Nowcasting economic trends can make use of a broad range of machine learning methods. This not only serves the purpose of optimization but also allows replication of past information states of the market and supports realistic backtesting. A practical framework for modern nowcasting is the(...)
In today’s newsletter, you’ll use Polars, a high-speed data-handling tool that’s becoming essential in quantitative finance and algorithmic trading. You’ll see how to compare its performance to pandas for many common data manipulation techniques. By the end of this post, you’ll understand how(...)
In his 2012 paper “The Other Side of Value: The Gross Profitability Premium,” Robert Novy-Marx demonstrated that profitability, as measured by gross profits-to-assets, had roughly the same power as book-to-market (value factor) in predicting the cross-section of average returns – profitable firms(...)
Fractional Brownian motion is defined as a stochastic Gaussian process XtXt that starts at zero X0=0X0=0 has an expectation of zero E[Xt]=0E[Xt]=0 and has the following covariance1: E[XtXs]=σ212(∣t∣2H+∣s∣2H−∣t−s∣2H)(1) E[XtXs]=σ221(∣t∣2H+∣s∣2H−∣t−s∣2H)(1) where σσ is the volatility parameter(...)
Sum up: by combining all the vols into one strategy and randomizing key parameters, we can generate useful signals that yield a decent return with some consistency. We’re not meeting all the quant_rv goals yet, but we’re making progress on all the fronts. ~ Links to earlier parts ~ Part 1: jumping(...)
Portfolio Management: A Deep Distributional RL Approach – David Pacheco Aznar This thesis presents the development and implementation of a novel Deep Distributional Reinforcement Learning (DDRL) approach in the field of quantitative finance: the Distributional Soft Actor-Critic (DSAC) with an LSTM(...)
During 2017 I blogged about Statistical Shrinkage. At the end of that post I mentioned the important role signal-to-noise ratio (SNR) plays when it comes to the need for shrinkage. This post shares some recent related empirical results published in the Journal of Machine Learning Research from the(...)
The traditional financial theory attributes security returns to market- or factor-based risk, with no role ascribed to other influences. In this research, the authors argue for including investor demand as an additional variable in explaining returns. Can changes in investor demand generate(...)
We started off with the conceptualisation of trading alpha in different abstract representations, such as mathematical formulas, graphs and visual representations: Alpha-Encoding Data Structures Alpha-Encoding Data Structures HangukQuant · Jun 30 Read full story For machine trading this would(...)
Backtest speed can significantly affect research friction. The ability to form a hypothesis and quickly get an answer from a backtest allows you to investigate more hypotheses. In this article, I explore several factors that affect backtest speed and compare the performance of 3 open-source(...)
The low-beta anomaly for the capital asset pricing model (CAPM)—low-beta stocks outperform high-beta stocks—was first documented more than 50 years ago by Fischer Black, Michael Jensen, and Myron Scholes in their 1972 paper, “The Capital Asset Pricing Model: Some Empirical Tests.” In our 2016 book,(...)
Introduction Simulator/backtester architecture Preparing the data Simulating a single market Simulating market orders Part 2: Simulating trading costs Simulating funding Simulating many markets Finish Subscriber materials (source code) Introduction In the last article, we looked at how markets work(...)
Pure macro(economic) strategies are trading rules that are informed by macroeconomic indicators alone. They are rarer and require greater analytical resources than standard price-based strategies. However, they are also more suitable for pure alpha generation. This post investigates a pure macro(...)
Quantocracy: This is a curated mashup of quantitative trading links. Adversarial Deep Hedging: Learning to Hedge without Price Process Modeling – Masanori Hirano, Kentaro Minami, Kentaro Imajo Deep hedging is a deep-learning-based framework for derivative hedging in incomplete markets. The(...)
The square root of your portfolio’s covariance matrix gives you a powerful way of understanding where your portfolio variance is coming from. Here I show how to calculate the square root and provide an interactive example to explore how it works. Author Adrian Letchford Published 27 July 2023(...)
Abstract: We find that by using a novel measure of investor attention, generated from InvestingChannel’s clickstream data on online financial news consumption, we can identify broad groups of stocks which are less efficiently priced and therefore where anomalies such as Value and Momentum are(...)
Crypto-market price actions often revolves around the news. Good or bad? It does not matter. However, the recent long-term battle between the SEC and Ripple seemed to reignite the markets. On July 13, 2023, XRP/USDT suddenly shoot up, dragging a number of not so obvious cryptos up along. This was(...)
In recent years, the Transformer architecture has experienced extensive adoption in the fields of Natural Language Processing (NLP) and Natural Language Understanding (NLU). Google AI Research’s introduction of Bidirectional Encoder Representations from Transformers (BERT) in 2018 set remarkable(...)
We started off with the conceptualisation of trading alpha in different abstract representations, such as mathematical formulas, graphs and visual representations: Alpha-Encoding Data Structures Alpha-Encoding Data Structures HangukQuant · Jun 30 Read full story For machine trading this would(...)
Running regressions on past returns is a great tool for academic researchers who understand this approach’s nuance, assumptions, pitfalls, and limitations. However, when factor regressions become part of a sales effort and/or are put in the hands of investors/advisors/DIYers, “the tool can quickly(...)
In a multi-asset portfolio, it is usual that some assets have shorter return histories than others1. Problem is, the presence of assets whose return histories differ in length makes it nearly impossible to use standard portfolio analysis and optimization methods… Estimating the historical(...)
It’s just too easy to do all the volatility measures, with quantmod (well, with TTR actually). Let’s skip all the preliminaries and have a look. And, a Pearson pairs table: C2C Parkinson Rogers-Satchell Garman-Klass,Yang-Zhang C2C 1.0000000 0.4395541 0.2619220 0.3573710 Parkinson 0.4395541(...)
I first learned about this algorithm in the book Kernel Adaptive Filter: A Comprehensive Introduction1 sometime in 2012 or 2013. This book goes in depth into how to build kernel filters and does a fantastic job of easing you into the mathematics. I highly recommend having a read if you can. In my(...)
Reinforcement Learning for Credit Index Option Hedging – Francesco Mandelli, Marco Pinciroli, Michele Trapletti, Edoardo Vittori In this paper, we focus on finding the optimal hedging strategy of a credit index option using reinforcement learning. We take a practical approach, where the focus is on(...)
Betting on War? Oil Prices, Stock Returns and Extreme Geopolitical Events Knut Nygaard (Oslo Metropolitan U.) and L.Q. Sørensen (Storebrand Asset Mgt.) July 2023 We show that the ability of oil price changes to predict stock returns is largely limited to five extreme geopolitical events: the 2022(...)
My August 4, 2022, Alpha Architect article examined the research demonstrating that cross-sectional momentum has provided a premium that has been found to be persistent across time and economic regimes, pervasive around the globe and across sectors and asset classes (stocks, bonds, commodities and(...)
Everybody knows what volatility is. But there’s more than one way to measure it. The last couple of posts I’ve been trying to document a little more about the plain vanilla standard way to measure vol in the context of my efforts toward finding an ETF switching strategy to use realized volatility(...)
This study explores the degree to which fund concentration as measured by high tracking error or active share, affects the magnitude of excess returns and whether or not the likelihood of outperformance or underperformance are distributed similarly. Three methods of analysis were used to examine(...)
There is grave danger in tying your strategy to one selected set of parameters, particularly if those parameters are cherry picked to give more exciting results than other possible choices. I’m trying to working to avoid that in quant_rv. So far, quant_rv has two main parameters that can vary: the(...)
Financial Machine Learning – Bryan T. Kelly, Dacheng Xiu We survey the nascent literature on machine learning in the study of financial markets. We highlight the best examples of what this line of research has to offer and recommend promising directions for future research. This survey is designed(...)
While sustainable investing continues to gain in popularity, economic theory suggests that if a large enough proportion of investors choose to favor companies with high sustainability ratings and avoid those with low sustainability ratings (sin businesses), the favored company’s share prices will(...)
An empirical analysis of the U.S. bond market since the 1960s emphasizes occasional abrupt regime changes, as defined by yield levels, curve slopes, and related volatility metrics. An arbitrage-free bond pricing model illustrates that bond risk premia can be decomposed into two types. One is(...)
Should investors prefer companies with high profit margins or companies with improving profit margins? Is it better to own an unprofitable company that's getting better, or a profitable company that's getting worse? This post explores these questions by analyzing the profitability growth(...)
Using the input data as described in Quantitative And Machine Learning Asset Analysis: Single Moving Average (SMA) – (current price – N day average)/N day average, where N = 21, 42, 63, …, 231, 252, formed into an array. Dual Moving Average (DMA) – Same as SMA with 21 day average substituted for(...)
The conventional wisdom suggests that by spreading your investments across a wide range of assets, you can mitigate risk and achieve greater long returns. In this article, we will explore the diversification benefits of conglomerate stocks and why they can be valuable additions to a stock(...)
This blog post serves as a summary and exploration of ~100 papers, providing insights into the key trends presented at ICML 2023. The papers can be categorized into several sub-fields, including Graph Neural Networks and Transformers, Large Language Models, Optimal Transport, Time Series Analysis,(...)
Covered call strategies aim to offer index-like returns with lower volatility and higher yields They have underperformed their benchmarks significantly over longer periods They are tools for market timing, but that is difficult to execute successfully INTRODUCTION JP Morgan has been a late-comer to(...)
In time-series analysis we often examine signals for specific volatility patterns. The simplest one is a periodic or quasi-periodic modulation. In finance these modulations are of paramount importance allowing for signal decomposition, separating short-term variations from long-term trends.(...)
Value as an investment strategy has long been popular in both academia and among practitioners and is supported by valuation theory, which provides a framework for identifying the drivers of expected returns: the prices investors pay and the expected future cash flows investors will receive.(...)
In the research report Random rotations and multivariate normal simulation1, Robert Wedderburn introduced an algorithm to simulate i.i.d. samples from a multivariate normal (Gaussian) distribution when the desired sample mean vector and sample covariance matrix are known in advance2. Wedderburn(...)
For v1.2.0 we take a step back from 1.1.0 to meet some of the new goal requirements right off the bat, and to play explore. In particular, we remove the code to test QQQ (or other ETFs) and related vars. Next we change code to make it easy to explore parameters (like the volatility threshold) to(...)
So we need some starter code, and some goals for where we’re going. The starter code comes from a blog post by Learning Machines back in April 2023. He’s got some great stuff on his blog (we’ll use some of his ideas here), so take a good look through his Quantitative Finance category, at least.(...)
The Forex Market is the global marketplace where currencies are bought and sold. It is the largest and most liquid financial market in the world, with trillions of dollars traded daily. A currency pair is an asset composed of two currencies traded on the financial market. Its price represents the(...)
This blog post serves as a summary and exploration of ~100 papers, providing insights into the key trends presented at ICML 2023. The papers can be categorized into several sub-fields, including Graph Neural Networks and Transformers, Large Language Models, Optimal Transport, Time Series Analysis,(...)
All popular factors generated negative excess returns in 1H 2023 Small caps performed best, low-risk stocks worst Somewhat surprisingly, long-short multi-factor products produced positive returns INTRODUCTION We present the performance of five well-known factors on an annual basis for the last 10(...)
Executing a live trading strategy can be a daunting task. From analyzing market data and identifying trading signals to deploying and monitoring trades in real-time, the process requires precision, speed, and accuracy. Fortunately, advancements in technology have paved the way for innovative(...)
Effect J. González 28/06/2023 No Comments In a previous post we saw how avoiding being in the market during Earnings publications could be a zero-sum game in the long run. In this post our purpose is to study if it is possible to take advantage of the effect in the stock prices based on the(...)
Since the discovery of the size, value, and momentum effects in the 1980s and 1990s, a plethora of other factors have been identified in the asset pricing literature, which led John Cochrane to coin the phrase “zoo of factors.” It has raised questions and led to research into how many factors are(...)
How does a company's profitability affect its stock returns? In this post, I use Alphalens, a Python library for analyzing alpha factors, to investigate the relationship between operating margin, a profitability ratio, and future returns. This is the second post in the fundamental factors(...)
In the previous article we wrote a Python function which utilised the Polygon API to extract a month of minutely data for both a major (EURUSD) and exotic (MZXZAR) FX pair. We plotted the returns series and looked at some of the issues that can occur when working with this type of data. This(...)