The EconomistNovember 23rd 2019 Finance & economics 672
Buttonwood A river needs a dam
T
he thamesseems to draw people
who work on intelligence-gathering.
The spooks of mi6 are housed in a funky-
looking building overlooking the river.
Two miles downstream, in a shared
office space near Blackfriars Bridge, lives
Arkera, a firm that uses machine-learn-
ing technology to sort intelligence from
newspapers, websites and other public
sources for emerging-market investors.
Its location is happenstance. London has
the right time zone, between the Ameri-
cas and Asia. It is a nice place to live. The
Thames happens to run through it.
Arkera’s founders, Nav Gupta and
Vinit Sahni, both have a background in
“macro” hedge funds, the sort that like to
bet on big moves in currencies and bond
and stock prices ahead of predicted
changes in the political climate. The
firm’s clients might want a steer on the
political risks affecting public finances
in Brazil, or to gauge the social pressures
that could arise as a consequence of an
austerity programme in Egypt. It applies
machine learning to find market in-
telligence and make it usable.
For many people, the use of such
technologies in finance is the stuff of
dystopian science fiction, of machines
running amok. But once you look at
market intelligence through the eyes of
computer science, it provokes disquiet-
ing thoughts of a different kind. It gives a
sense of just how creaky and haphazard
the old-school, analogue business of
intelligence-gathering has been.
Analysts have used text data to try to
predict changes in asset prices for a
century or more. In 1933 Alfred Cowles,
an economist whose grandfather had
founded the Chicago Tribune, published a
pioneering paper in this vein. Cowles
sorted stockmarket commentary by
William Peter Hamilton, a long-rulingeditor of the Wall Street Journal, into three
buckets (bullish, bearish or doubtful) and
attached an action to each (buy, sell or
avoid). He concluded that investors would
have done better simply to buy and hold
the leading stocks in the Dow Jones index
than to follow Hamilton’s steer.
The application of machine-learning
models to text-as-data might seem a world
away from Cowles’s approach. But in
concept, it is similar. The relevant text is
sought. Values are ascribed to it. A statis-
tical model is applied. Its predictions are
tested for robustness. Of course, with bags
of computing power and suites of self-
learning models, the enterprise is on a
different scale from Cowles’s rudimentary
exercise. The endless expanse of the in-
ternet means far richer source material.
The range of possible values ascribed to it
will be broader than “bullish, bearish or
doubtful”. And self-learning algorithms
can test and retest the combinations that
yield the best predictions.
It is tempting to focus on the black-box
elements of all this: the language software
that “reads” the source text and the algo-rithms that use the data to make predic-
tions. But this is like judging a hi-fi sys-
tem by its speakers. A lot of the import-
ant work comes earlier in the process.
Arkera, for instance, spends a lot of effort
finding all the relevant text and “clean-
ing” it—stripping it of extraneous junk,
such as captions and disclaimers. “A
good signal is crucial,” says Mr Gupta.
He gives Brazil’s pension reform as an
example. The country has 513 parliamen-
tarians. They have social-media ac-
counts, websites and blogs. They speak
to the press—Brazil has scores of region-
al newspapers. All are potential sources
of useful data. If you cut corners at this
stage you might miss something that
even the best statistical model cannot fix
later. There is little point in having a cool
amplifier and great speakers if the stylus
on your record-player is worn out.
Any good emerging-market analyst
knows this, too. If you bumped into one
shortly after Brazil’s elections last year,
he was probably on his way to Brasília to
sound out prospects for a crucial pension
reform. Without it, Brazil’s public debt
would be certain to explode, sparking
capital flight. In July a pension bill finally
passed Brazil’s lower house. Arkera’s
models tracked the leanings of Brazil’s
politicians to get an early sense of the
likely outcome. It would be hard for an
analyst working unaided to mimic this
reach, even if he was always on the
ground and spoke perfect Portuguese.
Intelligence-gathering is a labour-
intensive business. It is thus ripe for
automation. That this is happening in
finance is also natural. There is a well-
defined objective (to make money).
There is a well-defined end-point (buy,
sell or avoid). Without such clarity of
purpose, intelligence is an endless river.
It is one undammed thing after another.How machine learning is revolutionising market intelligencetry’s central bank does not report its expo-
sure to derivatives.
A broader question is whether Asia
should be faulted for its predilection for
saving. Take Singapore, which lies at the
extreme end with a current-account sur-
plus of 18% of gdp. The imf argues that the
country’s external position is “substantial-
ly stronger” than warranted by fundamen-
tals. It has called for the government to
spend more on infrastructure and on social
security, which would help reduce its citi-
zens’ precautionary savings.
But Singapore has pushed back againstsuch criticisms. Before the mid-1980s it
regularly ran a current-account deficit. Its
surplus ballooned as it hit a demographic
sweet spot, with lots of workers and few re-
tired people. In the coming years, though,
it expects its surplus to narrow as its popu-
lation gets older. Households will draw
down savings and the government will face
mounting health-care costs. For China,
South Korea and Taiwan, all of which are
set to age rapidly, the dynamics are likely to
be similar.
Economists also continue to question
how much blame Asian savers really de-serve for the global financial turmoil of- There were plenty of other culprits.
They included America’s lax mortgage reg-
ulations and Europe’s rash banks, which
borrowed heavily and scooped up danger-
ous debt products. Once again, the West is
doing much on its own terms that is alarm-
ing enough, from America’s trade wars to
Europe’s inability to muster a co-ordinated
fiscal response to its economic woes. Sur-
plus savings in Asia are yet another drag on
a world suffering from weak demand. But
of all the things to worry about, they are not
top of the list. 7