One technique for optimizing systems is to create a regime filter. A most common example is a binary classifier that classifies the market into either bull or bear markets based on closing above or below the 200 day moving average. But, there are problems with binary classifiers and we will

One of the most widely used risk measures is the Value-at-Risk, defined as the expected loss on a portfolio at a specified confidence level. In other words, VaR is a percentile of a loss distribution. But despite its popularity VaR suffers from well-known limitations: its tendency to underestimate

Quantopian has generously offered the Quantocracy community 3 free tickets to this year’s QuantCon in NYC. Two of the tickets are for the QuantCon main event on 04/29 ($699 value), and one deluxe ticket includes both the main event and a full day of workshops ($1,099 value). A number of very smart

I’m excited to be sharing this one with you today for a number of reasons. Firstly, I’ve been trying to get this guest on the show for over a year now, in fact it’s been longer than that because we first got in touch in July 2015, so it’s been a long time in the making. But secondly, and

This is the first in a series of posts in which we will change gears slightly and take a look at some of the fundamentals of algorithmic trading. So far, Robot Wealth has focused on machine learning and quantitative trading research, but I had several conversations recently that motivated me to

Using data for five major stock market declines during the 1987-2008 period, this paper provides evidence that value stocks are generally less sensitive to major stock market declines than growth stocks, controlling for beta, firm size, and industry group. Further analysis using several hundred

Albert Einstein is reported to have said the following: The more I learn, the more I realize how much I don’t know. I can relate. Having studied finance for a long time (PhD, professor, books, articles, etc.), I think I now know less about how the stock market works. In fact, I probably should

I. Trading Strategy Developer: John Ehlers and Ric Way. Source: Ehlers, J., Way, R. (2010). Zero Lag (well, almost). Concept: Trend following trading strategy based on moving average filters. Research Goal: To verify performance of the Zero Lag Moving Average (ZLMA). Specification: Table 1. Results:

January 2017 Trend Following: DOWN -2.84% If December bucked the trend of the last 6 months, January was a continuation of the downward direction seen in the second half of 2016. The index starts 2017 with a negative performance, in the context of global uncertainty, and keeps flirting with the

Yesterday I discussed two swing-trade systems that work pretty well in out-of-sample data. While each works differently, they overlap enough that you don’t get any benefit from running them both at the same time. One great thing about these two systems is that they’re dead simple to manage.

Trend Following started the year with the same flavour as it ended 2016: down. The index posted a negative performance in January but is still slightly up since the low in October last year. Please check below for more details. Detailed Results The figures for the month are: January return: -3.32%

I have created a quantitative trading strategy that incorporates a simple machine learning model to trade SPY as part of my ongoing research in quantitative trading. The focus here was not on creating a strategy with alpha but rather to develop a framework both in my mind and in code to develop more

The narrative of Smart Beta products is that factors are becoming an investment commodity. Factors are not commodities, but unique expressions of investment themes. One Value strategy can be very different from another, and can lead to very different results. There are many places that factor

The QuantStart team are very happy to announce that the full version of Advanced Algorithmic Trading has now been released. This brings the total number of pages to 517. To access the full version customers simply need to follow the download link received in the original pre-order purchase email. If

The fastest way to test the profitability of a trading model generating signals is to do a simple backtest (which means no hindsight biases i.e at least 1 period of timeframe lag from signal even if you timeframe is in milliseconds) using historical time series. actual returns = absolute return (no

Well, I was midway through a formal book review on Larry and Andrew’s new book, “Your Complete Guide to Factor-Based Investing,” when I noticed that the team over at GestaltU already wrote the review I was going to write — great job and I encourage everyone to read it. larry factor book So

This is a summary of the January performance of a number of excellent tactical asset allocation strategies. These strategies are sourced from books, academic papers, and other publications. While we don’t (yet) include every published TAA model, these strategies are broadly representative of the

Recently, I have been interested in applying machine learning to trading. This post contains some of my thoughts regarding a framework for thinking about trading as a machine learning problem, treating trading as a classification or regression problem, and transforming the output of a machine

How can we predict future returns of a series? Many series contain enough information in their own past data to predict the next value, but how much information is useable and which data points are the best for the prediction? Is it enough to use only the most recent data points? How much

One of the side projects I worked on in the past handful of months was Mr. Market Feels: a stock market sentiment Twitter bot that used automated image processing to extract and tweet the value of CNN Money’s Fear and Greed Index every day. Motivation There have been attempts to backtest the

In previous blog posts, we explored the possibility of using various volatility indices in designing market timing systems for trading VIX-related ETFs. The system logic relies mostly on the persistent risk premia in the options market. Recall that there are 3 major types of risk premium:

In the past few years “smart beta” (also known as “alternative beta” or “strategic beta”) investments have grown rapidly in popularity. As of the current date (January 2017), assets in these investment categories have grown to over USD$500 billion, and are expected to reach USD$1

2016 was a rather boring investment year that turned out surprisingly profitable if you used the strategies that worked. I missed the boat I largely missed the best strategies boat as my portfolio was over 60% in cash throughout the year. In spite of that I still I was still able to earn a

Ah…leveraged ETFs. All that beta without all the embarrassment of trying to borrow money from your broker (or cousin) to leverage your returns. Is the regular ETF not volatile enough for you? Buy the 2x version! Still too tepid? Perhaps the 3x version is what you’re looking for. Unless you’re

This post contains some of the research I have done regarding how to measure the performance of a trading strategy. The immediate goal of conducting this research is to build out a collection of performance measure tools in R to evaluate, compare, and measure the performance of trading strategies.

Smart beta. Empirical finance. Evidence-based investing. These terms have migrated from the periphery of the investment ecosystem just ten years ago to become the investment world’s most popular memes today. Why? It stands to reason that investors are simply disenfranchised with traditional forms

The advent of algorithmic trading in the late last century caused a massive tectonic shift in the way trading took place in exchanges worldwide. Be it trading in stocks, derivatives, Forex or commodities, trading firms worldwide adopted algorithmic trading in a big way. The last couple of decades

This post documents some of my research in creating a trading strategy centered around shorting leveraged exchange-traded funds (ETFs). I present the following thought experiment to motivate readers: Suppose an underlying instrument increases by 25% on day 1 and decreases by 20% on day 2. The return

Cliff Asness, Antti Ilmanen, and Thomas Maloney of AQR are out with a new paper about market timing with value, titled: Market Timing: Sin a Little. Specifically, the paper explores whether the Shiller PE (also known as the cyclically adjusted P/E, or CAPE) can be effectively used to directionally

Modern portfolio theory provides a way for investors to identify the efficient frontier: the set of portfolios that maximize return per unit of risk. Taken to its logical conclusion, modern portfolio theory states that all investors should invest in the same global market portfolio and increase or

As of yesterday (25’th january 2017) Vix Term Structure closed at 0.794. By Vix Ts im mean the ratio between 1 month and 3 month implied Spx volatility. Taking a quick look at what low Vix Ts values have meant for Vix returns going forward and run a bare bones backtest to gauge the initial

A lot of research already have been done trying to find out how to predict the stocks market returns. On a daily time frame, both trend-following and mean-reversal trading strategies applied to single stocks can’t sustain a stable Sharpe ratio across the time, making us believe that even if the

Despite the many interesting features of options, private traders rarely take advantage of them (I’m talking here of serious options, not binary options). Maybe options are unpopular due to their reputation of being complex. Or due to their lack of support by most trading software tools. Or due to

My recent research has been focused on finding strategies that are not highly correlated with the S&P500 index. One of my most popular posts is ETF Sector Rotation. The idea for this post is to apply those concepts to a list of country ETFs. Would this produce decent returns that were not highly

We seek to describe the broad cross-section of average stock returns. We follow the APT literature and estimate the common factor structure among a large cross-section containing 278 decile portfolios (associated with 28 market anomalies). Our statistical model contains seven common factors (with an

Density estimation belongs with the literature of non-parametric statistics. Using simple bootstrapping techniques we can obtain confidence intervals (CI) for the whole density curve. Here is a quick and easy way to obtain CI’s for different risk measures (VaR, expected shortfall) and using what

This is a test of the Generalized Protective Momentum (GPM) strategy from JW Keuning and Wouter Keller. The strategy builds off of the authors’ popular Protective Asset Allocation (PAA) model that we discussed last month. Results for the GPM strategy from 1989, net of transaction costs, follow.

Most investment portfolios are a collection of risk factors, such as exposure to credit and equity risk. Monitoring and managing these factors is critical. The standard approach is reviewing portfolios through a plain-vanilla asset allocation lens – 60% stocks, 30% bonds, 10% cash, for instance.

Last month we did a blog post on using high-yield bonds as a key indicator. This month we continue with a focus of using financial stock ETFs as a second indicator. Many people seem to want to try to simplify everything down to one variable -- often something like a P/E ratio or a moving average. We

Imagine we’re traders in a market where the cross-section of returns is related to V \geq 1 variables: In the equation above, \alpha^\star denotes the mean return, and each \beta_v^\star captures the relationship between returns and the vth right-hand-side variable. Some notation: I’m going to

The term statistical arbitrage (stat-arb) encompasses a wide variety of investment strategies that typically aim to exploit a statistical equilibrium relationship between two or more securities. The general principal is that any divergence from the equilibrium is a temporary effect and that bets

Throughout this series, which has been a window into the workflow of professional quant trading firms, we’ve encouraged you to submit questions and requests for further clarification. So, in this episode, being the final installment, Delaney answers as many of these questions as possible (within

Position sizing is often the result of portfolio construction and is therefore largely overlooked in manager selection. Risks introduced by active strategies can change not only the absolute risk level of the portfolio, but also the relative composition of risk. Active risk can also create tracking

In addition to the "usual" tricks of statistical arbitrage, trend-following and fundamental analysis, many quant shops (and retail quants!) engage in natural language processing (NLP) techniques to build systematic strategies. Such techniques fall under the banner of Sentiment Analysis. In

Risk Management… It’s not as sexy as the latest hot indicator… Or the undiscovered penny stock poised for an explosive move… Or the trading guru who appeared out of nowhere and is now promising to share the “secrets” to making million dollar profits overnight… But there are a whole

The CBOE PutWrite Index has outperformed the BuyWrite Index by approximately 1.1 percent per year between 1986 and 2015. That is pretty impressive. But troubling. Yes – troubling – because the theory of put-call parity tells us that such outperformance should be almost impossible via a

A decision tree is one of the widely used algorithms for building classification or regression models in data mining and machine learning. A decision tree is so named because the output resulting from it is the form of a tree structure. Visualizing a sample dataset and decision tree structure

Welcome back! This week’s post will backtest a basic mean reverting strategy on a cointegrated ETF pair time series constructed using the methods described in part I. Since the EWA (Australia) – EWC (Canada) pair was found to be more naturally cointegrated, I decided to run the rolling linear

Shiller’s Cyclically Adjusted Price to Earnings Ratio (CAPE ratio) is at 27.8, which is 11.1 above its long-term mean of 16.7, signifying overvaluation of stocks and low forward returns. According to Jeremy Siegel it incorporates time-inconsistent data, and the failure to correct for changes in

Traders are constantly looking for variables that predict returns. If x is the only candidate variable traders are considering, then it’s easy to use the Bayesian information criterion to check whether x predicts returns. Previously, I showed that using the univariate version of the Bayesian