, then describes a practical…
This note describes a five-minute trading rule that uses returns from an Indian equity ETF as a lead signal for MSCI futures. When the ETF’s average return exceeds the futures’ average return, the spreadsheet generates a buy signal; when it is lower, it…
This tutorial surveys a practical development setup for quantitative programming: code editors, command line terminals, isolated language and library environments, Git version control, repositories, and cloud machines. Its core advice is to choose tools by…
This interview follows an engineer with mathematics, statistics, and machine learning experience who moved toward financial analytics and algorithmic trading. He describes learning about markets independently, finding that general online material did not…
The article introduces deep learning as a branch of machine learning and outlines neural network types, including multilayer perceptrons, convolutional networks, and recurrent networks. It describes supervised and unsupervised learning at a high level, and…
The article introduces extensions to ordinary linear regression for financial modeling. Polynomial regression adds transformed predictor terms to represent curved relationships while remaining linear in the coefficients. The article describes forward…
The project describes a stock pairs strategy that models one price as a time-varying linear function of another. A Kalman filter updates the intercept, hedge ratio, spread, and spread volatility; spread z-scores set entry and exit signals. It screens…
The article explains how ARTFIMA extends ARFIMA with a tempering parameter that controls how quickly long-memory effects decay, allowing a model to represent both short- and long-term dependence. It outlines the roles of the autoregressive and moving-average…
This article introduces a MATLAB toolbox for obtaining historical stock prices and developing algorithmic strategies. Its most substantive research concept is walk-forward analysis: repeat optimization on an in-sample window, then evaluate the selected setup…
The article introduces algorithmic trading as software that computes signals from market data and can submit or divide orders. It organizes preparation around five requirements: access to appropriate data, charting and research platforms, programming…
This interview follows a trader’s education in economics, technical analysis, and algorithmic trading. He describes using data and backtests to examine discretionary trading ideas while continuing to place trades manually, rather than operating a fully…
The document outlines a daily pairs-trading strategy for related equities, implemented in R and illustrated with Johannesburg Stock Exchange shares. It selects similar companies, calculates a price ratio as the spread, estimates its mean and standard…
This tutorial demonstrates evaluating a decision-tree model that predicts whether the next adjusted close of Apple stock will rise or fall. It constructs features from the open-close relationship, daily range, and rolling return volatility and average…
This project compares intraday futures strategies built from daily pivot levels. It calculates pivot points using classic, Camarilla, and Fibonacci approaches, then tests textbook support-and-resistance rules alongside two alternatives on one-minute data for…
This article explains the difference between model parameters, which are learned from training data, and hyperparameters, which are set before training and guide the learning process or model structure. Examples include learning rate, training epochs,…
The document introduces mean reversion as the tendency for prices or returns to move back toward a historical average after deviating from it. It outlines ways to define that average, detect deviations, and form signals using moving averages, RSI, and MACD.…
The document explains Python Pickle as a way to serialize Python objects into binary files and restore them in a later session. It frames the technique as useful when data preparation, backtesting, or model training takes substantial time, since saved…
The document broadens trading risk management beyond portfolio construction to include the systems and processes that generate and route orders. It surveys market, counterparty, liquidity, regulatory, operational, scalability, technology, and personnel…
The document presents exploratory data analysis (EDA) as a way to understand financial datasets before modeling or developing trading signals. It describes EDA goals such as finding relationships, unusual observations, missing values, and variables that may…
The document explains how quantitative value investing uses financial data and predefined rules to identify potentially undervalued stocks. It describes common measures including price-to-earnings, price-to-book, price-to-sales, price-to-cash-flow, return on…
This webinar description introduces mean reversion as the idea that prices or returns may move back toward an average. Its outline signals several concepts relevant to assessing such strategies: time-series stationarity, the Augmented Dickey-Fuller test, and…
A chemical engineer describes learning Python for algorithmic trading without prior programming experience. The account emphasizes rewriting code after lessons, recording notes in notebook software, and using active recall to retrieve code and concepts from…