Tactical Asset Allocation using Deep Learning

Disclosures: qplum LLC is a registered investment adviser.  Information presented is for educational purposes only and does not intend to make an offer or solicitation for the sale or purchase of any specific securities, investments, or investment strategies.  Investments involve risk and are never guaranteed.  Be sure to first consult with a qualified financial adviser and/or tax professional before implementing any strategy discussed herein. Past performance is not indicative of future performance.

Gaurav Chakravorty

CIO at qplum

www.qplum.co/events

What will we cover today

Asymmetric utility function/loss aversion 

Goals from asset allocation

Tactical vs Strategic Asset Allocation

Deep Learning Approach

Results

 

 

Top pain points for an investor:

I. Aversion to losing

It is not always just about higher returns.

Utility function is not uniformly distributed.

Utility function is not the same.

 

II. Anchoring around a sustainability rate

Most pension funds have a nominal target yield.

 

Not meeting the target yield is a big deal compared to outperformance

Other pain points

III. Capacity:

Investments that have scale and capacity  to get in and to get out

 

IV. Should work with illiquid assets:

Illiquid investments are a part of everyone's portfolio.

One cannot look at liquid investments without considering the illiquid assets that are a part of the portfolio already.

Asset Allocation >> Security Selection

“By choosing to place asset allocation at the center of the investment process, investors ground the decision-making framework on the stable foundation of long-term policy actions.

 

Focus on asset allocation relegates market timing and security selection decisions to the background, reducing the degree to which investment results depend on mercurial, unreliable factors.

 

Selecting the asset classes for a portfolio constitutes a critically important set of decisions, contributing in large measure to a portfolio’s success or failure. Identifying appropriate asset classes requires focus on functional characteristics, considering potential to deliver returns and to mitigate portfolio risk. Commitment to an equity bias enhances returns, while pursuit of diversification reduces risks. Thoughtful, deliberate focus on asset allocation dominates the agenda of long-term investors.”
 

– David Swensen

Goals of asset allocation:

(a) Target constant risk in the portfolio.

 

(b) Optimize portfolio for the specified utility function.

 

(c) Constrain any studies to a specified, systematic risk management threshold.

Tactical (dynamic) vs Strategic (constant)

(a) Dynamic allocation does better risk targeting.

 

(b) Dynamic allocation offers a systematic approach to observed changes in expected returns and expected risk.

Deep Learning framework for tactical asset allocation

Workflow

A bit more about the cost function

Results

Disclosure This is for educational purposes only. All investments carry risk. Back-tested performance is not indicative of future results. Any return values and/or projections are based on the back-tested results from Jan 1st, 1995 till date. Average case return is the back-tested return.
The actual performance for investments in this portfolio could be different.
Read our full disclosure here about back-tested performance and projections. qplum is not a tax advisor. Please consult with your tax advisor before making any decisions about your tax liabilities.

Flagship Portfolio

Asset Classes

80+ ETFs covering:

- Global equities (US, Europe, Emerging Mkts)

- Real Estate (Domestic and International)

- Global Fixed Income

Risk Management

The left half of the graph shows the risk manager decreasing the allocation to the markets as portfolio value goes down. The right half shows progressive re-allocation of cash to markets when portfolio value starts increasing again.

Scenarios where risk management triggered

60/40 ACWI/AGG

US Investor Index

Backtested Asset Allocation

Investing with a trustworthy tool

"security analysis may begin--modestly, but hopefully--to refer to itself as a scientific discipline "

 

Imagining investing with "trustworthy tool" and not experts.

- Benjamin Graham

Towards a science of security analysis published 1952

Questions?​

 

gchak@qplum.co

Disclosures: qplum LLC is a registered investment adviser.  Information presented is for educational purposes only and does not intend to make an offer or solicitation for the sale or purchase of any specific securities, investments, or investment strategies.  Investments involve risk and are never guaranteed.  Be sure to first consult with a qualified financial adviser and/or tax professional before implementing any strategy discussed herein. Past performance is not indicative of future performance.

Tactical Asset Allocation using Deep Learning

By Gaurav Chakravorty

Tactical Asset Allocation using Deep Learning

Gaurav Chakravorty, co-founder and Chief Investment Officer at qplum, will discuss how Deep Learning can be used in global tactical asset allocation. We will show how this investment strategy compares to a traditional institutional investing benchmark as well as qplum's US investor index. We believe that Deep Learning will provide a huge contribution to asset management in its utility for core tactical asset allocation rather than indirectly predicting returns.

  • 3,123