The Goldman Sachs World Cup 2014 Prediction Model

As someone who is both a fan of the World Cup and statistical modeling, it was with great interest that I read “The World Cup and Economics 2014,” a report issued by Goldman Sachs. They have outlined their predictions in a 67 page report. Goldman Sachs estiamtes that Brazil, the host nation, has a 48.5% chance to win the tournament, while Argentina, Germany, and Spain are the follow-up favorites (14.1%, 11.4%, and 9.8% to win the World Cup 2014, respectively).

The Goldman Sachs methodology is rather straightforward:

The explanatory variables in the regression analysis are as

1. The difference in the Elo rankings between the two
teams. The Elo ranking is a composite measure of
national football team success that is based on the entire
historical track record. Unlike the somewhat better
known FIFA/Coca-Cola rating, the Elo rating is available
for the entire history of international football matches.
Statistically, we find that the difference in Elo rankings is
the most powerful variable in the model.

2. The average number of goals scored by the team over
the last ten mandatory international games.

3. The average number of goals received by the opposing
team over the last five mandatory international games.

4. A country-specific dummy variable indicating whether the
game in question took place at a World Cup. This variable
is meant to capture whether a team has a tendency to
systematically outperform or underperform at a World Cup.
We only include this variable for countries that have
participated in a sufficient number of post-1960 World Cup
games (including Brazil, Germany, Argentina, Spain,
Netherlands, England, Italy and France).

5. A dummy variable indicating whether the team played in
its home country.

6. A dummy variable indicating whether the team played on
its home continent, with coefficients that are allowed to
vary by country.

From there, it’s up to Monte Carlo simulation to make the predictions:

We generate a probability distribution for the outcome of each
game using a Monte Carlo simulation with 100,000 draws,
using the parameters estimated in the regression analysis
described above. We use the results of this simulation
analysis to generate the probabilities of teams reaching
particular stages of the tournament, up to winning the
championship. We use the rounded prediction of the goals
scored to determine the outcomes of each game during the 
group stage and the unrounded forecast to pick the winner in
the knockout stage.

Unfortunately, the model has some limitations:

To be clear, our model does not use any information on the
quality of teams or individual players that is not reflected in a
team’s track record. For example, if a key player who was
responsible for a team’s recent successes is injured, this will
have no bearing on our predictions. There is also no role for
human judgment as the approach is purely statistical.

You can read the entire report here: Goldman Sachs – World Cup 2014 Economic Report

For further reading, compare the Goldman Sachs predictions to the Five Thirty Eight World Cup Model (both models have pegged the probabilities of Brazil, Argentina, Germany, and Spain to win World Cup 2014 to within a couple of percentages, and in the same rank order of winning the tournament):


Did Goldman Sachs Overstep in Criminally Charging Its Ex-Programmer?

Michael Lewis’s latest piece for Vanity Fair is an 11,000 examination of how Goldman Sachs acted after finding that one of its ex-programmers, Sergey Aleynikov, allegedly stole computer code. There was a federal trial, and the 41-year-old father of three was sentenced to eight years in federal prison. Investigating Aleynikov’s case, Michael Lewis holds a second trial. The entire piece is worth reading, especially the interviews with Aleynikov in which he presents his views on life (quoted at the bottom in this post).

First, this was an interesting anecdote on why Russians are the best programmers on Wall Street:

He’d been surprised to find that in at least one way he fit in: more than half the programmers at Goldman were Russians. Russians had a reputation for being the best programmers on Wall Street, and Serge thought he knew why: they had been forced to learn programming without the luxury of endless computer time. “In Russia, time on the computer was measured in minutes,” he says. “When you write a program, you are given a tiny time slot to make it work. Consequently we learned to write the code in a way that minimized the amount of debugging. And so you had to think about it a lot before you committed it to paper. . . . The ready availability of computer time creates this mode of working where you just have an idea and type it and maybe erase it 10 times. Good Russian programmers, they tend to have had that one experience at some time in the past: the experience of limited access to computer time.”

A new rule created by the SEC in 2007 called Regulation NMS led to the proliferation of high frequency trading (HFTs):

For reasons not entirely obvious (yet another question for another day), the new rule stimulated a huge amount of stock-market trading. Much of the new volume was generated not by old-fashioned investors but by extremely fast computers controlled by high-frequency-trading firms, like Getco and Citadel and D. E. Shaw and Renaissance Capital, and the high-frequency-trading divisions of big Wall Street firms, especially Goldman Sachs. Essentially, the more places there were to trade stocks, the greater the opportunity there was for high-frequency traders to interpose themselves between buyers on one exchange and sellers on another. This was perverse. The initial promise of computer technology was to remove the intermediary from the financial market, or at least reduce the amount he could scalp from that market. The reality has turned out to be a boom in financial intermediation and an estimated take for Wall Street of somewhere between $10 and $20 billion a year, depending on whose estimates you wish to believe.

Goldman decided to hire Serge Aleynikov to beef up their algorithms to compete with the likes of big hedge funds like Citadel:

A lot of the moneymaking strategies were of the winner-take-all variety. When every player is trying to buy Pepsi after Coke’s stock has popped, the player whose computers can take in data and spit out the obvious response to it first gets all the money. In the various races being run, Goldman was seldom first. That is why they had sought out Serge Aleynikov: to improve the speed of their system.

The article explains how Goldman is a money-making machine, but the appearance of black swan events led many Wall Street firms to lose millions of dollars at the height of the financial crisis, Goldman included:

Day after volatile day in September 2008, Goldman’s supposedly brilliant traders were losing tens of millions of dollars. “All of the expectations didn’t work,” recalls Serge. “They thought they controlled the market, but it was an illusion. Everyone would come into work and were blown away by the fact that they couldn’t control anything at all. . . . Finance is a gambling game for people who enjoy gambling.”

This was probably the most damning paragraph in the piece about Goldman’s relationship with open source software:

But most of his time was spent simply patching the old code. To do this he and the other Goldman programmers resorted, every day, to open-source software, available free to anyone for any purpose. The tools and components they used were not specifically designed for financial markets, but they could be adapted to repair Goldman’s plumbing.

Serge quickly discovered, to his surprise, that Goldman had a one-way relationship with open source. They took huge amounts of free software off the Web, but they did not return it after he had modified it, even when his modifications were very slight and of general rather than financial use. “Once I took some open-source components, repackaged them to come up with a component that was not even used at Goldman Sachs,” he says. “It was basically a way to make two computers look like one, so if one went down the other could jump in and perform the task.” 

On the individualistic (selfish) nature of competition at Goldman, even when efforts were collaborative in nature:

It made no sense to him the way people were paid individually for achievements that were essentially collective. “It was quite competitive. Everyone’s trying to show how good their individual contribution to the team is. Because the team doesn’t get the bonus, the individual does.”

And then we get to the meat of the piece, where Michael Lewis invites people in the HFT industry to come up with their own verdict of whether Serge Aleynikov did something nefarious and/or illegal:

Our system of justice was a poor tool for digging out a rich truth. What was really needed, it seemed to me, was for Serge Aleynikov to be forced to explain what he had done, and why, to people able to understand the explanation and judge it. Goldman Sachs had never asked him to explain himself, and the F.B.I. had not sought help from someone who actually knew anything at all about computers or the high-frequency-trading business. And so over two nights, in a private room of a Wall Street restaurant, I convened a kind of second trial. To serve as both jury and prosecution, I invited half a dozen people intimately familiar with Goldman Sachs, high-frequency trading, and computer programming.

You have to read the piece for the conclusion. As one of the jurors assembled by Michael Lewis says: it was nauseating how Sergey was treated.

One last bit in the informal jury process that caught my attention was Serge’s demeanor and approach to life. Take things as they come; negativity is pointless:

At one point one of the people at the table stopped the conversation about computer code and asked, “Why aren’t you angry?” Serge just smiled back at him. “No, really,” said the other. “How do you stay so calm? I’d be fucking going crazy.” Serge smiled again. “But what does craziness give you?” he said. “What does negative demeanor give you as a person? It doesn’t give you anything. You know that something happened. Your life happened to go in that particular route. If you know that you’re innocent, know it. But at the same time, you know you are in trouble and this is how it’s going to be.” To which he added, “To some extent I’m glad this happened to me. I think it strengthened my understanding of what living is all about.”

What are your thoughts?


There’s a very interesting addendum in Vanity Fair in which Michael Lewis is interviewed about his piece. Here, he shares his personal thoughts on Sergey’s time in prison:

Q: For the past 200, 250 years, prison has been an essential part of the Russian experience. Like Dostoyevsky and other Russian authors, and their heroes, Serge found some sense of purpose in his incarceration. Do you think an American could have come away from the experience with that same perspective?

[Michael Lewis]: In the 1950s, European filmmakers, when their films were going to be made for both a Russian and American audience, would change the ending. They would make a happy ending for the American audience and a tragic one for the Russian audience. There’s a photographer named Tacita Dean who has done a series of photographs called “Russian Endings” where she has played on this. I would say that in some ways, there’s something in the water in Russia that enables you to derive a kind of pleasure from a tragic experience. That is not in the water in America. A kind of richness from a tragic experience. And whatever chemical is in the water, Serge drank plenty of it. He is very persuasive on the subject that this was not an all-together bad experience for him. It woke him up to many aspects of life that he had previously been asleep to. I believe him. I don’t think it’s just superficial rationalizing.

When you’re with him, it’s shocking how without anger or bitterness he is. You would never guess, at the dinners I had, that he was one who spent time in jail. You would have picked every other person there.

Also worth highlighting is financial blogger Felix Salmon on his reaction to Lewis’s piece:

I’m increasingly coming to the conclusion that America’s system of jurisprudence simply isn’t up to the task of holding banks and bankers accountable for their actions. The only people who ever get prosecuted are small fry and insider traders, rather than the people who really caused the biggest damage. And the lesson of Sergei Aleynikov is that if and when the laws get beefed up, the banks will simply end up taking advantage of those laws for their own vindictive purposes, rather than becoming victims of them. Given the ease with which Goldman got the FBI to do its bidding, one has to assume that, most of the time, the government will be working on the same side as the big banks, rather than working against them. Do we really want to give those banks ever more powerful weapons?

How Financial Crises are Like Hurricanes

Felix Salmon opines on how financial crises are similar to huge storms, such as the impending Hurricane Sandy barreling down on New York and the rest of the East Coast:

Financial crises are similar to storms: they require humility, not hubris. Being prepared can be helpful at the margin, but ultimately it doesn’t matter how good your liquidity management teams and risk ledgers and counterparty hedging operations are: if everybody else is blown over by forces beyond their control, then you will be too.

That’s why skyscrapers always used to be built well above the water level, and that’s why we used to have dumb regulations like Glass-Steagal and Basel I, which weren’t very sophisticated, but which generally did the trick. Buildings like 200 West are a bit like Basel III: they’re built with models, so that they can withstand certain forces. But if an unprecedented storm arises, they’re still more at risk than, say, Trinity Church, built more than 150 years earlier. Sometimes, simple common sense (high ground is safer, huge books of complex derivatives can blow up in unpredictable ways) does a lot more good than any amount of sophisticated preparation.

The gist of Felix’s post relates to how Goldman Sachs is protecting its multi-millionaire dollar headquarters with sandstorms, but the analogy can be expanded to all the big banks.

Bonus Day at Goldman Sachs

Today is Bonus Day at Goldman Sachs, or as it is colloquillay known: Compensation Communication Day. On this day:

Most employees are called one by one into a managing partner’s glass-walled office, where they are informed of their bonus numbers, as well as any stock awards or deferred cash payments they will get..

In what may seem like a paradox, many Goldman employees will be hoping that the firm’s stock does poorly on Thursday. That is because the firm is expected to give deferred stock to a large number of employees in lieu of larger cash payments. The exact number of shares an employee receives will be calculated based on the firm’s closing price on Thursday, according to a person with knowledge of the bank’s plans, meaning that the lower the price, the more shares employees will get, and the bigger the potential gains if the company’s fortunes improve.


Even the largest bonuses at Goldman this year are likely to be a far cry from those given out during Wall Street’s prelapsarian (Editor’s note: awesome word!) years. As Charles D. Ellis recounts in The Partnership: The Making of Goldman Sachs, employees at the firm were once paid their yearly bonuses in stacks of $100,000 checks ($100,000 being the biggest single-check amount the firm’s payroll system could process).

Can you imagine carrying a stack of checks larger than your stash of cash in your wallet? I can’t.

Readings: Goldman Partners, Atlanta’s Offices, The Wire at Harvard

Here’s what I’ve read recently:

1) “At Goldman, Partners are Made, Unmade” [New York Times] – the article begins with a bold introduction:

On Wall Street, becoming a partner at Goldman Sachs is considered the equivalent of winning the lottery.

And then goes on to explain that while achieving partner status at Goldman is joining the elite, the status may be taken away:

As many as 60 Goldman executives could be stripped of their partnerships this year to make way for new blood, people with firsthand knowledge of the process say. Inside the firm, the process is known as “de-partnering.” Goldman does not disclose who is no longer a partner, and many move on to jobs elsewhere; some stay, telling few of their fate.

I find this fact fascinating: I knew that Goldman had partners at its firm (even though the company is public), but I had no idea that partners could have been unmade. This is in stark contrast to academia, where a professor who has attained tenure usually will not be stripped of the status unless he does something completely stupid.

And while being de-partnered sounds bad, I find it hard to agree with the claim made by Michael Driscoll:

“Being partner at Goldman is the pinnacle of Wall Street; if you make it, you are considered set for life,” said Michael Driscoll, a visiting professor at Adelphi University and a senior managing director at Bear Sterns before that firm collapsed in 2008. “To have it taken away would just be devastating to an individual. There is just no other word for it.”

What do you think?

2) “Atlanta Awash in Empty Offices Struggles to Recover From Binge” [Bloomberg] – an insightful piece explaining how the recession is still deep, especially in my hometown, Atlanta.

The gist:

Atlanta is no longer showing robust population and job increases. Unemployment topped 10 percent for most of the past year and exceeded the national rate for most of 2008, 2009 and 2010. While Atlanta’s office space increased 5.8 percent in the past five years, office jobs shrank 9.8 percent

I was surprised to learn that Bank of America (the company) was not the largest tenant in the Bank of America Plaza:

Bank of America Corp., the largest tenant in the 55-story tower, plans to reduce its space to 13 percent from 30 percent and cut its rent to about half the current $36.65 a square foot, according to the watch-list data.

The homebuilders in Atlanta are idle as well:

Atlanta’s homebuilders, who had led the nation in single- family construction permits from 1995 to 2005, have been largely idled. Permit volume declined 91 percent from 2005 to 2009, according to the Census Bureau.

A lot more sobering statistics in the Bloomberg piece.

3) “Why We’re Teaching ‘The Wire’ at Harvard” [Harvard Kennedy School] – one of the most compelling, gritty, and moving television shows of all time is HBO’s The Wire. One Harvard course in urban inequality is embracing this television show:

Of course, our undergraduate students will read rigorous academic studies of the urban job market, education and the drug war. But the HBO series does what these texts can’t. More than simply telling a gripping story, “The Wire” shows how the deep inequality in inner-city America results from the web of lost jobs, bad schools, drugs, imprisonment, and how the situation feeds on itself.

Powerful. Certainly a strong testament that education can go beyond the textbook.