Creating your Own Mean Reversion Trading Strategy (Guide)

In this post, you will learn how to develop a mean-reversion trading strategy, as well as its merits and demerits. We explain what mean reversion is, whether it works, and the markets where it works. And we also explain how mean reversion is different from momentum trading.

Momentum trading: what is it?

Momentum trading is a method of trading where you go long or short in the same direction as the movement over the last defined periods. For instance, research shows that if you had been going long the best 20 stocks over the last six months and rebalancing monthly, you would have had a tremendous edge in the stock market and beaten the indices by a wide margin. While this edge was discovered in the early 1990s, it still worked well after it was revealed.

What is mean-reversion trading?

Mean-reversion trading is a trading method that exploits the tendency of the price to revert to its mean when it makes an exaggerated move to one side. It is the opposite of momentum and trend-following strategies which focus on trading in the direction of the momentum and moving to another asset when momentum wanes.

The mean-reversion strategy is based on the statistics concept of regression to the mean, which implies that outliers are abnormalities and the dataset would tend towards the mean value. It has been shown that this concept works in certain financial markets, such as the stock market. However, it doesn’t work in the commodity market.

Both mean-reversion and momentum strategies work in the stock market. But while mean reversion works in the short-term swing trading, momentum seems to work best in the medium/ long-term timeframe (3-12 months’ timeframes).

Do mean-reversion strategies work?

Of course, mean reversion works. However, it does not work in all markets. From our experience, it works best for stocks and less for other financial assets. It doesn’t seem to work in the commodity market.

Why do stock prices mean-revert?

One possible explanation could be the need for institutional investors to rebalance their portfolios, which creates both buying and selling pressures in different stocks. That is, as stocks go up and down, they become more liable to rebalancing: stocks that have risen for some time but are losing momentum are sold, while those that have fallen are bought. To put it differently, mean reversion is a result of profit-taking in overvalued stocks and buying interest in undervalued stocks.

Since both hedge funds and mutual funds have mandates on how to operate, as regards risk parameters and diversification, they are obligated to reshuffle their portfolio, and most often, this is against the prevailing trend.

One other aspect is short selling and arbitrage. As you know, short-sellers short overvalued stocks and buy undervalued stocks, effectively dampening both upside and downside moves. In the same way, arbitrageurs sell those that rise in value and buy those that fall in value.

Some popular indicators for the mean-reversion strategy

There are many indicators you can use to create a mean-reversion strategy. They are mostly oscillators and other indicators that can show overbought and oversold levels, as well as give indications about the likely mean value of the price. These are the common ones: ?

• The internal bar strength (IBS) indicator
• The stochastic indicator
• The Bollinger Bands
• Williams %R – does it work?
• The RSI indicator
• The ADX

Which other variables mean-revert?

It has been shown that even fundamental factors, such as earnings and returns, tend to mean-revert. For example, the best funds over the last three years, are not likely to be among the top funds over the next three years and vice versa.

Similarly, volatility has been shown to also mean-revert. Take a look at this average true range (ATR) of the S&P 500 since the year 2000:

The chart above is that a 25-day ATR in the S&P 500 from 2000 until April 2021. Note how volatility waxes and wanes, despite gradually rising as we approach 2021. After a spike, it comes down before spiking again.

Can you use a stop loss order when trading a mean-reversion strategy?

Almost all backtests show that mean-reversion strategies don’t work well with stop loss orders because the farther the price goes in that direction (against your position), the better the signal. As a result, stop-losses might be very detrimental to the strategy unless you set a very wide stop-loss order to prevent rare cases of catastrophic losses.

Sentiment indicators are mean-reverting

As you will come to realize soon, technical indicators are not the only mean-revertive indicators; sentiment indicators are also mean-reverting in nature.

An example is the put/call ratio, which measures the number of puts and calls traded daily, weekly, monthly, or any other timeframe you are looking at. This sentiment indicator serves as a measurement of the mood of the markets. it tends to show mean-reversion as you can see in the graph below, which is the put/call ratio for equities over the last three years:

Source: CBOE.

Since investors and traders tend to buy puts when equity prices go down, the put/call ratio can be used as a sentiment indicator for mean-reversion strategies.

Disadvantages of mean-reversion trading

Every strategy has its pros and cons, and mean reversion is not an exception. The disadvantages of mean reversion strategies include the following:

• They don’t let the profits run: With a mean-reversion strategy, you cut the winners and let the losers run, which is the opposite of what many trading experts recommend. But since you aim for a regression to the mean, you sell or close the position after a moderate move in your desired direction.
• Not easily compatible with the use of stop loss orders: As we pointed out above, mean-reversion strategies don’t easily work well with stop-loss orders. They tend to work better without stops, which can lead to huge losses.
• The profit distribution is slightly skewed to the right side of the x-axis: Trading outcomes of many mean-reverting strategies are not evenly (normally) distributed: The majority of the trades are winners around the mean, but at the same time, there are a few big losers. Mean-reversion strategies have thin right tails and fat left tails. While the win ratio is normally very high, the distribution often has more big losers than big winners. In the bar chart below, you can appreciate the high win ratio, but the left tail is “fat” while the right tail is “thin”:
• They require frequent trading: You need to trade quite frequently to be able to achieve a high CAGR. While this offers you a big sample of trades, which can be a good thing as it allows your trading edge to play out, it means you would pay a lot in trading commissions and also have higher chances of getting a slippage. However, the faith in a mean-reverting system can easily grind to a halt when you get the infrequent big loser. This is opposite to what happens in trend-following strategies which have more big winners than losers (the biggest risk in trend-following is that your account slowly bleeds to death.)
• A mean-reversion strategy is more likely to deteriorate quickly: With a mean-reversion strategy, you can make a lot of money for over a year, and the next year, your account starts bleeding out.

How to create a mean reversion strategy

Mean reversion strategies follow a simple principle: You buy when the asset has fallen significantly and sell when it has risen towards its mean value, or you short when the asset rises significantly above its mean price and cover your short when it falls to its mean or lower. Thus, you need a benchmark to establish the dynamic mean and a way to identify the levels you consider being significantly away from the mean.

Therefore, to create a mean-reversion strategy, follow these steps:

• Have an idea or a hypothesis: Make your hypothesis as precise as possible so that it can be easily tested.
• Gather the data for the product you want to test: The best data have little to no errors, and if possible, include delisted stocks to avoid survivorship bias.
• Make buy and sell rules: Let your trading rules have a few parameters/variables as possible to avoid curve-fitting the data to the past.
• Have exit criteria: While often overlooked, the exit is important. Mean reversion strategies work best when you sell on strength, but you can test exit with time stops to verify robustness. You can use based on n-days (time exit). Apply common sense and be street-smart, not academic smart. Keep it simple.
• Play around with optimization: This is necessary to find out how the strategy performs with other sets of values.
• Test out of sample with a demo account: Do this over a few months.

Final thoughts

Mean reversion is often intuitive — buy weakness and sell strengths. They are easy to understand, implement, and execute. However, they allow you to cut the winners and let the losers run. While mean reversion can be profitable, you need to diversify to different timeframes, instruments, and markets to reduce risks.

Read more similar articles here on?The Robust Trader?or on?Quantified Strategies

(The article is partly written by AI. You find our best content (non-AI) on our website - Quantified Strategies)