Potentials - November/December 2017 - 11

the bottlenecks that occur during
rush hour periods (Fig. 4). The goal
is to address the conditions of markets during crashes in a more careful manner than by assuming static
conditions going forward. In contrast
to normal conditions, crash periods
display high volatility and correlation coefficients approaching one.
This situation is called contagion and
is treated separately in a multiregime
portfolio model.
To accomplish this task, we apply a
popular nonparametric ML method-
trend filtering-to the historical performance of a broad stock market, in
this case the S&P 500 index (Figure 5).
This type of no-assumption, modelfree approach is common in the ML
field. The historical performance of
asset categories is displayed under two regimes-normal and crash-
over the period 1998-2016 (Fig. 6).
We can gather interesting information by observing the performance
of the assets under the two regimes.
In particular, government bond returns have been a posit ive i nvestment during crash periods due to
their "flight to quality" characteristic.
In contrast, most stock markets experienced sharp drawdowns during
crash periods (over 30% drop), thus
showing the need to include other
types of assets besides stock in an
investment portfolio to protect the
investor's capital during crash periods. Real assets have provided good

performance under both regimes, and
these assets have become more popular with institutional investors since
the 2008 crash.
Given these regimes, we can develop a set of scenarios over future time
periods that represent the market in a
more accurate fashion than by assuming a static, single-regime economic
environment. Thus, we can minimize
worst-case risks within the financial
planning systems. Again, the goal is
to improve investment performance
by careful risk management.

Reinforcement learning
Reinforcement learning (RL) spans
the traditional areas of ML and decision models. This modeling ap--proach
has seen noteworthy successes, in--
cluding Google's Alpha Go. In the
traditional set up, the modeler as--
sumes a Markov chain for defining
the evolution of the underlying environment and a discounted additive
utility function. A Markov chain
switches between regimes by means
of a transition probability matrix.
The goal is to discover a set of policy

Five Factors as Building Blocks

Positive
Loadings

Negative
Loadings
U.S. International Corporate Real Commodity TIPS
Equity
Equity
Bond
Estate
Currency Protection
U.S. Treasuries

Inflation Protection
World Equities

Hedge
Fund

High Yield

FIG3 Factors as building blocks to asset category performance (historical data:
1998-2016).

(a)

(b)

FIG4 Traffic patterns under (a) normal and (b) rush-period congestion in Princeton, New Jersey.

IEEE POTENTIALS
November/December 20 1 7

■

11

Table of Contents for the Digital Edition of Potentials - November/December 2017

Potentials - November/December 2017 - Cover1
Potentials - November/December 2017 - Cover2
Potentials - November/December 2017 - 1
Potentials - November/December 2017 - 2
Potentials - November/December 2017 - 3
Potentials - November/December 2017 - 4
Potentials - November/December 2017 - 5
Potentials - November/December 2017 - 6
Potentials - November/December 2017 - 7
Potentials - November/December 2017 - 8
Potentials - November/December 2017 - 9
Potentials - November/December 2017 - 10
Potentials - November/December 2017 - 11
Potentials - November/December 2017 - 12
Potentials - November/December 2017 - 13
Potentials - November/December 2017 - 14
Potentials - November/December 2017 - 15
Potentials - November/December 2017 - 16
Potentials - November/December 2017 - 17
Potentials - November/December 2017 - 18
Potentials - November/December 2017 - 19
Potentials - November/December 2017 - 20
Potentials - November/December 2017 - 21
Potentials - November/December 2017 - 22
Potentials - November/December 2017 - 23
Potentials - November/December 2017 - 24
Potentials - November/December 2017 - 25
Potentials - November/December 2017 - 26
Potentials - November/December 2017 - 27
Potentials - November/December 2017 - 28
Potentials - November/December 2017 - 29
Potentials - November/December 2017 - 30
Potentials - November/December 2017 - 31
Potentials - November/December 2017 - 32
Potentials - November/December 2017 - 33
Potentials - November/December 2017 - 34
Potentials - November/December 2017 - 35
Potentials - November/December 2017 - 36
Potentials - November/December 2017 - 37
Potentials - November/December 2017 - 38
Potentials - November/December 2017 - 39
Potentials - November/December 2017 - 40
Potentials - November/December 2017 - 41
Potentials - November/December 2017 - 42
Potentials - November/December 2017 - 43
Potentials - November/December 2017 - 44
Potentials - November/December 2017 - 45
Potentials - November/December 2017 - 46
Potentials - November/December 2017 - 47
Potentials - November/December 2017 - 48
Potentials - November/December 2017 - Cover3
Potentials - November/December 2017 - Cover4
https://www.nxtbook.com/nxtbooks/ieee/potentials_20190102
https://www.nxtbook.com/nxtbooks/ieee/potentials_20181112
https://www.nxtbook.com/nxtbooks/ieee/potentials_20180910
https://www.nxtbook.com/nxtbooks/ieee/potentials_20180708
https://www.nxtbook.com/nxtbooks/ieee/potentials_20180506
https://www.nxtbook.com/nxtbooks/ieee/potentials_20180304
https://www.nxtbook.com/nxtbooks/ieee/potentials_20180102
https://www.nxtbook.com/nxtbooks/ieee/potentials_111217
https://www.nxtbook.com/nxtbooks/ieee/potentials_091017
https://www.nxtbook.com/nxtbooks/ieee/potentials_070817
https://www.nxtbook.com/nxtbooks/ieee/potentials_050617
https://www.nxtbook.com/nxtbooks/ieee/potentials_030417
https://www.nxtbook.com/nxtbooks/ieee/potentials_010217
https://www.nxtbook.com/nxtbooks/ieee/potentials_111216
https://www.nxtbook.com/nxtbooks/ieee/potentials_091016
https://www.nxtbook.com/nxtbooks/ieee/potentials_070816
https://www.nxtbook.com/nxtbooks/ieee/potentials_050616
https://www.nxtbook.com/nxtbooks/ieee/potentials_030416
https://www.nxtbook.com/nxtbooks/ieee/potentials_010216
https://www.nxtbook.com/nxtbooks/ieee/potentials_111215
https://www.nxtbook.com/nxtbooks/ieee/potentials_091015
https://www.nxtbook.com/nxtbooks/ieee/potentials_070815
https://www.nxtbook.com/nxtbooks/ieee/potentials_050615
https://www.nxtbook.com/nxtbooks/ieee/potentials_030415
https://www.nxtbook.com/nxtbooks/ieee/potentials_010215
https://www.nxtbook.com/nxtbooks/ieee/potentials_111214
https://www.nxtbook.com/nxtbooks/ieee/potentials_091014
https://www.nxtbook.com/nxtbooks/ieee/potentials_070814
https://www.nxtbookmedia.com