mean reversion ii pairs trading strategies deutsche bank

Highlights

This Deutsche Depository financial institution research shows how to improve pairs trading with RavenPack's news analytics. Their enhanced signal significantly reduces discrepancy risk and too boosts the average return per pair.

The portion of non-converged pairs dropped by about half from 15% to 7%.
Average profit per pair magnified from 2.3% to 2.8% for the European strategy, and from 1.6% to 1.9% for the US Scheme.
Return distribution becomes much positively skewed.

Below is a pairs example for Sports Direct International plc and Dixons Carphone plc 'tween November 2022 to January 2022.

mean reversion

Whole, the Sports Exact Intl price dropped by more than 40% over a full stop of two months. Understandably, trading the pair would have realised a loss. However, with access code to a time period news analytics feed, the loss could have been avoided by ignoring partner off trades with damage divergence supported by negative opinion and abnormal news program loudness on either of the ii companies (in this pillowcase, "Sports Direct Intl.").

mean reversion

Albumen Report

In a early report, Deutsche Bank discussed cross-sectional mean reversion strategies in equity markets. Pairs trading, which attempts to exploits a impermanent mispricing between ii securities with a stable relative price human relationship, is another type of mean reversion scheme. In that report, Deutsche Bank show how you can improve both the survival of the fittest and trading aspects of a conventional pairs trading scheme.

Fundamental risk models help to identify profitable pairs

Pairs trading strategies typically anticipate co-integrated relationships between stocks belonging to the same country and sphere/industry group. They believe on that point are superior means with which to enchant the level of "fundamental similarity" betwixt stocks. For example, they show that utilizing a fundamental risk model to nam stock pairs significantly reduces divergence risk, and also improves the average return per pair.

Word analytics overlay to further enhance pairs trading performance

Divergence risk increases in the symmetry of idiosyncratic risk associated with a pair's constituent stocks. A news analytics overlay which helps to differentiate between price divergence due to news as opposed owed to random price movements, importantly improves the performance of the trading scheme by reduction the number of non-convergent trades.

Beyond stock pairs

In looking for potential pairs candidates, they do not hold to limit ourselves to stock pairs. Deutsche Bank proposes a novel method supported bunch and dynamic tree-cutting to systematically place clusters of stocks as latent constituents for synthetic pairs trading strategies.

mean reversion

Introduction
Pairs Trading: The Basics

Existing Pais Trading Approaches
The Benchmark Strategy

An Increased Pairs Trading Model

Identifying Pairs Using a Fundamental Risk Model
Applying A News Analytics Overlay to Pairs Trading

An Addendum to Stock Pairs
Conclusions
References
Cecal appendage

Summarizing the Results

mean reversion Peter Hafez - Top dog Data Scientist - RavenPack

mean reversion

The rule of pairs trading is remarkably unsubdivided, but the devil is in the detail.

An investor finds assets whose prices emotional in collaboration historically, open a trade away shorting the winner and buying the loser when the spread between them widens. The trade is closed when the spread converges. Only that is not thus simple...

Complete the years, pairs trading has become one of the most fashionable applied mathematics arbitrage strategies. The strategy exploits parttime anomalies betwixt prices of assets that have some equipoise relationship. While methods may differ in mundanity, all implementations swear on the use of statistical psychoanalysis of historical prices to identify pair candidates with stabile bury-relationships.

The main dispute in building such strategies is that, often, cointegration between ii assets breaks pile out-of-sample – making the trade a losing proposition.

Fundamental Similarity

In an set about to solve the gainsay of cointegration breakdown, investors can profit from looking for pairs that have some degree of "fundamental similarity". Typically, pairs trading programs are looking for cointegration relationships between stocks belonging to the Lapplander country and sector/industry group.

However, In a past study, Deutsche Bank utilized a risk model to proxy fundamental similarity. Overall, they found that taking such glide slope importantly reduced divergence risk across their portfolio, and also improved the mean return per copulate.

Differentiating Between "White" and "Tough" Divergence

Even though fundamentally mistakable stocks are more likely to move in tandem in the near hereafter, there are no guarantees for such behavior. Considering any several stock, a large balance of the damage apparent motion is driven by idiosyncratic lay on the line, which could permanently alter the sense of equilibrium relationship between a company pair.

The profits and risks from trading stock pairs are rattling much related to the character of information result which creates divergence. If divergence is caused by a piece of news related specifically to one constituent of the twin, on that point is a good chance that prices bequeath depart further. But then, if divergence is caused by random price movements or a differential reaction to common selective information, convergence is more likely to follow afterward the initial divergence.

To tryout the effects of news on a pairs trading scheme, Deutsche Bank used two aggregated indicators based on RavenPack's Big Data analytics copied from news and social media data measuring sentiment and media attention. Specifically, using the two indicators, Deutsche Rely created a percolate that would ignore trades where disagreement was supported away negative sentiment and abnormal news volume. Figure 16, from the report, illustrates the pairs trading process with the news cover.

mean reversion

Below is an overview of Deutsche Bank's winder findings - applying the RavenPack Openhanded Data analytics overlay (see Forecast 17):

Lower Divergence Risk: the percentage of not-converged pairs born by finished a half from 15% to 7%
High Return: average profit per pair also raised from 2.3% to 2.8%, and the return distribution becomes more positively skewed
Significant P-Values: the increase in median returns is confirmed by significant p-values (danlt;0.05) from the slanted pair off-heady t-test

mean reversion

Figure out 19, from the report, shows the results of the pairs strategies practical happening the MSCI U.S. universe. As terminate be seen from the graph, the same conclusions can beryllium reached, albeit the strategies have relatively glower returns in the U.S. The moderate return per pair low-level the benchmark strategy, the increased strategy using the risk theoretical account, and the final strategy with both risk model and word overlay are 0.2%, 1.6% and 1.9% respectively.

mean reversion

Overall, Deutsche Bank finds that applying a news show analytics overlay potty help differentiate between "angelical" price divergence (which is presumptive to converge) from "bad" difference. To a greater extent importantly, such power provides significant improvements to the performance of a traditional pairs trading scheme, especially by reducing divergence risk.

Click Here to download the PDF and bear on reading the "Mean Reversion II: Pairs Trading Strategies" Flannel Paper

Request White person Paper