Economic Data Sciences PRO
Understandable A.I.
Understandable Artificial Intelligence
Overview
©2018 Economic Data Sciences
EDS was given 3 funds by a U.S. based endowment: IEMG and two active Emerging Markets
- The goal: compare the funds head to head and decide which fund is better
- EDS expanded the task and analyzed which fund should be added to a traditional 60-40 portfolio
IEMG vs Active EM Funds:
Return and Standard Deviation
- Both active funds have higher Sharpe Ratios vs. IEMG
- EM has a slight advantage
©2018 Economic Data Sciences
EM
*Data from EDS, Prospecta Trust, & Bloomberg, courtesy of London Business School
Return and Total Factor Sensitivity
- Both active funds seems better vs. IEMG
- Developing Mkts has a slight advantage
©2018 Economic Data Sciences
EM
EM
*Data from EDS, Prospecta Trust, & Bloomberg, courtesy of London Business School
Which fund is better?
©2018 Economic Data Sciences
- Analysis was done on a standalone basis
- Both active funds appear better than the passive
- EM Fund is better on St. Deviation
- Developing Mkts Fund is better on Total Factor Sensitivity
Further Analysis
©2018 Economic Data Sciences
- Anaylze total factor exposures for each fund
- Compare funds with traditional U.S. 60/40 portfolio
IEMG Factor Risk Exposure
-
Highest exposure to:
- U.S. industrial production
- Chinese leading indicators
- U.S. market
©2018 Economic Data Sciences
*Data from EDS & Bloomberg, courtesy of London Business School
EM Fund Factor Risk Exposure
-
Directionally similar exposure compared to IEMG
- Higher Systemic Risk
- Lower exposure to U.S. market
©2018 Economic Data Sciences
*Data from EDS & Bloomberg, courtesy of London Business School
Developing Mkts Factor Risk Exposure
- Similar exposure as IEMG
©2018 Economic Data Sciences
*Data from EDS & Bloomberg, courtesy of London Business School
Adding Funds To Existing Portfolio
©2018 Economic Data Sciences
- Use default U.S. 60/40 with 8% target return portfolio
- How much would each of the 3 funds add
Adding To Existing Portfolio
-
A.I. prefers Developing Mkts Fund:
- Lower fees vs. EM Fund (0.86% vs. 1.25%)
- Higher Total Factor Sensitivity
©2018 Economic Data Sciences
Should Either Be Picked?
- We analyze entire Client universe
©2018 Economic Data Sciences
EM
*Data from EDS, Prospecta Trust, & Bloomberg, courtesy of London Business School
Should Either Be Picked?
- Driven by Chinese leading indicators
- Each column represents a different fund
©2018 Economic Data Sciences
Should Either Be Picked?
- High exposure to metals
- Second only to dedicated gold & special minerals fund
©2018 Economic Data Sciences
Should Either Be Picked?
- Extremely high exposure to U.S. industrial production
©2018 Economic Data Sciences
Should Either Be Picked?
- EM Innovators Fund has the highest systemic risk of the 3
©2018 Economic Data Sciences
Should Either Be Picked?
- All have negative exposure to U.S. consumer prices
©2018 Economic Data Sciences
Should Either Be Picked?
- Negative exposure to U.S. retail sales
©2018 Economic Data Sciences
Conclusions
Funds need to be evaluated in a full portfolio context
- Both active funds seem better than the passive one
-
Selection becomes harder between the 2 active funds:
- EM Fund has a higher Sharpe Ratio
- Developing Mkts Fund has a higher Total Factor Sensitivity
- Developing Mkts has lower fees
- Developing Mkts has lower Systemic Risk
- All 3 funds could potentially be replicated/replaced
©2018 Economic Data Sciences
Disclaimers
©2018 Economic Data Sciences
Please remember that past performance may not be indicative of future results. Different types of
investments involve varying degrees of risk, and there can be no assurance that the future performance
of any specific investment, investment strategy, or product made reference to directly or indirectly in this
presentation, will be profitable, equal any corresponding indicated historical performance level(s),
or be suitable for an individual's portfolio.
Our projections are based on current market conditions which can vary over the coming months and weeks. Additionally, our projections are based on historical market behavior which
may vary unexpectedly. Using Machine Learning, our tool should adjust to new market fluctuations but we might not be able to avoid short term volatility.
Get In Touch
©2018 Economic Data Sciences
info@EconomicDataSciences.com
info@EconomicDataSciences.com
Comparing funds and deciding which to add to existing portfolio
By Economic Data Sciences
