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.
286 documents
The document presents hypothesis testing as an early step in quantitative strategy research. It uses a claim about whether the average return of Nifty 50 stocks exceeds a specified benchmark to explain how to define null and alternative hypotheses, choose a…
This overview compares free and paid sources for historical market data accessed through Python APIs. It describes retrieving single and multiple instruments, using daily or intraday frequencies, and handling several asset classes, with examples involving…
This article introduces five technical indicators for assessing price trends, momentum, and volatility: moving averages, the Average Directional Index, Moving Average Convergence Divergence, the Relative Strength Index, and Bollinger Bands. It distinguishes…
The article explains why systematic research depends on reliable, structured inputs and outlines a Python workflow that retrieves end-of-day prices and fundamental growth data through financial data APIs. Its illustrative research question is whether…
The article surveys stock market simulators for practicing trades with virtual funds. It describes services for manual trading, historical chart exercises, and, in some cases, automated strategies or broker connections. The listed features include market…
The article explains random forests as ensembles of decision trees that reduce reliance on any single tree’s prediction. Trees are built from randomly selected data features, and their classifications are combined by majority vote; for continuous outputs,…
Sourabh Sisodiya describes moving from discretionary trading based on technical analysis and candlestick patterns toward rule-based strategies after questioning whether his approach had a reliable edge. He presents backtesting as a way to assess a system and…
This overview explains the academic and practical skills that can support work in algorithmic trading. It maps computer science to programming, mathematics and statistics to probability and quantitative methods, finance and economics to markets and risk, and…
This tutorial walks through setting up Zipline for backtesting on Windows. It covers creating a Conda environment, installing Jupyter and Zipline, configuring a Quandl data key, and ingesting historical data. It also describes using Pyfolio to produce a…
The article describes trading ideas as hypotheses about how an asset may behave in particular circumstances, then suggests developing them through experience, research papers, forums, books, and learning from practitioners. It gives momentum research as an…
The article presents reinforcement learning (RL) as a trial-and-error approach in which an agent learns actions from rewards, with an emphasis on maximizing longer-term outcomes. It maps the framework to trading through states, such as price and indicators;…
The article proposes evaluating automated strategies with two linked measures: win rate and the ratio of average winning to average losing trades. It defines expected edge as win probability times average win minus loss probability times average loss, and…
This article describes an introductory online course on momentum trading offered through B3’s education platform in partnership with QuantInsti. It presents the course as suitable for learners with basic Python knowledge and says the material covers…
This overview introduces multi-leg options strategies, including straddles, strangles, iron condors, and iron butterflies. It explains Delta, Gamma, Theta, Vega, and Rho as measures of how option values and portfolio exposures respond to changes in the…
This project tests a mean-reversion pairs strategy on Mexican stocks. It screens an initial equity universe for complete price histories and minimum average trading volume, then tests within-industry pairs for cointegration with an augmented Dickey-Fuller…
This guide introduces algorithmic trading as a process of turning trading rules into programs, evaluating them with historical data, and deploying them for automated or partly automated execution. It outlines a learning path covering financial markets and…
The article outlines a supervised learning workflow for classifying EUR/USD direction. It introduces features, feature selection, and support vector machines, then describes a model using hourly EUR/USD data dating back to 2010, with MACD and Parabolic SAR…
This webinar listing introduces sentiment analysis, also called opinion mining, as the computational classification of text opinions into positive, negative, or neutral attitudes. It frames the technique as potentially relevant to financial markets alongside…
This article organizes suggested reading for people learning algorithmic trading. Its categories span market microstructure, statistics and econometrics, technical analysis, options, advanced statistics, machine learning, Python, and portfolio management.…
This strategy uses a large language model to set long-only exposure for AAPL according to market states, rather than asking it to predict price direction. Historical price features are discretized into readable states, and monthly statistics for each state…
This project builds a random forest regression model to estimate the next day’s EUR/USD closing price from daily price data, technical indicators, and Twitter sentiment. Predictors include OHLCV values, short and long EMAs, RSI, OBV, and daily mean sentiment…
This study tests whether public filings reporting C-suite purchases of common shares are followed by abnormal stock returns. It builds a research sample from SEC Form 4 data, carefully distinguishing transaction rows, aggregated purchase components, and…
The document explains how to explore portfolio allocations by repeatedly assigning random weights to four U.S. financial-sector stocks, calculating each portfolio’s annualized return and standard deviation, and comparing the results. It defines three…
The article introduces algorithmic trading as using coded rules to generate and execute orders, then compares it with manual trading. It highlights speed, simultaneous monitoring of markets, reduced reliance on emotional judgment, and the ability to backtest…