FactorResearch publishes a white paper on building multi-factor models. SUMMARY Three common approaches for creating multi-factor portfolios are the Combination, the Intersectional and the Sequential models The results from the Combination and Intersectional models are comparable in terms of trend

The simple fact that the SPX posted a gain on the first 4 days of the year is a pretty rare occurrence, with 2018 only being the 9th instance since 1961. While instances have been low, the intermediate-term performance following such strong starts to the year has been impressive. And looking at most

This is the second in a multi-part series in which we explore and compare various deep learning tools and techniques for market forecasting using Keras and TensorFlow. In Part 1, we introduced Keras and discussed some of the major obstacles to using deep learning techniques in trading systems,

It is that time of year again, the American Finance Association Annual Meeting is underway. The conference is in Philadelphia, starting today (January 5) and running through Sunday (January 7). This 3-day conference has 73 sessions, 246 papers and 12 presentations with no papers (general

We have just published a white paper showcasing the benefits of hedging a sentiment signal using risk factors from several MSCI Barra Risk Models. In this post, I provide some details on the methodology used for the strategy and on the achieved results. Excess returns: Ignores several risk factors

A few weeks ago, we did a deep dive into the factors versus characteristics debate. One of the reasons we’ve brought up this debate is due to the fact that “factor” loadings (from regressions) are arguably not as helpful as portfolio characteristics. In other words, knowing a portfolio P/E

As traders, we of course need money to make money, but not everyone has 10-50k of capital lying around to start one's trading journey. Perhaps the starting capital is only 1k or less. This article describes how one can take a small amount of capital and multiply it as much as 10 fold in one

Back in June of 2016, I wrote this post about random entries and trailing exits. It turns out (on average) that you can beat buy-and-hold of the S&P 500 by simply buying members of the S&P 100 randomly, as long as you a) have a market-timing filter, and 2) have a trailing stop of 20%. Yes

The “January effect,” in common with the “Halloween indicator” and “sell in May and go away”, is a catchy, get-rich-quick investment idea adored by financial commentators because it is so easy to explain to unsophisticated readers. It rests on the claim that the U.S. stock market

Last night’s subscriber letter featured (an expanded version of) the following study, which looks at performance in the 1st couple of days following a positive 1st day of a new year. 2018-01-03 The stats and curve all suggest some immediate follow-through has been typical. There have now been 9

Deep learning is an active area of research in machine learning. I train deep feedforward neural networks (DFN) based on a set of 68 firm characteristics (FC) to predict the US cross-section of stock returns. After applying a network optimization strategy, I find that DFN long-short portfolios can

Blogging was light in December. We spent the month working on the launch of a new fintech project that many of our readers will be excited about. We’ll be sharing details in the coming month and getting back to our regular blogging and site development schedule. — Allocate Smartly This is a

In statistics, the null hypothesis is the default statement that you test with data. From this test, you can either reject the null hypothesis in support of an alternative or assert that there is not enough evidence to believe anything other than the null hypothesis with a certain degree of

2017 was a positive year for most factors Quality, Growth and Momentum showed the strongest performance Value, Dividend Yield and Size generated negative returns INTRODUCTION We present the performance of seven well-known factors on an annual basis for the last 10 years and the full-year 2017. It is

In the last few years, deep learning has gone from being an interesting but impractical academic pursuit to an ubiquitous technology that touches many aspects of our lives on a daily basis – including in the world of trading. This meteoric rise has been fuelled by a perfect storm of: Frequent

In the previous post, we looked at some statistical properties of the empirical distributions of spot SPX and VIX. In this post, we are going to investigate the mean reverting and trending properties of these indices. To do so, we are going to calculate their Hurst exponents. There exist a variety

So many research papers, so little time. How do you separate the wheat from the chaff? You might start with the following five economic and financial papers that appeared in The Capital Spectator’s Research Review column in 2017. In a sea of newly minted studies over the past 12 months, these

Conventional wisdom can be defined as ideas that are so accepted that they go unquestioned. Unfortunately, conventional wisdom is often wrong. Two great examples are that millions of people once believed the conventional wisdom that the Earth is flat, and millions also believed that the Earth is the

This paper examines persistence in the cryptocurrency market. Two different longmemory methods (R/S analysis and fractional integration) are used to analyse it in the case of the four main cryptocurrencies (BitCoin, LiteCoin, Ripple, Dash) over the sample period 2013-2017. The findings indicate that

Since December, bitcoins can not only be traded at more or less dubious exchanges, but also as futures at the CME and CBOE. And already several trading systems popped up for bitcoins and other cryptocurrencies. None of them can claim big success, with one exception. There is a strategy that easily

What are the research questions? Given the prevalence of buybacks as a form of corporate payouts, should they be explicitly included in supply-side models such as the dividend discount model (DDM) used to forecast of stock returns? Does the same superior performance extend to the prediction of

Yesterday I decided to examine performance of XIV during the last few days of the year. The thought was that we are now in a time period that is generally regarded as seasonally bullish. Additionally, volume and volatility are often light this week with many traders on vacation. So I thought with

An investment in knowledge pays the best interest. (Benjamin Franklin) December 2017. Reading Time: Several hours. Author: FactorResearch. SUMMARY Contains 34 research papers that we published on FactorResearch.com in 2017 Focus on factor investing and quantitative strategies from an investor’s

Well here we are, another year gone (and so fast too!). I’m glad you could join me for this final episode for 2017, where we’ll be reviewing all of the special guests we had on the show this year, the topics and insights they’ve shared plus their top trading lessons. I think this is a great

During a time of year that is renowned for its low volatility and bullish seasonality, one might think XIV would have some strong historical returns. Well… 2017-12-25 …one would be wrong. Happy Holidays anyway!

Put that machine learning tutorial down. Machine learning is for closers only. As some of you that were around back in the early of this blog may know, I always held high hopes for the application of machine learning (ml) to generate trading edges. I think like many people first coming across

Strategy: core directional choices that best best moves you into your desired future Tactics: specific actions that will best implement your strategies Without a core strategy to anchor all tactics suggestions to see which best FIT (feasible, impactful, timely) the strategy, one could randomly

There has been much discussion of the small-cap premium recently. Has its popularity cannibalized its utility? Are large firms preventing a level playing field? Will the small-cap premium exist going forward? This article does not address these concerns directly, but it does identify and analyze

This post will be about investigating the efficacy of contango as a volatility trading signal. For those that trade volatility (like me), a term you may see that’s somewhat ubiquitous is the term “contango”. What does this term mean? Well, simple: it just means the ratio of the second month of

The academic research has generally found valuations, such as the earnings yield (E/P) (or the CAPE 10 earnings yield) and valuation spreads, have predictive value in terms of future returns. The higher the earnings yield, the higher the expected return, and the larger the spread in valuations

Carry trade returns vary across fixed and floating currency regimes. Over the last century, outsized carry returns occur exclusively in the floating regime, being zero in the fixed regime. The absence of skewness in floating carry returns rules out a skewness-based explanation for this result.

Is it possible to foresee the future movements of a stock? Let’s use Machine Learning techniques to predict the direction of one of the most important stock indexes, the S&P 500. Pregaming The Standard & Poor’s 500 (S&P500) is a stock market index based on the capitalization of the

Trend-following is something I’ve struggled with for years — always felt like voodoo magic and data-mining. That said, I finally came around to appreciating the practice after a ton of research replication efforts, independent research. At the time I was investigating the topic there really

Are cryptocurrencies potentially useful portfolio diversifiers? In their November 2017 paper entitled “Exploring the Dynamic Relationships between Cryptocurrencies and Other Financial Assets”, Shaen Corbet, Andrew Meegan, Charles Larkin, Brian Lucey and Larisa Yarovaya apply a battery of tests

Pairs trading is a nice example of a strategy based on mathematical analysis. We’ll demonstrate how to leverage data to create and automate a pairs trading strategy. Underlying Principle Let’s say you have a pair of securities X and Y that have some underlying economic link, for example two

Does the industry concentration exhibited in short sellers’ holdings convey new material information about the industry? Are the excess returns obtained from industry shorting combined with firm-specific shorting strategies explained by risk? Is the industry shorting signal correlated with

Traditional value strategies simply sort the investment universe based on one or more valuation metrics (e.g. book-to-market, price-to-earnings, etc.) and purchase the securities that look the cheapest. However, this process is often prone to structural sector bets, which are uncompensated sources

Value & Size generate abnormally large positive returns in January, Momentum negative returns Abnormal returns are limited to the last week of December and first week of January Difficult to harvest these returns efficiently due to illiquidity of markets at these times INTRODUCTION At this time

In this blog, we will step by step implement a machine learning classification algorithm on S&P500 using Support Vector Classifier (SVC). SVCs are supervised learning classification models. A set of training data is provided to the machine learning classification algorithm, each belonging to one

Andreas Koukorinis lives in London and in 2013 he co-founded Stratagem Technologies—a tech startup using AI and machine learning to trade sports as a financial product. These sports predominately include; football, tennis and basketball. But for Andreas, his roots are in trading instruments and

Asian options are path-dependent options whose payoff depends on the average value of the underlying asset during a specific set of dates across the life of the option. Because the payoff of the Asian options depends on the average value of the underlying asset, volatility in the average value is

The US stock market has been on a tear lately. Has the party gone too far? A rising chorus of analysts say that caution is advised, citing several valuation metrics. The Shiller PE Ratio, for instance, is currently at its second-highest level since the late-1800s. Valuations appear stretched, but

Here is a link to our recent podcast on Behind the Uniform. I’m so humbled and honored to have Wesley Gray on the show today, talking about his experience building Alpha Architect. I found Wes through a Wall Street Journal article that starts with: “Wesley Gray’s value-focused fund of overseas

You should have a plan for when you screw things up because I can guarantee it will happen. This is the screw up I did last night and how I handled it this morning. Enjoy this unplanned post. The Nightly Ritual Each night for 250 days of the year, I do the following for my trading. Step 1: In the

In this mini series on Time Series modelling for Financial Data, so far we’ve used AR, MA and a combination of these models on asset prices to try and model how our asset behaves. We’ve found that we were able to model certain time periods well with these models and failed at other times. This

Clustering has already been discussed in plenty of detail, but today I would like to focus on a relatively simple but extremely modular clustering technique, hierarchical clustering, and how it could be applied to ETFs. We’ll also be able to review the python tools available to help us with this.

In the last article, we looked at correlations between Iron Condor returns and Iron Condor structures / trade management. Specifically, we started with the following list of areas to investigate: Correlation between Iron Condor strategy structure / management and result metrics Which result metrics

“Big data” is already a frequently-heard buzzword, both in the business analytics arena, but also in the field of high-performance scientific computing. Basically, “big data” encompasses the collection, processing, indexing and utilization of large-scale datasets. Some concrete examples

Finding quotes and historical data for Bitcoin and Bitcoin futures can be an adventure. Below I’ve assembled links to the online resources that I’ve been able to find. In many cases, data is available from multiple sources. I did not attempt to list all of them. BTC Quotes Yahoo Finance

This paper studies the relation between global foreign exchange (FX) return dispersion risk and the cross-section of currency momentum returns. We find robust empirical evidence that FX return dispersion is a priced risk factor and that it contains information beyond traditional factors. Currencies