A simple equity Systematic Trading Strategy using one ratio.

Keywords: Put-call ratio, puts, calls, options, S&P500, trading, investing, systematic, quantitative, volatility.

A call option is the right to buy a certain asset in the future at a pre-determined price while a put option is the right to sell a certain asset in the future at a pre-determined price. Hence, when you buy a call you get to buy something later and when you buy a put you get to sell something later. Every transaction has two sides, therefore, when you’re buying a call or a put, another agent is selling them to you. This brings two other positions that can be taken on options, selling calls and selling puts. The put/call indicator deals with the buyers of options and measures the number of put buyers divided by the number of call buyers. That gives an idea on the sentiment of market participants around the specified equity (in our case it will be the S&P500 index). A higher put/call ratio means that there are more put buyers (traders are betting on the asset going lower) and a lower put/call ratio signifies more calls (traders are betting on the rise of the asset). A simple strategy can be elaborated on the extremes of the PCR which may predict a reversal of sentiment and hence of the S&P500's direction. Let’s back-test it. I’ve downloaded the total volume Put-Call ratio on the S&P500 since 2006 from the CBOE website, and have optimized a bit the conditions (with no risk management):

• When the PCR touches 1.20 -> Go long the S&P500 for 20 trading days.
• When the PCR touches 0.65 -> Go short the S&P500 for 20 trading days.

There is always a bias that the equity market is trending upwards and therefore, the short signals will have a bit less quality. Below are our triggers. Green is for buy orders and red is for short orders. I've allowed successive trading signals to allow the indicator to be in its natural state, therefore the only optimization done was on the holding period and the barriers.

The number of long signals is noticeably higher than the number of short signals and the signal quality seems to be slightly better (statistics below). Long signals seem to capture well the botoms of corrections and consolidations. The equity curve of the strategy is somewhat satisfying but still not 100% reflecting the reality (did we really know that this strategy will work back in 2006 if we hadn't had the results already?). Also, the returns are gross of fees even if they're a bit negligible:

The performance evaluation metrics seem to favour the long strategies due to the upward trending bias of the S&P500 and therefore, the interest shifts to the short positions' hit ratio which is a mere 52%. On a total risk-reward ratio of 1.27, a 52% hit ratio is not much. Again stating that this back-test was done in absolution (no risk management to handle stops and profits).

The below table is just to show the logic of the algorithm. The trade is initiated after the signal has been confirmed (row 21 showing a value below 0.65, thus opening a short position on tomorrow's close). We can further optimize and open the trade on tomorrow's opening bar. On row 30, is the result of a previous trade after 20 holding days have passed.

Conclusion

Will this strategy keep working for the forseeable future? That is hard to say but what is for sure, that it will take a long time to know. From the data above, in 13 years, we've only had 131 trades, amounting to 10 trades per year. Relaxing some conditions will give us 1 trade per month. It may not be bad for a sub-allocation of a portfolio to actively trade on this strategy assuming more optimization is done. The stats are not bad but way better than many known strategies. The back-test performed is a sanity-check of the predictive ability solely, it does not mean that after adjusting for risk, the strategy will still be adequate.

In a previous article (https://www.dhirubhai.net/pulse/forecasting-putcall-ratio-machine-learning-models-sofien-kaabar/), I've discussed forecasting the PCR using machine learning algorithms which in turn would use the results to forecast t + 1 S&P500 returns.