Tuesday, April 12, 2016

Pairs Trading: Using Structured News to Reduce Divergence Risk

Posted by at

A study by Deutsche Bank

The principle of pairs trading is remarkably simple. An investor finds assets whose prices moved together historically, open a trade by shorting the winner and buying the loser when the spread between them widens. The trade is closed when the spread converges. Although, it may sound simple…the Devil is in the detail!
Bookmark and Share

Over the years, pairs trading has become one of the most popular statistical arbitrage strategies. The strategy exploits temporary anomalies between prices of assets that have some equilibrium relationship. While methods may differ in sophistication, all implementations rely on the use of statistical analysis of historical prices to identify pair candidates with stable inter-relationships.

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

Tuesday, April 5, 2016

Can Earnings Sentiment Give Investors an Edge over Consensus?

Posted by at

Tracking company earnings is a key element of any fundamental trading strategy. Often, a short-term trading opportunity arises following the realization of a company either missing or beating market expectations. Gaining an edge on such information, however, is very difficult since there are literally millions of eyes on Wall Street looking at the same information. In a recent study, we considered whether earnings sentiment could provide the edge that everyone so much desires.
Bookmark and Share
Well, to address this question, we considered RavenPack Big Data Analytics derived from real-time news and social media content. More specifically, we leveraged RavenPack’s elaborate event taxonomy to track the sentiment of news tagged as being related to earnings, revenues or dividends, i.e. spanning anything from changes to analyst’s estimates or company guidance, to reported figures being better or worse than expected. This allowed us to move beyond the “hard numbers” to consider how earnings information is portrayed in the news from a sentiment perspective and how to weigh potentially conflicting information, i.e. positive historical results vs. negative future guidance.

Tuesday, September 29, 2015

Improving Equity Portfolio Performance With Thematic Alpha Streams

Posted by at
Using Sentiment to Create Theme-based Alphas
In our recent research, we have decided to approach sentiment on a thematic basis, meaning we separate out sentiment for different corporate event groups - earnings, M&A, analyst ratings being examples. This has delivered improved results for equity portfolios we construct - not just in terms of returns, but also increased diversification and lower turnover.
Bookmark and Share
This thematic, or alpha stream, approach differs to one of our legacy tactics where we aggregated sentiment across all event types - one dimensional and perhaps leading to too much smoothing.

The concept of alpha streams is very well known in the investment community, and there has been a fair bit of research into combining alpha streams, but little research exists on the actual alpha creation. Such know-how is usually kept secret by portfolio managers to maintain their edge.

Tuesday, July 7, 2015

Using Sentiment to Create Theme-based Alphas

Posted by at
Using Sentiment to Create Theme-based Alphas
Most sentiment analytics providers simply tell you a piece of information, or a day’s worth of information, is positive or negative. Indeed, in our past research, we have used simple aggregate measures of sentiment like moving averages. But stock prices do not react uniformly to sentiment across corporate event types. So, when building trading signals, it may be more profitable to treat sentiment thematically.
Bookmark and Share
To address this hypothesis, we conducted a study in which we dissected sentiment into event themes, according to RavenPack’s event taxonomy, identifying how the sentiment signal decays by event type. As part of our research, we considered the results by company size and region. In this particular paper we only looked at the performance of each theme-based indicator, but in future, this information could be used when deciding on the directionality of investing and/or holding periods related to the sentiment of particular event types.

You can request the full paper from our website.

The highlights of our findings included:

Monday, June 8, 2015

Apple Needs Good News From WWDC To Match Price Momentum

Posted by at
Apple Sentiment

Apple’s Worldwide Developers Conference kicks off in San Francisco Monday and it’ll be keenly watched by Apple fans and analysts alike for new product launches and enhancements. Positive news is definitely needed by Apple because sentiment momentum has lagged price over the last month or so.

Bookmark and Share
Figure 1 below shows the relative strength indicators (RSI) of Apple’s sentiment, derived from RavenPack News Analytics, against price RSIs. As you can see, shorter-term price momentum spiked into overbought territory late May and this wasn’t fully supported by a run higher in sentiment strength. That short-term move in price momentum is reflected in the longer-term price momentum edging higher. But there’s no corresponding move in sentiment.

Friday, May 15, 2015

At Face Value, US Q1 Earnings Surprise Not Supported By Sentiment

Posted by at
Earnings Picture

US first quarter earnings season is pretty much over so let’s take stock from an news analytics perspective. As pointed out by our partners, FactSet, the earnings surprise percentage so far this earnings season has been higher than average and potentially the highest since Q1 2011. Have we seen this in the news sentiment analytics?

Bookmark and Share
No. Although it has been a busy quarter in terms of media coverage of earnings and revenue events, relative sentiment remains slightly negative. That said, relative sentiment has picked up over the last couple of weeks.

Figure 1 shows the count of detections of these two event groups (the blue bars) for the US market as a whole. This measure of media attention for revenue and earnings has been the highest of the last year.
Figure 1: US Earnings & Revenue Sentiment RSIs & Media Attention

Wednesday, May 6, 2015

News Sentiment Helps Pick Turning Points In Price Momentum Factors

Posted by at

Factor investing is a term in more or less every portfolio manager’s vocabulary these days, but all managers face the challenge of understanding when risk premiums associated with traditional factors can be harvested and when they can’t.

Bookmark and Share
A large corpus of academic research, spanning more than 40 years, has highlighted the existence of long-term risk premiums linked to factors such as value, low size, low volatility, high yield, quality, and momentum. For instance, the concept of Value investing is to look for stocks that have low prices relative to their fundamental value – commonly captured by a high book-to-price or earnings-to-price ratio (amongst other measures).