Quantocracy

Quant Blog Mashup

ST

Quantocracy’s Daily Wrap for 12/01/2023

This is a summary of links featured on Quantocracy on Friday, 12/01/2023. To see our most recent links, visit the Quant Mashup. Read on readers!

  • Cloud or Local: Where to Run Your Quant Trading? [Quant Rocket]

    Is it better to run your quant trading in the cloud or locally? In this article, I outline the pros and cons of each approach and explain why running locally is often better for research while running in the cloud is better for live trading. Don't assume the cloud is better It's common to imagine that every serious workload should run in the cloud. We associate the cloud with modern,

Quantocracy’s Daily Wrap for 11/29/2023

This is a summary of links featured on Quantocracy on Wednesday, 11/29/2023. To see our most recent links, visit the Quant Mashup. Read on readers!

  • What is a robust stochastic volatility model research paper [Artur Sepp]

    I would like to share my research and thoughts about stochastic volatility models and, in particular, about the log-normal stochastic volatility model that I have been developing in a series of papers (see introductory paper with Piotr Karasinski in 2012, the extension to include quadratic drift with Parviz Rakhmonov in 2022, and application of the model to Cheyette interest rate model and to
  • Commodity carry as a trading signal part 2 [SR SV]

    Carry on commodity futures contains information on implicit subsidies, such as convenience yields and hedging premia. Its precision as a trading signal improves when incorporating adjustments for inflation, seasonal effects, and volatility. There is strong evidence for the predictive power of various metrics of real carry with respect to subsequent future returns for a broad panel of 23
  • A New Book Takes A Deep Dive At Solving The Portfolio Problem [Capital Spectator]

    Financial wisdom is said to be cyclical rather than cumulative, but thats unfair. At least in the dominion of portfolio management and design, academics and money managers have made great strides in decoding Mr. Markets cryptic signals over the past half century. The challenge, having led the proverbial horse to water, is making him drink. The stakes are high. History, in fact,
  • Statistical Shrinkage (4) – Covariance estimation [Eran Raviv]

    A common issue encountered in modern statistics involves the inversion of a matrix. For example, when your data is sick with multicollinearity your estimates for the regression coefficient can bounce all over the place. In finance we use the covariance matrix as an input for portfolio construction. Analogous to the fact that variance must be positive, covariance matrix must be positive definite to

Quantocracy’s Daily Wrap for 11/28/2023

This is a summary of links featured on Quantocracy on Tuesday, 11/28/2023. To see our most recent links, visit the Quant Mashup. Read on readers!

  • A Guide to Forecast Scalars [Return Sources]

    In my last post about the overnight anomaly, I created a trading signal based on the difference between recent overnight returns and recent intraday returns. I calculated the signal for various time frames (ranging from about a week to about a year), and I mentioned that I applied different forecast scalars to each time frame. I didnt really elaborate what a forecast scalar is, and I
  • Overlapping Momentum Stocks – do they cause outperformance? [Alpha Architect]

    Momentum investors utilize different timeframes to identify high momentum equities: past 6, 9, 12 months as an example. Obviously, there is a significant degree of overlap in momentum stocks identified across various past time frames. However, there has been little research focused on understanding the characteristics of momentum stocks formed on six and 12 months that overlap one another. The

Quantocracy’s Daily Wrap for 11/26/2023

This is a summary of links featured on Quantocracy on Sunday, 11/26/2023. To see our most recent links, visit the Quant Mashup. Read on readers!

  • Improving the default plot timescale for backtesting in R [Babbage9010]

    Default plots often include a few or many bars of misleading data where a strategy may have zeros or NAs compared with the benchmark, for example where the strategy uses a moving average lookback period before generating a trade signal. Theres a simple way to start the plot after the strategy is generating signals, and it improves quality of the stats generated too. I dont see this tip often
  • Covered calls: are investors making a devil’s bargain? [Alpha Architect]

    Many retail investors focus on generating what they consider to be income, leading to the popularity of dividend-focused strategies. To take advantage of this demand, investment firms have marketed covered call strategies that are purported to not only generate income but also reduce volatility. Covered calls involve selling call options on a security owned by a fund in exchange for a premium. The

Quantocracy’s Daily Wrap for 11/21/2023

This is a summary of links featured on Quantocracy on Tuesday, 11/21/2023. To see our most recent links, visit the Quant Mashup. Read on readers!

  • The Overnight Anomaly: Alive and Well [Return Sources]

    In finance, the overnight anomaly is the name for the unusual phenomenon that overnight stock market returns are much higher than intraday returns. In a 2008 paper, Return Differences between Trading and Non-trading Hours: Like Night and Day, the authors break down the U.S. equity premium into its night-time and day-time components, and find that the entire premium is due to night
  • A Long-Term Look at the Wednesday Before Thanksgiving [Quantifiable Edges]

    Thanksgiving week has shown some strong seasonal tendencies over the years. Ive documented this in years past on the blog. From a seasonal standpoint, Wednesday before Thanksgiving is one of the most bullish trading days of the year. The chart below shows performance from Tuesdays close to Wednesdays close on the day before Thanksgiving. SPX performance on Wed before Thanksgiving It

Quantocracy’s Daily Wrap for 11/20/2023

This is a summary of links featured on Quantocracy on Monday, 11/20/2023. To see our most recent links, visit the Quant Mashup. Read on readers!

  • Exponentially weighted covariance in an Equal Risk Contribution portfolio optimisation problem [Robot Wealth]

    The Equal Risk Contribution (ERC) portfolio seeks to maximally diversify portfolio risk by equalising the risk contribution of each component. The intuition is as follows: Imagine we have a 3-asset portfolio Assets 1 and 2 are perfectly correlated (correlation of 1.0) Asset 3 is uncorrelated with the other two (correlation of 0.0) Lets say we equal-weighted the three assets. Wed have 33% in
  • Takeaways from QuantMinds 2023 [Cuemacro]

    Its been exactly a decade since I attended my first QuantMinds event. At the time, it was called Global Derivatives, and as the name suggests, it was very much focused towards option pricing and its associated areas. It was held for a number of years in Amsterdam, at the Okura Hotel (whilst I cant remember what the burgers were like, I can safely say the sushi was excellent year), and then
  • Statistical Shrinkage [Eran Raviv]

    Imagine youre picking from 1,000 money managers. If you test just one, theres a 5% chance you might wrongly think theyre great. But test 10, and your error chance jumps to 40%. To keep your error rate at 5%, you need to control the family-wise error rate. One method is to set higher standards for judging a managers talent, using a tougher t-statistic cut-off. Instead of the usual
  • Commodity carry as a trading signal part 1 [SR SV]

    Commodity futures carry is the annualized return that would arise if all prices remained unchanged. It reflects storage and funding costs, supply and demand imbalances, convenience yield, and hedging pressure. Convenience and hedging can give rise to an implicit subsidy, i.e., a non-standard risk premium, and make commodity carry a valid basis for a trading signal. An empirical analysis of carry
  • Research Review | 17 November 2023 | Return Expectations [Capital Spectator]

    Causes of Deviations from a Real Earnings Yield Model of the Equity Premium Austin Murphy and Zeina N. Alsalman (Oakland University) October 2023 A market-based forecast of inflation added to equity earnings yields explains much of the variation in stock market returns over multi-year horizons. Return deviations from the prediction are found to be negatively related to the current inflation rate

Quantocracy’s Daily Wrap for 11/15/2023

This is a summary of links featured on Quantocracy on Wednesday, 11/15/2023. To see our most recent links, visit the Quant Mashup. Read on readers!

  • Military Expenditures and Performance of the Stock Markets [Quantpedia]

    Si vis pacem, para bellum, is an old Roman proverb translated to English as If you want peace, prepare for war, and it is the main idea behind the military policy of a lot of modern national states. In the current globally interconnected world, waging a real hot war has very often really negative trade and business repercussions (as the Russian Federation realized in 2022).
  • Using time series lag() in R finance [Babbage9010]

    Backtesting quant strategies in R requires paying attention to how we lag() our time series. Here be dragons. Lagging a time series relative to another is important in many areas, but we use it a lot in backtesting financial strategies. Ive struggled with the logic of lag() several times, and gotten it wrong more than once. And different packages within the R universe apparently use lag()
  • Sector Rotation Strategy: Should Trading Rules Make Sense? [Alvarez Quant Trading]

    I was doing my usual reading when I came across a sector rotation strategy. I have seen lots of these strategies but this one had a different twist. The strategy was a momentum strategy but instead of buying the top three, it was buying the middle three. The article gave no reason other than it works and gives the best results. In general, people fall into two camps about trading rules. The

Quantocracy’s Daily Wrap for 11/14/2023

This is a summary of links featured on Quantocracy on Tuesday, 11/14/2023. To see our most recent links, visit the Quant Mashup. Read on readers!

  • Small Trader Alpha: An Arbitrage Strategy in SPY Options [Return Sources]

    In this post, I'll discuss in detail an arbitrage trade in SPY options that I'd been running for about a year. (Some of you may have read a short version of this in this twitter post). I'm no longer using it, but it's still a viable strategy to earn some extra money. To be clear, this is a very low capacity trade; I made about 5 thousand dollars with it over a year, and I
  • Inflation surges – how long to return to normal? [Alpha Architect]

    How long will it take for the current level of inflation to subside? If history is any guide, it could take quite a while. Across 198 policy interest rate hikes of at least 1%, a decrease of 1% in inflation took 2 to 4 years (Havranke and Rusnak, 2013). The authors of this research article conduct an empirical analysis of the behavior representative of inflation to provide a realistic context for

Quantocracy’s Daily Wrap for 11/12/2023

This is a summary of links featured on Quantocracy on Sunday, 11/12/2023. To see our most recent links, visit the Quant Mashup. Read on readers!

  • Wiener Khinchin theorem and Gaussian processes [OS Quant]

    The Wiener-Khinchin theorem provides a clever way of building Gaussian processes for regression. Ill show you this theorem in action with some Python code and how to use it to model a process. The Wiener-Khinchin theorem states that an autocovariance function of a weakly stationary process is a function of the power spectral density and vice versa. These two are called Fourier duals and can be

Quantocracy’s Daily Wrap for 11/11/2023

This is a summary of links featured on Quantocracy on Saturday, 11/11/2023. To see our most recent links, visit the Quant Mashup. Read on readers!

  • An Expenonetially Weighted Covariance Matrix in R [Robot Wealth]

    Exponential weighting schemes can help navigate the trade-off between responsiveness and stability of the inherently noisy estimates we make from market data. We previously saw examples of calculating the exponentially weighted moving average of a vector, and estimating the correlation between SPY and TLT using an exponential weighting scheme [link]. In this article, well implement an
  • Quant_rv performance over three decades [Babbage9010]

    In recent posts we added nATR as a vol measure, went short instead of flat, and significantly improved quant_rvs performance over our in-sample test period 2006-2019. Now we look at the more recent record including the Covid Swoon and Inflation Coaster, and the years prior from the Roaring 90s through the Dot Com Crash. Short take: this was not a strategy anyone would have chosen before the
  • The Performance of Major Private Equity/LBO Firms [Alpha Architect]

    Attracted by the glamour and potential for lottery-like returns, global private equity (PE) assets under management reached $4.2 trillion in 2022. PE involves pooling capital to invest in private companies by providing venture capital (VC) to startups or by taking over and restructuring mature firms via leveraged buyouts (LBOs). PE investors believe that the benefits outweigh the challenges not