Update of #AssetAllocation strats in my package with yesterday's return. Brutal.
Worst static allocation: Sandwhich -12.4% YTD
Worst tactical allocation: Dual momentum -7.9% YTD
Best (least worse) static: Conservative income -6.85%
Best tactical: Ivy +1.36%
YTD statistics for static allocations.
All max drawdown for the year = cumulative return
YTD statistics for tactical allocations:
Why is Ivy doing better? Commodities (DBC FTW)
• • •
Missing some Tweet in this thread? You can try to
force a refresh
Finally had a chance to read the published version of this paper. The authors train a convolutional neural network using images of price and volume charts to predict the direction of the stock.
The results are quite interesting and show a lot of promise in terms of developing a trading strat. Here's a figure showing decile returns and vols from portfolios constructed with signals from a CNN trained using images of past 5 days to predict direction of next 5 days return:
What is interesting with this type of paper is that I see a lot of reactions like: "See, this paper proves that technical analysis works!"
Like with many things nowadays, theres little room for nuance....
Our paper "Covid-19 and herding in global equity markets" (with @GersonJunior__) is now published in the Journal of Behavioral and Experimental Finance and freely available for 30 days using the link below.
In the paper, we investigate the presence of herding in 10 equity markets, with a particular focus on analyzing the Covid-19 period and comparing it with previous crisis period such as the 2007-2008 GFC.
The countries in the study (Australia, Belgium, Brazil, China, France, Italy, Japan, Sweden, the UK, and the US) were chosen because they show a remarkable diversity in terms of governments’ responses to pandemic as well as its impact and the timing of Covid-19 waves.
@WifeyAlpha recently posted a thread with 16 buy-and-hold asset allocation schemes, i.e. fixed-weight portfolios that can be implemented with ETFs. I decided to write some code to test these in #R#RStats. The code is available on #RPubs: rpubs.com/arubesam/stati…
The code is a quick & dirty calculation using monthly returns with monthly rebal. It does not take into account transaction costs. The code can be easily adapted to test other asset allocation schemes.
I use the following #R packages: quantmod to get prices from Yahoo; PerformanceAnalytics for calculation of performance metrics. All backtests start when data for all necessary tickers becomes available.
In the RPubs post above, I provide the #R code to backtest the strategy, as well as some results replicating Gatev, Goetzmann & Rouwenhorst (2006) and Do and Faff (2010), and extending the sample to the end of 2020. In this thread, I show some of these results.
Pairs trading is a type of systematic trading strategy based on finding pairs of stocks or assets that have historically "moved together", and betting that divergences will eventually get corrected. It is a simple form of statistical arbitrage.
I gave myself the challenge of reading (at least) one paper a day, every day. I'm considering keeping a live log in this thread. 🤔 I'll be generous with myself and also count any papers that I'm re-reading.
Yesterday's paper.
Beltz, A. M., & Gates, K. M. (2017). Network Mapping with GIMME. Multivariate Behavioral Research, 52(6), 789–804. doi.org/10.1080/002731…
21/06/2020 - Campbell, J. Y., & Shiller, R. J. (1987). Cointegration and Tests of Present Value Models. Journal of Political Economy, 95(5), 1062–1088.
Brushing up on several present-value papers starting in the 80s.