Quant Mashup Evolving Neural Networks through Augmenting Topologies – Part 2 of 4 [Gekko Quant]This part of the tutorial on using NEAT algorithm explains how genomes are crossed over in a meaningful way maintaining their topological information and how speciation (group genomes into species) can be used to protect weak genomes with new topological information from prematurely being eradicated(...) You don't need to be a scientist to build a backtesting algotrading system in Python [Jon.IO]This is the another post of the series: How to build your own algotrading platform. Last time we talked about The "for-looper" backtester (as I love to call them). Now it's time to see some code! We said that we have something like that: Bayesian Linear Regression Models with PyMC3 [Quant Start]To date on QuantStart we have introduced Bayesian statistics, inferred a binomial proportion analytically with conjugate priors and have described the basics of Markov Chain Monte Carlo via the Metropolis algorithm. In this article we are going to introduce regression modelling in the Bayesian(...) Bold, Confident & WRONG: Why You Should Ignore Expert Forecasts [GestaltU]If you read the paper, watch the news, and listen to investment experts you are doing it all wrong. There are no market wizards; the emperors have no clothes; most people are ‘swimming naked’. The following paragraphs offer abundant and incontrovertible evidence condemning expert judgment for(...) Build Better Strategies! Part 4: Machine Learning [Financial Hacker]Deep Blue was the first computer that won a chess championship, in 1996. It took 20 more years until another computer program, AlphaGo, could defeat the best human Go player. Deep Blue was a model based system with a fixed chess library and hardwired chess rules. AlphaGo is a data-mining system, a(...) Autoregressive model in S&P 500 and Euro Stoxx 50 [Quant Dare]In this post we are talking about autoregressive models and their application to a financial world. This model follows the idea that the next value of the serie is related with the p previous values. Definition of p-order autoregressive model An autoregressive model or AR is a type of modelling that(...) The Dynamic Duo Of Risk Factors: Part II [Capital Spectator]Last week’s post on analyzing US equity value and momentum risk premia ended with a question: How much, if any, improvement should we expect by adding a dynamic system for managing exposure to these risk factors vs. a buy-and-hold strategy? What follows is a preliminary effort in searching for an(...) Parallel Tempering and Adaptive Learning Rates in Restricted Boltzmann Machine Learning [Dekalog Blog]It has been a while since my last post and in the intervening time I have been busy working on the code of my previous few posts. During the course of this I have noticed that there are some further improvements to be made in terms of robustness etc. inspired by this Master's thesis, Improved(...) Benchmarking Commodity CTAs [Quantpedia]While much is known about the financialization of commodities, less is known about how to profitably invest in commodities. Existing studies of Commodity Trading Advisors (CTAs) do not adequately address this question because only 19% of CTAs invest solely in commodities, despite their name. We(...) How to Value Nadex Bull Spreads? [MKTSTK]Exotic options have always been a hobby of mine. One of the curious things about Dodd-Frank was it started to push swap trading onto exchanges. As such, a cottage industry of exchange traded exotics (in the US they're technically swaps) has popped up over the last few years. The biggest of(...) Trading the index with seasonal strategies [ENNlightenment]I recently listened to an interesting interview at Better System Trader with Jay Kaeppel on Seasonality, a topic which I hadn’t done much backtesting on previously. Jay outlined 3 rules for constructing a seasonal trading strategy on the stock index: - Stay long the last 4 days and first 3 days of(...) A Monte Carlo Simulation function for your back-test results – in R [Open Source Quant]In this post on bettersystemtrader.com, Andrew Swanscott interviews Kevin Davey from KJ Trading Systems who discusses why looking at your back-test historical equity curve alone might not give you a true sense of a strategy’s risk profile. Kevin Davey also writes on the topic here for(...) Machine Learning and Its Application in Forex Markets [Quant Insti]In the last post we covered Machine learning (ML) concept in brief. In this post we explain some more ML terms, and then frame rules for a forex strategy using the SVM algorithm in R. To use ML in trading, we start with historical data (stock price/forex data) and add indicators to build a model in(...) Glamour Can Distract Investors [Larry Swedroe]There’s very strong historical evidence to support the existence of a value premium in equity markets. While there’s no dispute over the existence of the value premium (value stocks have provided an annual average return 5% higher than growth stocks over the long term), there is much debate over(...) Best Links of the Week [Quantocracy]These are the best quant mashup links for the week ending Saturday, 03/26 as voted by our readers: FX: multivariate stochastic volatility – part 2 [Predictive Alpha] Predicting Stock Market Returns—Lose the Normal and Switch to Laplace [Six Figure Investing] Momentum for Buy-and-Hold Investors(...) Momentum for Buy-and-Hold Investors [Dual Momentum]There are many investors who prefer to remain invested in stocks at all times. Perhaps they think tactical allocation is some kind of voodoo. Maybe they have a strong psychological bias against occasional whipsaw losses and do not mind bear market drawdowns. Maybe they have institutional constraints(...) Momentum and Mean Reversion in Different Time Frames [Throwing Good Money]In a recent blog post, I rather glibly stated that the market tends to revert to a mean. A reader called me out about the time frame I was using, which raises a good point. A market can tend toward both mean reversion and momentum over different time frames. Many traders would argue that different(...) Spikes Can Explain Returns [Larry Swedroe]Recently there has been a lot of research on the question of whether higher moments of return other than volatility (specifically, the skewness of returns) helps to explain equity returns. (I’ve included a brief definition of skewness and a demonstrative example of it below.) For instance, the(...) On Backtesting: An All-New Chapter from our Adaptive Asset Allocation Book [GestaltU]If you've been a regular reader of our blog, you already know that we recently published our first book Adaptive Asset Allocation: Dynamic Portfolios to Profit in Good Times - and Bad. As of this writing, it still stands as the #1 new release in Amazon's Business Finance category.(...) The Comprehensive Guide to Stock Price Calculation [Quandl]Adjusted stock prices are the foundation for time-series analysis of equity markets. Good analysts insist on properly-adjusted stock data. But the best analysts understand the adjustment process from first principles. This is Quandl's guide to the creation and maintenance of accurate adjusted(...) Markov Chain Monte Carlo for Bayesian Inference - The Metropolis Algorithm [Quant Start]In previous discussions of Bayesian Inference we introduced Bayesian Statistics and considered how to infer a binomial proportion using the concept of conjugate priors. We discussed the fact that not all models can make use of conjugate priors and thus calculation of the posterior distribution would(...) Have benchmarks made us bad active investors? [Alpha Architect]Obsession with short-term performance against market cap benchmarks preordains the dysfunctionality of asset markets. The problems start when trustees hire fund managers to outperform benchmark indexes subject to limits on annual divergence… Benchmarking causes, first, the inversion of the(...) Responding to Your Comments on Our Adaptive Asset Allocation Book [SkewU]If you've been a regular reader of our blog, you already know that we recently published our first book Adaptive Asset Allocation: Dynamic Portfolios to Profit in Good Times - and Bad. As of this writing, it still stands as the #1 new release in Amazon's Business Finance category.(...) The Dynamic Duo Of Risk Factors: Part I [Capital Spectator]The value and momentum factors have earned high praise in recent years as complementary sources of risk premia for designing and managing equity portfolios. AQR’s widely cited paper “Value and Momentum Everywhere” a few years back helped popularize the idea, pointing to applications in(...) A Few Notes On Adaptive Asset Allocation [CXO Advisory]In the introductory text for Part I of their 2016 book, Adaptive Asset Allocation: Dynamic Global Porfolios to Profit in Good Times – and Bad, Adam Butler, Michael Philbrick and Rodrigo Gordillo state: “…we have come to stand for something square and real, a true Iron Law of Wealth Management:(...) Smart Beta Strategies in Australia [Quantpedia]"Smart beta" investing is an alternative to the traditional active and passive approaches to funds management, whereby investors adopt a systematic method that provides exposure to factors that are argued to be related with expected returns at low cost. Therefore, the question of how smart(...) [Academic Paper] Optimal Delta Hedging for Options [@Quantivity]The “practitioner Black-Scholes delta” for hedging options is a delta calculated from the Black-Scholes-Merton model (or one of its extensions) with the volatility parameter set equal to the implied volatility. As has been pointed out by a number of researchers, this delta does not minimize the(...) On the 60/40 portfolio mix [Eran Raviv]Not sure why is that, but traditionally we consider 60% stocks and 40% bonds to be a good portfolio mix. One which strikes decent balance between risk and return. I don’t want to blubber here about the notion of risk. However, I do note that I feel uncomfortable interchanging risk with volatility(...) Slides from Investing in Smart Beta Conference [Flirting with Models]Justin spoke at the Investing in Smart Beta conference this week in Fort Lauderdale, FL. He spoke alongside Research Affiliates in a session titled "The Smart Beta Checklist: Choosing The Best Strategy & Risk/Return Profile For Your Portfolio." Here's a quick description:(...) FX: multivariate stochastic volatility - part 2 [Predictive Alpha]In part 2 our mean-variance optimal FX portfolio is allowed to choose from multiple models each week based on a measure of goodness (MSSE). The risk-adjusted return improves as a result with the annualized Sharpe Ratio rising to 0.86 from 0.49. In part 1 we estimated a sequential multivariate(...) Server -IV- [Algorythmn Trader]The previous post was about the auxiliaries to provide some basic interfaces, classes and messages. This post is about the 3rd project for our basic server solution. This project will allow to run the simple server and enable to connect a client. The RunServer project should be a WinForm project to(...) Why Investors Should Combine Value and Momentum [Alpha Architect]In the past we have discussed how to combine value and momentum strategies to improve an equity allocation. In this piece we discuss why an investor should combine use value and momentum.* Many investors recognize that stand-alone value and momentum strategies have historically worked. Of course,(...) The More Unique Your Portfolio, The Greater Its Potential [Investor's Field Guide]If there is a lot of overlap between your portfolio and the market, there is only so much alpha you can earn. This is obvious. Still, when you visualize this potential it sends a powerful message. Active share—the preferred measure of how different a portfolio is from its benchmark—is not a(...) Beware bad multi-factor products [Flirting with Models]This post is available as a PDF here. Summary Multi-factor portfolios are a great way to diversify across multiple factors that can potentially create excess risk-adjusted returns while simultaneously smoothing out relative performance volatility. There are two ways we've seen manufacturers(...) When Trading Detracts From Alpha [Larry Swedroe]As explained in my latest book, “The Incredible Shrinking Alpha,” which I co-authored with Andrew Berkin, accompanying the rapid growth of the actively managed mutual fund industry, the average performance of mutual funds has been trending downward over the past few decades. Teodor Dyakov, Hao(...) Best Links of the Last Two Weeks [Quantocracy]The best quant mashup links for the two weeks ending Saturday, 03/19 as voted by our readers: How to Learn Advanced Mathematics Without Heading to University - Part 1 [Quant Start] When Measures Become Targets: How Index Investing Changes Indexes [Investor's Field Guide] Meet the DIY Quants Who(...) Predicting Stock Market Returns—Lose the Normal and Switch to Laplace [Six Figure Investing]Everyone agrees the normal distribution isn’t a great statistical model for stock market returns, but no generally accepted alternative has emerged. A bottom-up simulation points to the Laplace distribution as a much better choice. A well-known problem in financial risk assessment is the failure(...) Reflections on Careers in Quantitative Finance [Jonathan Kinlay]Carnegie Mellon's Steve Shreve is out with an interesting post on careers in quantitative finance, with his commentary on the changing landscape in quantitative research and the implications for financial education. I taught at Carnegie Mellon in the late 1990's, including its excellent(...) Price Breakout with NR7 | Trading Strategy (Setup & Entry) [Oxford Capital]I. Trading Strategy Developer: Toby Crabel (Setup: NR7 Pattern); Laurence A. Connors, Linda B. Raschke (Entry: Price Breakout with NR7). Source: (i) Crabel, T. (1990). Day Trading with Short Term Price Patterns and Opening Range Breakout. Greenville: Traders Press, Inc; (ii) Laurence A. Connors,(...) Free Resources to Learn Machine Learning for Trading [Quant Insti]While being a vibrant subfield of computer science, machine learning is used for drawing models and methods from statistics, algorithms, computational complexity, control theory and artificial intelligence. It focuses on efficient algorithms for inferring good predictive models from large data sets(...) Don’t Bother Timing Premiums [Larry Swedroe]Because of the magnitude, persistence, pervasiveness and robustness of their related premiums, several factors have dominated the academic literature. Among them are market beta, size, value, momentum and profitability. However, despite their persistence, each factor has undergone even fairly long(...) Meet the DIY Quants Who Ditched Wall Street for the Desert (h/t @AbnormalReturns)In the high desert plain of New Mexico, Roger Hunter monitors automated trades on hog futures and currency pairs. Roger Hunter in his home office. Roger Hunter in his home office. Photographer: David Paul Morris/Bloomberg Four computer screens display a dizzying array of price charts and program(...) “Let’s make a deal”: from TV shows to identifying trends [Quant Dare]How about trying to find any use of the famous Monty Hall problem in a stock index context? Let your imagination run… First of all, some of you may be confused because neither “Monty Hall problem” nor “Let’s make a deal” are familiar to you so I will refresh you what these names are(...) Justin's Take: Building a Portfolio for Resolve's March Madness Challenge [Flirting with Models]A Newfound, we try to embrace March Madness as an opportunity to foster some good-natured competition within the company. This year we decided to mix things up and go with our own version of ReSolve's unique March Madness Challenge. When Corey originally suggested the idea, my initial reaction(...) Covered Calls Uncovered [Quantpedia]Equity index covered calls have historically provided attractive risk-adjusted returns largely because they collect equity and volatility risk premia from their long equity and short volatility exposures. However, they also embed exposure to an uncompensated risk, a naïve equity market reversal(...) Never Book a Loss (And Why That’s Bad For You) [Throwing Good Money]I have got a great trading system for you. I mean, look at that equity curve! It’s very straight, no drawdowns, and $30,000, compounded, became almost $120,000 over time. What’s the catch? They say (and I’m not sure who “they” are) that the average retail investor hates to book a loss, and(...) Adding Stops and Scaling Out to a Mean Reversion Strategy [Alvarez Quant Trading]I came on an idea recently that I had tested. I have tested adding max loss stops to a mean reversion strategy, with no success. See this post for more on that. About eight years ago, I tested scaling out of trades. But this person claimed that adding the two together was how to improve a mean(...) The Seven Deadly Sins of Quantitative Data Analysts [Quandl]Sooner or later, every quant is tempted by forbidden fruit. These all-too-human traits can permeate even the most sophisticated analysis. Keep these tips in mind as you develop strategies, and you just may turn vice into virtue. Quandl_7_sins_v04 (1) Download the printable version here. Corey's Take: Building a Portfolio for ReSolve’s March Madness Challenge [Flirting with Models]The team over at ReSolve recently posted about their very unique March Madness Challenge. The crux of their idea is that the rules governing a more traditional bracket system is fundamentally flawed since it inherently reduces the sample size upon which skill is measured. For example, nearly(...) Price Breakout with NR7 | Trading Strategy (Filter & Exit) [Oxford Capital]I. Trading Strategy Developer: Toby Crabel (Setup: NR7 Pattern); Laurence A. Connors, Linda B. Raschke (Entry: Price Breakout with NR7). Source: (i) Crabel, T. (1990). Day Trading with Short Term Price Patterns and Opening Range Breakout. Greenville: Traders Press, Inc; (ii) Laurence A. Connors,(...)