A bit late this year, due to a confluence of holidays, book launches, university exam writing and various other things. Here lies within my performance for the UK tax year 2022-23. Previous years can be found here. TLDR: Not great, absolute or relative. It was indeed a complete anus - horrible!.

Some of the strategies we track use economic data, like the unemployment rate, when making investment decisions. Like 99.99% of strategy backtests you’ll encounter, we’ve always taken the shortcut of basing our historical results on that economic data as it looks today. The problem is that

Over the almost 100 years that we have had data for U.S. stocks, the value premium (the annual average difference in returns, relative to accounting measures, from buying stocks whose market prices are low versus stocks whose market prices are high) has averaged 4.4% per year (when using

Welcome back, fellow traders and machine learning enthusiasts! We hope you’ve been enjoying our journey towards building a successful machine learning trading strategy. If you missed Part 1 of our series, don’t fret – you can always catch up on our exploration of various financial data

We will host our 6th annual “Democratize Quant” conference on May 18th via Zoom. The event is 100% free, but we do screen participants to enforce our “no spammers” policy. Request access Conference website Our speaker line-up is excellent, and we look forward to some exciting discussions.

Stock momentum trading is popular in practice and extensively investigated in academic studies. The paper finds a new option momentum, extending a recent study by Heston et al. (2022), who show that options also display momentum. Our risk-based option momentum is substantially stronger, has a risk

I have seen some chat about the Russell “Death Cross” that occurred on Friday and the potential bearish implications for the market. A “Death Cross” is a catchy (though not terribly accurate) term for when the 50-day moving average of a security cross below its 200-day moving average. It is

Thanks to the courtesy of Packt Publishing, I had the pleasure of receiving, reading, and studying the new release of Python for Finance Cookbook, the book by Eryk Lewinson. This is the second (and probably the last) edition, according to the author himself. Therefore, it must be solid and

Investors typically use correlation to identify diversifying strategies, but the metric can be misleading Upside and downside betas and correlations provide a better perspective Common hedge fund strategies failed to provide attractive diversification benefits INTRODUCTION Are investors as rational

What are the Research Questions? Communication in social networks is not new. In fact, it goes back to coffee houses in the 17th century. According to Standage (2006), “the drama of the South Sea Bubble, a fraudulent investment scheme that collapsed in September 1720, ruining thousands of

In our book “Your Complete Guide to Factor-Based Investing,” Andrew Berkin and I provided evidence that among the hundreds of equity factors identified in the literature, there were only five that met our criteria for investment. The factor must have provided a premium that was: persistent

As a quantitative researcher, your main goal is to find new financial edges. In this article, we will show an overview of the pipeline for designing alpha-generating investment strategies, with associated python code as usual. Here are the main steps that will be presented. Investment rationale Data

Financial data is one of kind: we think is non-stationary, and the samples are non-iid, which means one cannot simply apply common machine learning techniques. In this post, we briefly cover some pitfalls when using machine learning algorithms in a financial context. 1. Harry Potter and the model

Tommorrow marks the official release of my 4th book: Henceforth to be known as AFTS (I've had authors copies since the 24th February, but modern supply chains being what they are it takes considerably longer for the book to arrive in the hands of my readers; although plenty of people on twitter

Most investors analyze investment products based on their holdings However, holdings often misportray of what is determining the risk profile A factor exposure analysis can identify the performance & risk contributors INTRODUCTION It is difficult to watch an hour of European television and not

What are the research questions? The authors argue that factor exposures are random variables governed by a specific distribution that drives the behavior factor exposures over time. Five factors are examined including value, momentum, quality, investment and low volatility, over 12 developed and

Trading in financial markets can be a challenging and complex endeavour, with ever-changing conditions and numerous factors to consider. With markets becoming increasingly competitive all the time, it is a never ending struggle to stay ahead of the curve. Machine learning (ML) has made several

Modified Value-at-Risk (mVaR) is a parametric approach to computing Value-at-Risk introduced by Zangari1 that adjusts Gaussian Value-at-Risk for asymmetry and fat tails present in financial asset returns2 through a mathematical technique called Cornish–Fisher expansion. Since its publication, mVaR

Several years ago, I started using the phrase, “It’s long/short portfolios all the way down.” I think it’s clever. Spoiler: it has not caught on. The point I was trying to make is that the distance between any two portfolios can be measured as a long/short strategy. This simple point, in my

This article analyzes six trend-following indicators from a digital signal processing (DSP) frequency domain perspective in which the indicators are considered as digital filters and their frequency response characteristics are determined. In addition, potential trading signals generated by each

At the end of 2018, researchers at Google AI Language made a significant breakthrough in the Deep Learning community. The new technique for Natural Language Processing (NLP) called BERT (Bidirectional Encoder Representations from Transformers) was open-sourced. An incredible performance of the BERT

All other things equal, an improvement in a country’s terms of trade, the ratio of export to import prices, translates into increased demand for its currency and a boost for its growth outlook. However, terms of trade are a rather subtle and sporadic influence. Therefore, many market participants

The authors ask the following questions: Does the rise of index investing change information production in the economy? Does it affect the informational efficiency of stock prices? What are the Academic Insights? The authors augment (and improve) the Grossman and Stiglitz (1980) model of endogenous

US tech funds underperformed their benchmark indices by 4% between 2018 and 2022 The factor contributions were marginal This resulted in a median alpha of -4% over the 5-year period INTRODUCTION Every day, fortunes are won and lost on the stock market. However, investing in stocks is not a zero-sum

Interest rates are not necessarily a pure random walk. This assumption falls out from noticing that yields of different bond maturities must be in some way related. Have a look at the yields of the 30 year and 3 year U.S. Treasuries in the plot below. Notice that the 3 year yield bounces up and down

All the popular ‘smoothing’ indicators, like SMA or lowpass filters, exchange more lag for more smoothing. In TASC 4/2023, John Ehlers suggested the undersampling of price curves for achieving a better compromise between smoothness and lag. We will check that by applying a Hann filter to the

The empirical evidence from studies such as the 2017 paper “A Century of Evidence on Trend-Following Investing” and the 2020 paper “Time Series Momentum in the US Stock Market: Empirical Evidence and Theoretical Analysis” has found that time-series momentum (TSMOM) has demonstrated

Here is a link to our recent chat with Isaiah Douglass and Josh Bennett. An overview of the conversation is below: On this week’s episode, Isaiah is joined by expert Dr. Wesley Gray, CEO of Alpha Architect, to discuss the concepts of value

This article deals with the degree of market vulnerability to spillovers from disruptions in the cryptocurrency markets. This study investigates the impact of the FTX collapse and bankruptcy across global financial markets. What do responses of financial markets to the collapse of FTX say about

The EURUSD currency pair has been one of the most closely watched and traded pairs in the forex market for years. Its movements can have a significant impact on the global economy and particular investments. In 2022, we witnessed a significant moment in the history of the global currency market. In

After a great 2022 for factor investing, this year has started negatively for all traditional factors Perhaps this can be attributed to a revival of the growth theme as growth ETFs have outperformed again Size performed best, low volatility worst INTRODUCTION We present the performance of five

A costless collar, sometimes referred to as a hedged equity or defined outcome strategy, is a risk management strategy that combines holding a long position in a stock or index with buying a put spread defined by a specific set of strikes (e.g. 5% OTM long put, 20% OTM short put). This provides

Investment strategy should be based on three fundamental principles. First, markets are highly, though not perfectly, efficient. That leads to the conclusion that active management is the loser’s game. Second, if markets are efficient, it must follow that you should believe that all unique sources

It’s always fun to push the boundaries of technology and see what it can do. The AI chatbots are the hot topic of actual discussion in the quant blogosphere. So we have decided to test OpenAI’s ChatGPT abilities. Will we persuade it to become a data analyst for us? While we may not be there yet,

Simple equity ETFs often have exposures to other asset classes Gold stocks are bond proxies & growth stocks are short commodities Investors may have unintended bets in their portfolios INTRODUCTION ETFs used to be like surgical instruments. StateStreet’s SPY tracks the stocks of the S&P

Towards the end of last year, we ran a couple of free Zoom webinars on: The Basics of Edge Extraction – the “trader smarts” of getting an edge Data Analysis for Traders – an interactive research session. Here are the recordings: Basics of Edge Extraction Data analysis for Traders The colab

From the Volume and Mean Reversion post, a reader sent a suggestion to instead use the ratio of 10 day moving average of the Close times Volume divided by the 63-day moving average of the Close times Volume (CV10/63). I had not tried this before and wanted to see how well it would work. First Steps

US real GDP growth and US stock market returns were positively correlated since 1900 However, the correlation was not consistent and even turned negative The evidence of this relationship from other countries is mixed INTRODUCTION Switch on Bloomberg TV or CNBC at any time of the day, and there is a

How does ChatGPT work? What is behind deep fake images of celebrities? How do we deal with the lack of data in finance? All these issues have in common the same underlying concept; they are based on generative models. Generative models are algorithms that create new instances of data that mimic the

With more than $1.2 trillion under management in the U.S. as of mid-July 20221, investors are more and more using bond ETFs as building blocks in their asset allocation. One issue with such instruments, though, is that their price history dates back to at best 20021, which is problematic in some

In the last third installment, we will finish exploring the world of market timing strategies (see parts 1 & 2). We will focus on yield curve predictors and incorporate all three ideas (price-based, macro-economic, and yield curve predictors) into one final trading strategy that yields an annual

Since the development of the CAPM, academic research has attempted to find models that increase the explanatory power of the cross-section of stock returns. We moved from the single-factor CAPM (market beta) to the three-factor Fama-French model (adding size and value), to the Carhart four-factor

This is an old concept concerning the opening range. The idea is that the opening range often sets the day’s high or low within the first hour of cash equities trading (9:30 am - 10:30 am EST). Recently a trader on [Youtube] made the claim that you can know with 88% probability the high or low of

In this second installment in a series of three articles, we will continue with our goal to construct a market timing strategy that would sidestep the equity market during bear markets. A few days ago, we started with price-based market timing strategies. Today, we will focus on macroeconomic

dplyr 1.1.0 was a significant release that makes several common data operations more syntactically intuitive. The most significant changes relate to joins and grouping/aggregating operations. In this post we’ll look at the changes to joins. First, install and load the latest version of dplyr:

In this series of three articles, our goal is to construct a market timing strategy that would reliably sidestep the equity market during bear markets, thereby reducing market volatility and boosting risk-adjusted returns. We will build trading signals based on price-based indicators, macroeconomic

Are you looking for a way to quickly assess the sentiment of public companies through their tweets without previously training any ML models? The OpenAI API provides powerful, zero-shot classification capabilities so that text data can be classified into multiple categories – regardless of whether

A few select multi-strategy hedge funds generated outsized returns in 2022 However, the average fund lost money The average fund can be simply replicated via the S&P 500 & cash INTRODUCTION Citadel made $16 billion in profits in 2022, Millenium $8.0 billion, and Point 72 $2.4 billion. These

This blog is a follow-up to the series of posts Snorkel Credit Sentiment - Part 1 (May 2019) May the Fourth: VADER for Credit Sentiment? (May 2019) Experimenting with LIME - A tool for model-agnostic explanations of Machine Learning models (May 2019) Using LIME to ‘explain’ Snorkel Labeler

Implementing a successful trading strategy with code can be a challenging task. While some traders prefer to use basic trading rules and indicators, a more advanced approach involving predictive modeling may be necessary. In this tutorial, I will guide you through the process of training and