Johan Fourie's blog

I'd rather be a comma than a fullstop

Archive for May 2017

Can Twitter predict the markets?

with one comment

Twitter-PPC

Ask anyone about the pitfalls of Twitter, and they might point to recent gaffs by a prominent South African politician as evidence that the dangers outweigh its benefits. But such warnings have not stopped many others, most notably the president of the United States, from tweeting on a regular basis: Twitter’s user base creates more than 500 million tweets a day, and it has added about 2 million new users in the last quarter of 2016.

Presumably this wealth of information must have some value. Twitter, sadly for its shareholders, struggles to turn such growth into profit: in the last quarter of 2016, revenue growth was only 1%. But because it captures public sentiment at a very granular level, it has attracted the interest of both scientists and entrepreneurs hoping to turn this information into public or private benefit.

The use of social media for prediction is, of course, not a recent phenomenon. Google Flu Trends, founded in 2008, used Google’s search engine to track the spread of flu in 25 countries. But excitement about the project waned as it struggled to make accurate predictions. A 2014 Nature paper noted the value of social media ‘Big Data’, but warned that ‘we are far from a place where they can supplant more traditional methods or theories’.

Twitter, though, seems to attract increasing attention. A 2014 paper uses Twitter to predict crime. A 2015 paper show how psychological language on Twitter predicts heart disease mortality. Another 2015 paper show how Twitter sentiment predicts enrollment of Obamacare. A 2016 paper show how Twitter could be used to predict the 2015 UK general elections.

But it is, understandably, the financial markets that has attracted the most attention. A 2016 paper by Eli Bartov (NYU Stern School of Business), Lucile Faurel (Arizona State University) and Partha Mohanram (University of Toronto) shows how Twitter can predict firm-level earnings and stock returns. They use a dataset of nearly a million corporate tweets by 3662 firms between 2009 and 2012, all tweeted in the nine-trading-day period leading to firms’ quarterly earnings announcements. The authors find, unsurprisingly, that the tweets successfully predicts the company’s forthcoming quarterly earnings, but find, more surprisingly, that the tweets predict the ‘immediate abnormal stock price reaction to the quarterly earnings announcement’. These findings are more pronounced for firms in weaker information environments, such as ‘smaller firms with lower analyst following and lower institutional ownership’, and are not driven by concurrent information from sources other than Twitter, such as press articles or web portals.

It makes sense that corporate communication provides information, but can public sentiment on Twitter also inform market activity? A 2017 NBER Working Paper, by Vahid Gholampour (Bucknell University) and Eric van Wincoop (University of Virginia), answers this question by looking at the Euro/Dollar exchange rate. They start with all Twitter messages that mention EURUSD in their text and that were posted between October 9, 2013 and March 11, 2016. There were 268 770 of these messages, for an average of 578 per day. What they hope to do, is to identify whether informed opinions about future currency changes can actually predict actual currency changes, so they eliminate all tweets that do not express a sentiment about the future behaviour of the two currencies. This reduces the sample to 43 tweets per day, or 27 557 in total. They then classify each of these tweets as positive, neutral or negative using a detailed financial lexicon that they develop to translate verbal tweets into opinions, and create a Twitter Sentiment index for each day. They also split the sample in two: those opinions expressed by individuals with more than 500 followers, which they call the ‘informed opinion’, and those with fewer than 500 followers, which they call the ‘uninformed opinion’.

So what do they find? It turns out that the 633 days of data they have is too short to calculate the Sharpe ratio, a measure of the risk-adjusted return. The annualized Sharpe ratio based on daily returns is 1.09 for the informed group and -0.19 for the uninformed group. The Sharpe ratio of 1.09 for the informed group is impressive, but it has a large standard error of 0.6. The 95% confidence interval is therefore very wide, ranging from -0.09 to 2.27. They then construct a model with a precise information structure, estimate the parameters and then recalculate the Sharpe ratio to average at 1.68 with a 95% confidence interval between 1.59 and 1.78. Success: ‘the large Sharpe ratios that we have reported’, they conclude, ‘suggest that there are significant gains from trading strategies based on Twitter Sentiment’.

If all this sounds terribly complicated, that is exactly the point. Translating opinions into numbers is not an easy undertaking, and discerning the ‘informed’ opinions from the noise is even less so. But there is no doubt that Twitter does offer some useful, perhaps even lucrative, insights. Whoever can exploit that knowledge first, stand to benefit most.

*An edited version of this first appeared in Finweek magazine of 20 April.

Written by Johan Fourie

May 16, 2017 at 06:24

Do CEOs deserve their high salaries?

leave a comment »

Whitey Basson

Late last year, Bloomberg reported that South African Chief Executive Officers earn the 7th most of any country in the world – a whopping R102 million per person per annum. This was equivalent to 541 times the income of an average South Africa. The study, understandably, caused some outrage.

These numbers have been disputed, mostly because they include CEOs who earn in foreign currency. A study by 21st Century Consultants found that the CEO salary of the median large cap South African firm in 2016 was less than R6 million, roughly 5% of the Bloomberg average. PwC found the median between R3.1 and R7.7 million.

But even at these lower levels, many ask whether CEOs deserve what they earn. Do the value that they add outweigh the millions spent on salaries and bonuses? This, of course, is an incredibly complex question. Economists have no laboratory where they can randomly assign CEOs their salaries, and see what the likely outcome might be. Instead, we have CEOs that respond to the firm’s internal and external demands in various ways, planning, strategizing, meeting and organizing. Which of these activities adds more value seems impossible to determine.

That is, until now. A new study by four economists – Oriana Bandiera (LSE), Stephen Hansen (Oxford), Andrea Prat (Columbia Business School) and Raffeala Sadun (Harvard Business School) – measure the behaviour of CEOs in Brazil, France, Germany, India, the UK and the US, and compare these measurements to their firm’s performance. They do this using a two-stage method: first, they collect the weekly diaries of 1114 CEOs in the six countries. These diaries include detailed information about the hourly activities of each CEO: with whom they met, the number and duration of plant/shop-floor visits, business lunches, how many people joined, and the functions of these participants (whether they were in finance or marketing, for example, or clients or suppliers).

Their finding is that CEO activities differ remarkably across firms. While CEOs spend most of their time in meetings, they ‘differ in the extent to which their focus is on firms’ employees vs outsiders, and within the former, whether they mostly interact with high-level executives vs. production employees’.

The authors then use a machine learning algorithm to create an index of CEO behaviour. At low values of the index, CEOs spend more time with production and in one-on-one meetings with employees and suppliers, and at high values CEOs spend more time with executives and in meetings with more participants.

The authors note that there is no theoretical reason for one type of behaviour to lead to better outcomes. That such different types of behaviour exist may just be a consequence of the fact that firms require different types of CEOs, i.e. some firms will do better with a low-index CEO while others would do better with a high-index CEO. When CEOs are perfectly matched – or ‘assigned’ – to the type of firm that suit their style, there should be no correlation between the index-value of a CEO and the firm’s performance. In other words, a low-index CEO matched to a firm that will benefit from a low-index CEO style would perform just as well as a high-index CEO matched to a firm that will benefit from this CEO style type.

The results, however, shows the opposite. High values on the CEO index are strongly correlated with higher firm productivity, a measure of firm performance. CEOs who spend most of their time in meetings with senior executives, engage in communication (phone calls, videoconferences, etc.), bring together inside and outside functions, and bring together more than one function of a kind are also more likely to lead more productive firms.

Their results also show that CEOs are often not matched to the right firm: “Our estimates indicate that, while low-index CEOs are optimal for some of the sample firms, their supply generally overstrips demand, such that 17% of the firms end up with the ‘wrong’ CEO.”

More importantly, it is in the two developing countries in their sample – Brazil and India – where this matching is especially bad: 36% of firms in those countries end up with the ‘wrong’ CEO compared to the only 5% in the four developed countries. “The productivity loss generated by the misallocation of CEOs to firms equals 13% of the labour productivity gap between high and low income countries”.

The authors do not speculate on why this difference exists. One likely reason is weaker competition for top jobs within a thinner talent pool owing to the unequal levels of education in these countries. Another may be that appointments happen for reasons other than merit.

What the study does show, though, is that the choice of CEO is critical for firm success. Appoint the wrong type of CEO, and productivity is likely to decline. Although some firms benefit from a CEO who frequently has one-on-one conversations and visits the production floor, most firms benefit from a CEO who spend their days leading large meetings with top executives from different fields.

That helps to explain the high salaries for CEOs in South Africa too. A mismatch between CEO and firm is costly and seems to happen quite frequently. The small talent pool means that most firms are willing to pay exceptional salaries to those rare individuals with a high CEO index-value. If they don’t, the firm is likely to suffer far more costly productivity losses.

It also points to the dangers of policies that hope to place an upper-bound on managerial remuneration. Lower levels of remuneration will likely lead to fewer CEOs with high index-value, and to higher levels of mismatch between CEOs and firms. That, as the authors show, will be devastating for firm-level productivity, and economic development. Beware the unintended consequences of policies made with good intentions.

*An edited version of this first appeared in Finweek magazine of 6 April.

Written by Johan Fourie

May 1, 2017 at 05:57