The profitability of trend-following strategies has been documented in a large number of empirical studies. The majority of these empirical studies find that these strategies are profitable in the long-run over periods ranging from 50 to 150 years. However, two issues of concern arise regarding the

Crisis Alpha is on everyone’s mind right now, maybe due to a bit of recency bias, but regardless of the reason thinking of and preparing for “tail-risk” is best done before it’s needed. Trend following is one such strategy that is rooted in academic research and is an enticing way to manage

Harvesting the variance risk premium has a sound theoretical foundation However, actual investment products have generated poor returns Furthermore, they are correlated to equities, providing few diversification benefits INTRODUCTION Investing is akin to fighting in a never-ending war. There are

What if your portfolio was only based on one idea? Something like “stocks always go up” or “value always beats growth.” You may be learning a humbling lesson right now that Mr. Market has taught us over and over again (and learning it the painful way). In this post, we’ll examine various

In our last post, we took a quick look at building a portfolio based on the historical averages method for setting return expectations. Beginning in 1987, we used the first five years of monthly return data to simulate a thousand possible portfolio weights, found the average weights that met our

After a month, we are back with a year-to-date performance analysis of a few selected trading strategies. In the previous article, we were writing about the performance of equity factors during the coronavirus crisis. Several readers asked us to take a look also on different types of trading

A very common question I get, is “when should I turn off a strategy?” Given the very volatile markets we have had the last few months, I can relate. Some strategies can thrive in these high volatility markets. While others can suffer. In the June 2020 issue of Technical Analysis of Stocks and

The convex payoff profile of trend following strategies naturally lends itself to comparative analysis with option strategies. To isolate the two extremes of paying for whipsaw – either up front or in arrears – we replicate an option strategy that buys 1-month at-the-money calls and puts based

Bonds had superhero qualities over the last few decades The case for bonds in asset allocation is not clear when yields are low or negative Japan can be used as a roadmap for the outlook of a 60/40 portfolio in the US or Europe FIXED INCOME KRYPTONITE “Faster than a speeding bullet. More powerful

Whether they are selecting a manager, a factor, or a strategy, investors can make two types of mistakes. We thought we were hiring Peter Lynch, not this loser! A Type I error (or false discovery) when selecting a manager who turns out to be unskilled. That Warren Buffett guy is washed up, let’s

In 2016, Dr. Marcos Lopez de Prado introduced the Hierarchical Risk Parity (HRP) algorithm for portfolio optimization. Prior to this, Harry Markowitz’s Modern Portfolio Theory (MPT) was used as an industry-wide benchmark for portfolio optimization. MPT was an amazing accomplishment in the field of

Cumulative indicators, such as the EMA or MACD, are affected not only by previous candles, but by a theoretically infinite history of candles. This makes them return slightly different results depending on the tested period. Although this effect is often assumed negligible, John Ehlers demonstrated

While most people agree that black lives matter (why shouln't they?), many also feel that the "PC Police" has gone too far with demands to ban movies like "Gone with the Wind", removing statues of historical figures, or renaming words like "blacklist". Here are my

In perfectly efficient markets, option prices should not convey any new information or contribute to the price discovery of underlying assets. However, if markets are not perfectly efficient, traders with private information might prefer to transact in option markets over stock markets even though

Back in November last year I posted about Random Vector Functional Link (RVFL) networks here and here. Since then, along with my recent work on Oanda's API Octave functions and Market/Volume Profile visualisation, I have continued looking at RVFL networks and this post is an update on this

Today we’ll incrementally build a strategy using trend-following, volatility targeting, and ensemble models and we’ll use Bitcoin as our use-case. Why bitcoin? Because it’s a maddening asset-class that’s extremely volatile over short periods of time and seemed like a fun place to test these

Extra Trees and Random Forest are two very similar ensemble methods and often a doubt arises as to whether to use one or the other. What is really the difference between them? In previous posts, “Random forest: many are better than one”, we have seen how to create a Random Forest from decision

This is “ReSolve’s Riffs” – live on Youtube every Friday afternoon to debate the most relevant investment topics of the day. The recent pandemic-led selloff has once again highlighted the importance of having ballast in portfolios to deal with extreme equity volatility – and ultimately

AI & Data Science in Trading Digital Week brings together experts in the use of AI and advanced data analytic techniques within asset management, primarily for finding alpha, managing risk and optimizing portfolios. Join us for a week long online event from wherever you are in the world. Use

At least once a year, the press and Twittersphere propagate the mistaken idea that investors can earn excess returns by buying the S&P 500 at the close of the market, then selling it at the open the next day. The logic is that by exposing themselves to only overnight returns, investors can seek

Defensive smart beta strategies like Low Volatility did not offer much capital protection in 2020 Long-short multi-factor investing generated negative returns, but still offered diversification benefits Managed futures finally found their redemption given positive & uncorrelated returns

This study is one of several studies reviewed here and here, attempting to measure factor crowding. This article specifically examines the presence of factor crowding by estimating the correlation between market order flow with the magnitude of the factor signal to trade. They hypothesize that

In our last post, we compared the three most common methods used to set return expectations prior to building a portfolio. Of the three—historical averages, discounted cash flow models, and risk premia models—no single method dominated the others on average annual returns over one, three, and

We recently added a monster correlation matrix to our factor library data sheet that maps out the correlation of all the factors against every other factor. Here is a sample output that highlights the difference in the correlations between value factors and different quality factors. Note the big

Breaking Bad Trends Ashish Garg (Research Affiliates), et al. May 7, 2020 We document and quantify the negative impact of trend breaks (i.e., turning points in the trajectory of asset prices) on the performance of standard trend-following strategies across several assets and asset classes. The

Lu Zhang and his colleagues made some waves with their new paper, “Replicating Anomalies.” (now published in the RFS — congrats!). We have a summary of the paper here. Lu Zhang, and his colleagues, Kewei Hou and Chen Xue, spent nearly 3 years carefully compiling and replicating 447

On Zero to Robot Master Bootcamp, we teach how to build a portfolio of three automated systematic trading strategies. One of them is a long term Risk Premia Harvesting strategy which trades asset class ETFs. ETFs are useful instruments for analysing long term (tradeable) performance of various asset

The Securities and Exchange Commission (SEC) has called for more research and discussion on the impacts of ETFs. In a previous post, we covered why ETF’s have not screwed up correlations, liquidity, and alpha opportunities. However, here is another post from Wes that outlines arguments that ETFs

The March 2020 equity market sell-off has caused many investors to re-investigate the potential benefits of tail risk hedging programs. Academic support for these programs is quite limited, and many research papers conclude that the cost of implementation for naïve put strategies out-weighs the

The Low Volatility strategy failed to protect investors in March and April 2020 Industrials & materials generated positive and technology & real estate negative relative performance Low Vol strategies do not deliver ESG benefits INTRODUCTION Low volatility (Low Vol) strategies have gained

Numerical Libraries & Data Structures numpy — NumPy is the fundamental package for scientific computing with Python. scipy — SciPy (pronounced “Sigh Pie”) is a Python-based ecosystem of open-source software for mathematics, science, and engineering. pandas — pandas is an open source,

In the past I have posted a series of blog posts about a Currency Strength Indicator (here, here, here and here). This blog post gives an Octave function to use Oanda's API to download all the 10 minute OHLC data required to calculate the above strength indicators on the 10 minute time frame.

It’s long been established that stock market returns aren’t normally distributed and that fat tails (extreme returns that are unexpected for a normal distribution) apply. This has implications, of course, for portfolio design and management. The first question: What are the choices for managing

Recently I was invited to talk with Justin and Jack on the Excess Returns Podcast. I thank them for the opportunity and enjoyed the conversation! Below are some of the topics we discussed: Struggles in value and its long-term potential going forward. What would it take to convince you that value

Why aren’t calls more expensive than puts for an asset which is more likely to go up than down? We have an asset trading at $100 for which the distribution of future returns is a known fact. It has annual returns described by a normal distribution with mean 5% and standard deviation 10%. This is,

From January 2017 through March 2020, the value premium, defined by HML (the return of high book-to-market stocks minus the return of low book-to-market stocks experienced a drawdown of 42 percent. 1 If we extend the period back to January 2007, the drawdown of about 51 percent is the largest ever.

In the world of Big Data, there are lots of tools and technologies to choose from. Choosing the “right” one depends on the things that you are building and the problems you are trying to solve. Trading firms have skilled teams that monitor and deploy data pipelines for their organisation and the

In this blog we’ve talked about autoencoders several times, both as outliers detection and as dimensionality reduction. Now, we present another variation of them, variational autoencoder, which makes possible data augmentation. If you have ever faced Machine Learning problems, you will have dealt

The previous article dealt with indicators based on correlation with a trend line. This time we’ll look into another correlation-based indicator by John Ehlers. The new Correlation Cycle indicator (CCY) measures the price curve correlation with a sine wave. This works surprisingly well – not for

Another opinion piece. If you can’t explain it simply you don’t understand it well enough. (Albert Einstein) Rant in progress A bit on Deep Learning What is so deep about deep learning? Nothing. There is nothing deep about it. If you read through the excellent Deep Learning book you can see (p.

Holding data in a tidy format works wonders for one’s productivity. Here we will explore the tidyr package, which is all about creating tidy data. In particular, let’s develop an understanding of the tidyr::pivot_longer and tidyr::pivot_wider functions for switching between different formats of

Access to high quality, cost effective market data is a continuing problem for retail traders. I was recently told about the ongoing efforts of the startup brokerage “Alpaca”. The gentleman I spoke with said the API gave access to the tick data of thousands of stocks everyday and without cost. I

Although there is widespread agreement that systematic value strategies have turned in at least a decade of underperformance, there is little agreement as to the underlying cause or cause(s). However, a number of rationalizations and critiques have emerged that question the long term viability of

In this post I will be reviewing the course “Mean Reversion Strategies by Dr. E.P. Chan” ( His research and publications have garnered widespread appreciation, over the years. Unfortunately for Python programmers most of his past research was done in Matlab. Matlab was a very popular tool for

Anyone that’s been around the markets knows that the monthly release of the United States Department of Labor’s Non-Farm Payrolls (NFP) data can have a tremendous impact, especially in the short term. NFP is a snapshot of the state of the employment situation in the US, representing the total

US bonds generated positive total returns in most inflation regimes Returns were mixed when inflation was above 4% Real returns were strongly negative when inflation was high INTRODUCTION Inflation is like cancer. It largely happens out of plain sight and requires focus to be noticed. The data is

Pattern matching locates similarly acting historical market windows and makes future predictions based on the similarity. They combine the strengths of both momentum and mean reversion by exploiting the statistical correlations of the current market window to the past. In the following blog post, we

I. Trading Strategy Source: Kaufman, P. J. (2020). Trading Systems and Methods. New Jersey: John Wiley & Sons, Inc. Concept: Momentum trading strategy based on Jesse Livermore‘s approach to swing trading. Research Goal: Performance verification of Swing Filter and Penetration Filter.

Over the past few weeks, we’ve examined the three major methods used to set return expectations as part of the portfolio allocation process. Those methods were historical averages, discounted cash flow models, and risk premia models. Today, we’ll bring all these models together to compare and

So, first off: I just finished a Thinkful data science in python bootcamp program that was supposed to take six months, in about four months. All of my capstone projects I applied to volatility trading; long story short, none of the ML techniques worked, and the more complex the technique I tried,