Recent Quant Links from Quantocracy as of 03/30/2025

The idea We don't have better algorithms; we just have more data. Peter Norvig. Peter Norvig is one of the greatest computer scientists of all time and a leading figure in artificial intelligence. As the former Director of Research at Google, he played a key role in shaping the technologies behind Google Search the flagship product of one of the most transformative companies of our

Prerequisites To fully grasp the bias-variance tradeoff and its role in trading, it is essential first to build a strong foundation in mathematics, machine learning, and programming. Start with the fundamental mathematical concepts necessary for algorithmic trading by reading Stock Market Math: Essential Concepts for Algorithmic Trading. This will help you develop a strong understanding of

Imagine you have to backtest a strategy on 50 stocks and for that you have to download price data of 50 stocks. But traditionally you have to download ticker by ticker. This sequential download process can be painfully slow, especially when each API call requires waiting for external servers to respond. What if you could download multiple stock data simultaneously? "Multithreading does

The dominance of mega-tech stocks, particularly the Magnificent 7, in both U.S. and global equity indexes has a profound impact on factor portfolios. When constructing value-weighted smart beta strategies, these portfolios often end up heavily concentrated in a few individual stocks. This concentration introduces idiosyncratic risk, skewing the risk profiles of factor strategies. While no

I had a thought this week about what constitutes my "trading edge". You know, the question every trader is expected to be able to answer. It's supposed to constitute some kind of evidence that you can out-perform the market, your peers, or whatever. Something Bob Pardo mentioned made me think differently about this when he reminded me that when trading pits were around, every trader

Macro risk premium scores are differences between market-implied risk and point-in-time quantified macroeconomic risk. Two principal types of scores can be calculated for credit markets: spread-based risk premium scores and rating-based risk premium scores. This post proposes a small set of these scores for EM foreign-currency sovereign debt, targeting 24 country sub-indices of the EMBI Global.

In Trade Like a Quant Bootcamp, we talk about win-win risk premia harvesting. Its a game where no ones really competing for the edge. Think about VTI (Vanguards Total Stock Market ETF). You expect to make more than implied by the stock markets cash flows (a risk premium) because holding these stocks is uncomfortable. Theyre sensitive to all kinds of nasty surprises. When you buy

Cross-Asset Momentum Capturing Time-Varying Return Predictability: The Multi-Asset Time Series Momentum Strategy (Harris, Taylor, and Wang) While standard time-series momentum strategies rely only on each asset's own return history, research shows that incorporating cross-asset predictability can be beneficial. This paper explores that idea by building a dynamic strategy that trades equities,

Cryptocurrencies are becoming mainstream. In this post, I feature some strategies for trading and managing risks in cryptocurrencies. Arbitrage Trading in the Cryptocurrency Market Arbitrage trading takes advantage of price differences in different markets and/or instruments. Reference [1] examined some common and unique arbitrage trading opportunities in cryptocurrency exchanges that are not