Twitter caused the Stock Market to Crash! (not really)

This is a cross-post from Trade The Sentiment.

On April 23 2013, the Associated Press reportedly had their Twitter account hacked.

At 1:07PM Eastern Time, a Tweet was sent out that claimed an explosion at the White House.  Here’s the Tweet:Screenshot at 2013-04-24 07:32:56

About 2 minutes after this Tweet was sent, the Stock Market saw a sell-off. According to my Tradestation Charts, the selloff began 2 minutes after the Tweet was sent. The Selloff took the S&P500 E-Mini futures contract down about 16 points within 2 to 3 minutes and then within 6 minutes of that tweet, the markets rebounded to levels before the tweet was sent.

A chart of the S&P500 SPY ETF is below for reference.

SPY

While this selloff was happening and throughout the rest of the day, many traders on Twitter were very adamant that this sell-off was the fault of “algorithms” that are listening to Twitter. These algo’s ‘heard’ the bad news from the AP Tweet and started selling and/or removing orders from the market, which caused the selloff that we say.

Additionally, many people are blaming this selloff on High Frequency Trading (HFT). Without going into too much detail, HFT can be described simply as trading that is done solely by computers where trades last only minutes or seconds.  This is a very very naive description but for the purposes here, it will work.

Many people are arguing on Twitter that this is a failure of Twitter security or that Twitter caused this crash.  I disagree wholeheartedly.

This was caused by human error. The security of the Twitter account isn’t really at issue…the AP have claimed that the hack came via a Phishing attempt.  If Twitter had Two-Factor authentication, perhaps the AP account wouldn’t have been hacked…but you can’t blame Twitter because the AP folks were fooled by a decent Phishing attempt.

I digress though…this isn’t a post about Twitter Security.  It’s a commentary on the “Twitter caused the markets to crash” mentality that is pervasive on Twitter right now.

Twitter didn’t do anything.

People are arguing that the crash is the fault of Twitter and the “algo’s”. But…what should have the reaction been to news of an explosion and injury to the President of the US?  Should it have been ignored? No…it shouldn’t have. It was news that SHOULD have driven the markets…and it did.

Sure…the speed at which the markets crashed might have been helped / driven by the HFT algo’s but I’d argue that this same news event would have caused a very similar action before HFT’s existed.

Imagine the Pit back in the days of manual Pit trading. If News had broke that the President had been injured in an explosion at the White House, wouldn’t the same movement have occurred?  Perhaps it wouldn’t have been as fast but it would happen.

For example – look at what happened when President Kennedy was assassinated….the Dow fell 3% that day after the news. Within a week, the markets had recovered that loss.  (source: The Stock Market’s Response to Dramatic Historical Events).  What we saw on April 23 was an event at a smaller scale but much faster.

So…did Twitter crash the markets?

Nope.

Traders were trading the markets. Just like they always do.  Sure…they may have been using technology to trade this news much faster than they used to be able to…but…this type of news is the type of news that should cause the markets to move.

Are there things that could be done better in the future to keep this type of event from happening? Sure.  Take a look at Nanex and what they are doing on the HFT front…they know that area backwards and forwards and based on their work, I believe there are many many changes that need to happen in the markets.

That said…I don’t think the markets are “broken” because this happened. They may be broken for other reasons. I also don’t think Twitter “crashed” the markets. Blame what you will…algo’s and HFT’s may have caused the quick sell-off  – but they were only acting in a way that they were told to act. It could be argued that HFT’s / algo’s caused the immediate rebound too.

The markets have always been news / event drive. This ‘event’ is no different.   Horrible news came out from a trusted source. This news was acted upon in a manner that was consistent with the news. The reaction was faster than most people would have liked, but I don’t believe the reaction is any different than it would have been 20 years ago.

It’s actually simple and straightforward – an event happened that *should* have caused the markets to drop…and they did. When it was determined that the event was false, the markets came back to where they were…as they should have.

So…Twitter didn’t crash the markets.  The markets reacted to news. Just like they always have.

This is a cross-post from Trade The Sentiment.

Comparing Market Sentiment – Twitter vs the “Professionals”

If you’ve been following me for more than a few months, you probably know that I’m researching Twitter Sentiment related to the market for my doctoral dissertation.

A few previous posts on the topic:

Last week, I published a quick update via a photo on twitpic to show a few friends and received quite a lot of feedback and response on that chart.

The chart that I shared was a chart of the 21 day moving average of the Bear / Bull Ratio of twitter sentiment..a revised version (current with data up to and including August 28 2012) is below. In the graphs below, the higher the number, the more ‘bearish’ the sentiment…the lower the number, the more ‘bullish’ the sentiment.

The top graph is the 21 day moving average of the Bear / Bull Sentiment Ratio with the average ratio shown as a yellow horizontal line. The bottom graph is the raw Bear/Bull Sentiment Ratio…you can see that it is rather noisy, hence the moving average to smooth it out.

I’ve taken things a step further to look at a longer-term view of twitter sentiment using Weekly Data. For this data, I sum up all data for each week (starting on Monday and ending on Sunday).  The Weekly Bear / Bull Ratio is shown in the top graph using a 5 week moving average of the Weekly Bear/Bull Sentiment Ratio.  The bottom graph contains the Raw Weekly Bear/Bull Sentiment Ratio data.

The question is, is the sentiment useful for understanding future market direction…or is it something that is ‘created’ by market movement.  That’s part of the research that I’m doing now.  I’m working on researching if there is any correlation / causation between twitter sentiment and price movement.  My gut tells me that there is correlation and the data points to this…but is twitter sentiment leading or lagging the market?  That’s the question (at least on of them that I have).

Is the Twitter Sentiment believable/accurate?

One of the things that has bothered me since day 1 of this research is whether the sentiment found via my twitter collection / analysis engine is ‘accurate’.   My analysis is only as accurate as my training data set…and right now, my training dataset shows an accuracy of ~90% using the Python Natural Language Toolkit’s accuracy measures.  So..I feel good there.

But…I wanted to look at comparing my Bear / Bull Sentiment Ratio with other sentiment measures to get a feel for how it might measure up.

I had a moment of brilliance yesterday.   Well…not really brilliance…more like a random thought. But…who’s to say brilliance isn’t really just randomness in the universe 🙂

I decided to compare twitter sentiment to the American Association of Individual Investors (AAII) Sentiment survey data that they release every week.

The latest AAII Sentiment Survey is shown below. I’ve taken the data from the latest survey spreadsheet and created a similar ratio to what I am using (I divide the bearish sentiment by the bullish sentiment).

Taking the AAII data and my Weekly Twitter Sentiment Bear/Bull data, I did a quick comparison between the two.  While the extremes are different, the data  generally follows similar patterns.

Not bad. The levels of the Bear/Bull ratio are different and more pronounced in the AAII survey, but the overall ‘direction’ is similar.

I feel good about this.  AAII reaches out to professional money managers for their sentiment survey…I’m watching Twitter to gather sentiment from people who are talking about the market.  While the data points are exact matches, the directional bias seems to be close.

Look for more on this in the future.