In this article, we present recent performance results of a market neutral long/short equity trading strategy executed in weekly timeframe for minimum transaction cost impact and lower risk in bear markets.
No one knows whether a bear market is on the horizon but there are signs that after a multi-year uptrend fueled by cheap money equity markets are about to correct. At the same time bond markets are also correcting and the combined effect increases the risk of investments in 60/40 portfolio and related allocations. In addition, financialization of commodities via ETF products endangers the historical anti-correlation with equity markets and imposes limits on allocation to managed futures. One strategy that has the potential of filling the gap is market neutral long/short equity.
Long/short equity strategies involve taking both long and short positions so that a net profit is made while market exposure is minimized. …usually during bull markets long positions tend to be more profitable than short and the other way around during bear markets. Therefore, the profitability of a long/short strategy does not depend on market direction. The strategy is called market neutral when allocations to long and short positions are equal.
There are many ways of developing and executing these type of strategies. In this article we look at a strategy in the weekly timeframe based on factors (also known as features, predictors or attributes) engineered by DLPAL LS:
DLPAL LS uses primitive attributes of price action, and specifically the open, high, low and close, to extract features types in an unsupervised learning mode based on general feature clusters. Then, the program uses the extracted features in supervised learning mode to identify long and short candidates in a universe of securities. The long/short identification is based on a set of calculated features and the user has flexibility in ranking the results according to their values… Historical files of features can be generated for backtesting the strategies and for machine learning.
The strategy described below is applied to Dow 30 group of stocks but any other group can be used.
Time-frame: Weekly (adjusted data)
Strategy type: Market neutral long/short equity
Universe: All Dow stocks from current composition
Backtest period: 01/04/2016 – 02/02/2018
Reserved for weekly feature calculation: 01/03/2000 – 12/31/2015
Open positions: 15 long and 15 short
Position size per stock: Equity/30
Position entry/exit: Open of next weekly bar
Commission per share: $0.01
Score: P-delta × S
Buy the top 15 and short the bottom 15 stocks based on the score at the open of the week
Strategy performance (01/04/2016 – 02/02/2018)
Below are the equity curve, underwater equity curve and monthly returns table. (Click on images to enlarge.)
Below is a Monte Carlo simulation graph.
There is less than 5% probability of 3.5% or higher drawdown according to the simulation.
Weekly execution involves updating weekly data files, ranking stocks according to score and then clicking L/S Pdelta*S 50/50. An example for next week is shown below:
Note that after ranking for the score LS P-delta*S at N = +/- 0, stocks with zero significance S are eliminated and there are only 28 stocks left, 14 long and 14 short after clicking LS P-delta*S 50/50.
If you have any questions or comments, happy to connect on Twitter: @priceactionlab
Hedge funds can receive a free fully functional demo of DLPAL LS valid for one month. For more details and information on how to order a demo click here.