Historical Constituents of an Equity Index in Python (Norgate Data)
Index-based backtests often suffer from a hidden form of survivorship bias: using today’s index constituents to simulate historical strategies. In this article, we build a point-in-time index constituency database using Python and Norgate Data, accurately tracking index additions, removals, and re-entries over time. The result is a survivorship bias-free dataset that reflects the true historical composition of major U.S. indices and can be directly integrated into robust quantitative backtests.
Building a Survivorship Bias-Free Crypto Dataset with CoinMarketCap API
Crypto datasets often miss failed or delisted tokens, creating blind spots in research. To address this, we’re sharing the code behind our dataset from Catching Crypto Trends: A Tactical Approach for Bitcoin and Altcoins to support more complete and transparent analysis.
Backtesting the Opening Range Breakout (ORB) Strategy in Python using Polygon.io
Discover how to backtest the Opening Range Breakout (ORB) strategy using Polygon.io. This guide walks you through executing the backtest, adjusting key parameters, and interpreting results to refine your trading approach.
How to Construct a Survivorship bias-free Database in Norgate using Python
Analyzing historical stock market data is essential for backtesting trading strategies, identifying tradable edges, and conducting in-depth financial research. However, gathering comprehensive datasets, especially those that include delisted stocks (i.e., stocks that no longer trade due to acquisitions, mergers, buyouts, or bankruptcy) can be challenging. This is where Norgate Data comes in—offering a powerful solution […]
Backtest a Profitable Trend-Following Strategy using Python
In this article, we present a comprehensive guide to the Python code used to replicate the backtest of the trend-following strategy described in our paper, “A Century of Profitable Industry Trends.” This strategy utilizes Kenneth French’s database to construct a long-only, industry-based trend-following portfolio. The dataset spans daily data from 48 industry portfolios between 1926 and 2024. Our analysis reveals that momentum-based portfolios significantly outperform a passive Buy & Hold approach over the past century. Notably, the strategy’s parameters were not optimized in-sample, indicating potential for enhanced performance with further tuning.
Backtest a Profitable Trend-Following Strategy
In this article, we discuss using Matlab for a trend-following backtest outlined in “A Century of Profitable Industry Trends”. We use Kenneth French’s data to compare a momentum-based strategy against a Buy & Hold approach. The results show that momentum portfolios can outperform, and we conclude with a Matlab script that lets readers test how different parameters might improve profitability.
Designing a Profitable Intraday Strategy Using Python and Alpaca
Explore our guide on backtesting the S&P500 ETF (SPY) using seven years of free Alpaca data. Learn a proven intraday momentum strategy to potentially beat the market, distilled into clear, actionable insights. Perfect for traders seeking effective, data-driven techniques.
Backtesting 2 Years of FREE Data Using Python: Enhancing SPY Momentum Strategies with Polygon, from ‘Beat the Market’
Dive into our latest exploration of Python-based backtesting with two years of free SPY ETF data from Polygon. This post expands on the momentum strategies from ‘Beat the Market’, providing detailed Python code and analysis to assess their profitability and effectiveness.
MATLAB: Backtesting “Beat the Market: An Effective Intraday Momentum Strategy for the S&P500 ETF (SPY)”
In the world of finance, MATLAB is a powerful tool used by quantitative researchers to run statistical inferences and backtest systematic trading strategies. In this blog post, we share the MATLAB code that has been used to study the profitability of the strategy presented in our paper “Beat the Market: An Effective Intraday Momentum Strategy […]