Open Source Traffic Analysis to Find Lull in IMF Communications

[Cross-posted from the Recorded Future Blog]

Today we read in the Financial Times that not only might Portugal be better off than earlier thought (having successfully sold government bonds a few days ago), but also Spain and Italy:

…The debt sale has boosted the euro, peripheral eurozone bonds and sparked a sharp rally in bank stocks, on the assumption that it reduced the chances of Portugal needing a bailout and could provide a fire break to a feared sovereign debt conflagration. Indeed, a well-supported €3bn auction of Spanish notes and a reasonable €6bn sale of Italian debt on Thursday has increased hopes that the latest pulse of eurozone angst is fast subsiding…

There are many signals that might be used to judge the financial health of a country. Certainly interest spreads and demand for sovereign debt at auctions come to mind, and we previously considered commentary by IMF officials on this blog. We’ll now re-explore these types of discussions by focusing our analysis on Portugal.

Portugal in the News

Portugal has been in the media a lot over the last couple months as it faces similar challenges to Greece in terms of indebtedness. Comparatively timelining the raw momentum for Portugal and Greece shows us a similar set of media patterns.

Traffic analysis on IMF officials – Greece and Ireland

As a basis for doing analysis on IMF officials, we’ve constructed a Recorded Future Watchlist of 25-3o IMF officials as well as a watchlist of “risky countries” in Europe such as Spain, Italy, Portugal, etc., that are typically called out as potential problems when it comes to sovereign debt.

Looking at IMF officials discussing our list of risky European countries, you’ll see in the visualization below that commentary became both generally active as well as positive just before bail-outs of Greece and Ireland.

As for Greece, right before the Irish bailout we find positive IMF statements as well as general positive sentiment regarding Greece from them.

Now, what about Portugal?

Remember from our first visualization that there’s been plenty of coverage of Portugal recently at a level similar to Greece. But we should ask ourselves, what about IMF officials specifically? Are they lighting up in the context of Portugal?

So, in terms of quotations mentioning Portugal by IMF officials see below. There was plenty of IMF speak on Portugal back in March/May at time of Greek bail out and a minor burst of positiveness in October. Since then, silence except for one John Lipsky comment about “facilities exist to help Portugal”.

To make sure that we’re not missing other types of events involving IMF Officials and Portugal, we can also inspect just co-occurrences between them, and again, there’s very little overlap.

Conclusions

• Before the Greek and Irish bailouts, IMF officials were quite active in general volume of discussion that also carried notable positive language. We’ve not seen this for Portugal; a potentially interesting signal of strength.
• To truly judge IMF officials and their public commentary related to specific countries we should explore this over long time periods and multiple crises.
• There are multiple kinds of normalization to do here including comparing bailouts, countries, non-problematic country debt situations with problematic country debt situations, etc.

Silence can be a powerful signal but obviously takes some interpretation. We will continue to watch Portugal.

Today we read in the Financial Times that “Analysts’ earnings forecasts have a negligible effect on a company’s share price, according to new research that will raise further doubts over stock-pickers’ ability to move markets”. While we have many friends who are analysts and certainly respect their work – it’s a pretty interesting point.

Now contrast that with the comment made by one of our blog readers recently

“It’s fun to contemplate the countless possibilities that come from aggregating data/events/etc … creating a “uniquely yours” data stream to shape your own indicators … and not having to wait-for and react-to the same data that everyone else is using (difficult to get ahead of the curve).”

Quite a contrast – would you rather track what everybody else reads or create your own unique insights?

As always, we welcome your comments below!

Christopher

When monitoring large amounts of media there’s an interesting opportunity to track potential economic indicators – direct and indirect – such as bankruptcies, corporate insiders buying/selling shares, credit ratings, analyst ratings, etc. at large scale. In this blog entry we’ll explore bankruptcies and ratings data from Recorded Future to make a high level judgement of whether the economy has turned around or not.

Bankruptcies

Bankruptcies are certainly an interesting part of the economy. Clearly when they start to happen at large scale things are about to go wrong (or perhaps already are). The ripple effects of single bankruptcies (General Motors, Lehman Brothers) can be massive across supply chains.

In this case we’ve reviewed the count of unique bankruptcies per month in aggregate as well as a simple rate of change metric for the same. The unique count is important as a bankruptcy event clearly can be covered repeatedly over and over – e.g. the General Motors event flooded the media stream in May/June. In the Spotfire visualization below we visualize the count of unique bankruptcies (red line) as well as the rate of change (blue line) over 2009 and can certainly see that bankruptcies picked up across the year, and peaked in July. The rate of change peaked earlier and has already turned negative. So, it seems that perhaps things are improving here!

Looking at a simple treemap of the bankruptcy events – organized by industry (just one level hierarchy) -  we can see on the left in the visualization below that the largest sector for bankruptcy events clearly is financial services, perhaps not a surprise. 

As a precursor to bankruptcies we may want to look at credit rating events – which we also pick up in Recorded Future. Reviewing those events below, across the year, in a somewhat simplified/filtered form, we can see how downgrades peaked earlier in the year, affirmations seems to be on the rise, but actual increases in credit ratings are still flat. The time lag between bankruptcies and credit ratings is quite logical – and would be interesting to model.

Finally in reviewing analyst ratings for 2009 we clearly see an increase across the year in upgrades – and actually perhaps now they (upgrades) are starting to flatten out (quite logical) – providing us with a sense of that analyst ratings first change, followed by credit ratings, before finally bankruptcies occur (yes, of course there is much more to story than that!). 

Applications

This type of data could potentially be used to create “macro indicators” – providing perhaps an early glimpse/prediction of what a later “official number” will be – which could be highly interesting in for example gaining an “up on the market” in terms of early indications of a impactful macro indicator. To improve it many things could be done – perhaps only looking at a particular industry or a specific data source (e.g. SEC filings).

However – the same sort of data could also be used to look at a particular company or portfolio of companies – what about if you could form an alert which allowed you to track the chain of a cut in analyst rating, a cut in credit rating, and first chatter of bankruptcy (and other events of course!) for a large set of of names/companies – and keep you notified along the way? Certainly something we want to do with Recorded Future.  

Conclusion

There are many ways this analysis may be argued as too simplistic – i.e. too short time period, should be compared against a baseline, seasonal adjustments, does it only look like an improvement – in reality the media flow just slowed down in August, or for that sake – media just getting bored with reporting bankruptcies. All these can be battled though – more/longer data frames, focusing on particular sources (SEC 8-K filings for bankruptcies), etc. etc.

The point of the exercise is less about trying to claim that this data is more accurate than for example an aggregation of bankruptcy court filings from primary sources or a number you may receive from an analyst – but more about how you can a) shape your own indicators from a novel data stream (media/internet) and b) be able to judge/read/react to those indicators faster than you can when waiting for a number that everybody else is waiting for (e.g. compare housing/jobless/etc. numbers).

Even more interesting is of course to combine this data with more indicators extracted from primary sources, internet, and media – insiders buying/selling shares, company restructurings, layoffs, buybacks, IPOs, company expansions,  etc. Recorded Future has all those event types and many more – and you can combine them – e.g. into a 4 step complex event that in total would indicate that a company is “turning around” or “flatlining”. Lots of opportunities for unique insights!

Finally: we’re obviously going to do some of the above improvements – and also look at incorporating forecasting/trending techniques here – as well as comparing results to 3rd party numbers/indicators.

As always, we welcome your comments below!

Christopher