One question often asked in forums and blogs is how to adjust stock prices in order to take into account dividend payments. There are several reasons why we may be interested in adjusting stock prices: Analyzing total returns taking into account dividend reinvestments for reporting (performance,

This is the third part of the Build Better Strategies series. In the previous part we’ve discussed the 10 most-exploited market inefficiencies and gave some example algorithms for trading strategies. In this part we’ll analyze the general process of developing a model-based trading system. As

One of the most commonly cited maxims is that market timing is impossible. In fact, empirical evidence makes a compelling case that market timing is feasible and can yield substantial economic benefits. What’s more, we even understand why it works. For the typical portfolio investor, applying

In the previous article in the Advanced Trading Infrastructure series I discussed and presented both the code and initial unit tests for the Position class that stores positional information about a trade. In this article we will consider the Portfolio class, used to store a list of Position

Do Volatility Futures Provide Useful Information for Future S&P500 Performance? Volatility or VIX Futures are based on the S&P500 index and are calculated from the implied volatility of different option strike prices across different expiration periods. In contrast to the VIX index, VIX

Investors often focus their analysis on benefits. In the finance industry, we’ve distilled this down to a single metric: alpha. Benefits and risk require separate analysis. Increasing benefits does not necessarily reduce risk or even leave it unchanged. In practice, increasing alpha can actually

Risk is not a simple entity, it comes in many flavours, and requires respect and consideration even when you least expect. If one was to try ‘totally avoid’ risk in their market endeavours they would most likely just be holding cash – where are the returns in that? The truth is that in almost

Python in Sydney: Course+Workshop Wednesday, March 16, 2016

I’ve been off the beaten path for the last few weeks in East Africa, so I’m long overdue one of these “best of” posts. Below are the best quant mashup links while I was away, as voted by our readers: Stock Market Prices Do Not Follow Random Walks [Turing Finance] Fitting time series models

Given the downturn in the energy sector and the persistent economic weakness abroad, investors have become increasingly focused on the possibility of a U.S. recession. In this piece, I’m going to examine a historically powerful indicator that would seem to rule out that possibility, at least for

That graph looks like a bunch of spaghetti, I realize. But I’ll explain! I’m back testing Genotick. It’s an open-source machine-learning java script. Probably to the developer’s dismay, I’m always throwing things at it to make it break. Much like a small child throwing a temper tantrum,

I've recently read a great post by the turinginance blog on how to be a quant. In short, it describes a scientific approach to developing trading strategies. For me personally, observing data, thinking with models and forming hypothesis is a second nature, as it should be for any good engineer.

In my previous post, I introduced the messaging topic. Now its time to talk about what I found on the message framework universe. To get a overview about past and upcoming topics, please have look here: Content++. There were several message frameworks I was come across and played around. The first

Psychology research suggests that when we make predictions, we suffer from “representative bias,” and mistakenly overweight observations that fit a particular narrative, and fail to consider base rate probabilities. For example, if we flip a coin 5 times and it shows up H, H, H, H, H, we may

In this post, I continue trying to fit the daily log returns of TASI index using heavy-tailed distributions. In the previous post, I used Pareto distribution to model TASI index’s left tail. In this post, I use Student t distribution. Recently, Student t distribution has been used widely by

Analyzing history as a guide to the future is riddled with caveats, but if you’re mindful of the limitations there’s a mother lode of perspective waiting to be mined in the cause of modeling relationships in macro and markets. One of the more useful techniques in this corner: impulse-response

In our 2016 Market Outlook (available on our website), we discuss expected real returns for U.S. equities over the next decade. The picture isn't pretty. A bear market may be just what the doctor ordered. U.S. Large-Cap Expected Real Return Forecast Horizon Jack Bogle 2.0% 10 Years Research

Blackjack odds are as good as you’ll get at most casinos. In most cases, the casino has just a 1% edge versus the gambler. So in a given night, you can go on a great run and win a lot of money playing blackjack. But of course if you played every day, all day, your odds of a sustained run steadily

The existence of risk premia has been widely documented in the academic literature over the past decades. Until now they have typically been handled as separate phenomena for specific markets or asset classes and thus examined independently. This study analyses risk premia across a variety of asset

For almost five decades, the literature on the investment performance of mutual funds has found that very few managers possess sufficient stock-picking or market-timing talent to allow them to consistently and reliably produce positive risk-adjusted performance after considering their fees. In other

This is the second part of our interview with a senior quantitative portfolio manager at a large hedge fund. In the first part, we covered the theoretical phase of creating a quantitative trading strategy. In this part, we cover the transition into “production.” You can read the first part of

The world of finance is no stranger to fashion and Low volatility equity investing has recently attracted serious interest from the investment community. Its popularity has led to doubts regarding the valuation level for this overcrowded arena. Just look at the current market caps of the most

If you own last year’s laggards you are probably wondering what all the fuss over the market is about. It has been tough sledding for the leaders so far this year as they have underperformed the laggards by quite a bit. In one of the models we track, the laggards moved in to positive territory

I read a blog post recently that began “suppose you have a trading system that works well on low-volatility days…” and I thought, hmm. Is that a thing? Is there an edge to low-volatility days vs high volatility days? Let’s turn this blog post into a speculator’s version of Dude, What Would

Josh Brown (i.e. The Reformed Broker) recently shared the aptly titled post How to Make Volatility Your Bitch highlighting how dollar cost averaging into a volatile market can lead to higher overall returns: Door number one – you spend 15 years putting $1000 into an investment every month for 15

We are happy to announce PortfolioEffectEstim toolbox availability for both R & MATLAB. It is designed for high frequency market microstructure analysis and contains popular estimators for price variance, quarticity and noise. For R https://cran.r-project.org/web/packages/PortfolioEffectEstim/

Summary Active strategies are often defined by the factor tilts they take on. For factor tilts to continue to out-perform the market over the long-run, they must exhibit premium volatility that causes short-term under-performance. Since alpha is zero-sum, investors that fold during periods of

We demonstrate that weak trading signals, which do not offer high risk-adjusted returns on their own, can be combined into a powerful portfolio. In other words, no need for holy grails when researching signals. We start our experiment with some key assumptions. We have 20 signals with annualized log

Quandl will soon be offering intra-day data (1 min bars). Rock on ! I was kindly given some data to test out (see below). I can’t say much more than this but keep an eye out for an official announcement soon 🙂 With both QuantGo and Quandl offering reasonably priced intra-day data, smaller trading

In one of our recent articles we’ve talked about most popular backtesting platforms for quantitative trading. Here we are sharing most widely used Python libraries for quantitative trading. Python is a free open-source and cross-platform language which has a rich library for almost every task

First things first. What do we mean by sparse estimation? Sparse – thinly scattered or distributed; not thick or dense. In our context, the term ‘sparse’ is installed in the intersection between machine-learning and statistics. Broadly speaking, it refers to a situation where a solution to a

Momentum is the tendency for winning stocks to keep winning and losing stocks to continue underperforming. It was identified as a risk factor in the early 1990s and targeted by investment practitioners since then. Unlike the value and size factors, the momentum factor has remained robust and

I’m happy to publish my first paper on SSRN entitled, “Speculation in a Path Dependent World” I found many otherwise talented managers entering a multi-manager platform (assigned capital with strict risk limitations) having a difficult time transitioning. The paper is my simple attempt to

In my previous post I talked about a architectural concept I had defined for my trading platform. Looking backward from now, it was a good decision to go for a service oriented architecture. But how do all the communication is done in a distributed system? Lets talk about this, and try to find some

Given recent performance, the question of whether small-cap stocks really do outperform over time has made its way into the financial media. So far, we’ve sought to answer it by considering a multifactor approach and examining international evidence. Today we’ll tackle a behavioral explanation.

As established in a previous post, Tadawul All Shares Index (TASI) of the Saudi stock market has high excess kurtosis (9.903). The high kurtosis indicates that TASI has heavy tails. This means that the probability of extremely large negative returns is higher compared to a normal distribution. In

The current study examines the turn of the month effect on stock returns in 20 countries. This will allow us to explore whether the seasonal patterns usually found in global data; America, Australia, Europe and Asia. Ordinary Least Squares (OLS) is problematic as it leads to unreliable estimations;

Hot off the press and haven’t had time to reverse engineer and verify, but this is pretty interesting stuff at first glance. The Enduring Effect of Time-Series Momentum on Stock Returns Over Nearly 100-Years This study documents the significant profitability of “time-series momentum”

Recently, Quandl interviewed a senior quantitative portfolio manager at a large hedge fund. We spoke about how she builds trading strategies–how she transitions from an abstract representation of the market to something concrete with genuine predictive powers. Can you tell us how you design new

Ben Carlson of A Wealth of Common Sense has a recent post, When Global Stocks Go On Sale, outlining that it is typically a pretty good time to be buying when the MSCI World stock index is in a 20% or greater drawdown. His insightful takeaway and chart outlining the historical drawdowns and forward

“A stop order is an order placed with a broker to sell a security when it reaches a certain price. A stop-loss order is designed to limit an investor’s loss on a position in a security” —investopedia. In this article we investigate how the addition of stop-loss orders affect a generic

I’m running a high risk of running out of movies with “short” in the title. So this had better be the last blog post on the subject! In my previous post (here), I looked at a short-sale signal where a stock was shorted after it averaged 3% gains each day over five days (in any distribution).

First draft of 'JavaScript for Financial Analysts' Chapter 15. ~ Like all superheroes JavaScript's biggest strength is also its main weakness. JavaScript can be distributed and run anywhere, easily. The problem is that each browser or platform supports a slightly different subset of

In the book, Short Term Trading Strategies that Work, which Larry Connors and I published in early 2008, we wrote about a simple strategy called “Double 7’s Strategy.” Through the years people often ask about this strategy. Does something that simple really work? How does it do in a portfolio?

In this article I will test a well-known relative strength trading model using ETFs. The test period will include the data between 01/01/2001 – today. The starting hypothetical balance will be $100,000. The ETFs I will be testing are as follows: IYZ (Telecoms) XLB (Materials) XLE (Energy) XLF

Summary We’ve heard from several market participants that they feel that markets have “gotten faster” lately. We define two quantitative measures of speed and examine how speed has evolved since the 1920s We demonstrate that market speed is actually well within normal ranges – but perhaps

Because volatility seems to cluster in real life as well as the markets, it has been a while since my last article. Sorry about that. Today we will be taking our first giant leap along A Non-Random Walk down Wall Street. The Non-Random Walk Series A Non-Random Walk Down Wall Street is the cheeky

Our friends at Alpha Architect just wrote a great piece titled "Even God Would Get Fired as an Active Investor." In the study, they show that while an omnipotent investor with perfect foresight would have delivered great returns over the long run, he would be fired many times along the way

We study the out‐of‐sample and post‐publication return predictability of 97 variables shown to predict cross‐sectional stock returns. Portfolio returns are 26% lower out‐of‐sample and 58% lower post‐publication. The out‐of‐sample decline is an upper bound estimate of data mining

My previous post was about my thoughts concerning general architecture of a trading platform. During my way rethinking it from end to end it becomes clear that a “client only” approach would not fit with my needs. So I went back to my list of entities and started the puzzling again. To see all