Understandable Artificial Intelligence

Content

©2019 Economic Data Sciences

  1. Founders
  2. Common Problems
  3. A.I.'s Ability to Solve These Issues
  4. EDS Implementation of A.I.
  5. How We Work
  6. Where EDS is Different
  7. Tangible Client Benefits
  8. Past Examples

Founders & Our Story

©2019 Economic Data Sciences

Edmund Walsh

Boris Vilidnitsky, CFA

Founder, Lead Data Scientist

Founder, COO

  • 11 years of research experience
  • Focus on applied mathematics, risk management, asset allocation, macro-economics, and computer science
  • MA in International Economics and Finance from Brandeis University; BA in Political Science from The Ohio State University
  • 10 years of experience in asset management
  • Focus on capital markets with specialties in equities, emerging markets, and Europe
  • MBA from Columbia and London Business Schools; MSc in Finance from Brandeis University; BA in Mathematics and Computer Science from Boston College

Boris and Edmund met 10 years ago while studying at Brandeis.

Five years ago, experiencing frustration with the lack of analytical rigor, Edmund began developing the software tool.

In early 2017, Boris developed the business plan and in July EDS was incorporated

Common Problems

©2019 Economic Data Sciences

From our work with other partners, following challenges emerge:

  • Get more from less
    • Can we make existing resources more efficient?
  • Beyond attribution
    • What drives a manager's investment and style?
  • Fee drag
    • Can we get the same results with lower fees?

Common Problems

©2019 Economic Data Sciences

Clients are looking for personalized, real-world solutions

  • Beyond portfolio theory
    • Is there a portfolio construction tool for the real world?
  • 'Fat'-Tail Risk
    • How can we manage down markets that hurt performance and can permanently impair capital?
  • Balancing risk and opportunities in their many forms
    • How can we determine the 'right' trade-off for our investments?

The Case for Artificial Intelligence

©2019 Economic Data Sciences

Significant performance improvement when combined with humans

At its core, A.I. allows for a broader, deeper analysis
Provides significant improvement in efficiency

It has a unique ability to make improvements by searching across every known factor to get the best from existing best-practices

56% of institutional investors plan to increase integration of A.I.*

* - Greenwich Associates 2018 survey

A.I. is best used when combined with humans

A.I. Already Impacts Your Investments

©2019 Economic Data Sciences

  • Market participants are quickly adapting
    • 2013 these groups were negatively correlated, in 2018 strongly positive

The observable impact of A.I. in hedge funds is clear*

*Past performance is not a reliable indicator of future results, Yearly performance available in the Appendix

Hiring A.I. Manager is Not Sufficient

©2019 Economic Data Sciences

  • Best practice in risk management limits investment into any single manager
    • As a result, any investment in a Manager using A.I. will have a relatively small impact at the total portfolio level
  • The market learns quickly and is incorporating A.I.
    • Decreases the potential each individual manager can bring
  • Multiple A.I. managers won't coordinate efforts
    • This significantly detracts from A.I.'s potential
  • Real A.I. value add: supplement entire investment process

Best benefits are generated from integration with investment process

A.I. Is Transformational

©2019 Economic Data Sciences

Using A.I. in financial services has become industry best-practice

  • Aug 2017: 20% usage of A.I. or Machine Learning
  • Aug 2018: 56% usage

Blackrock Data Science Core

Exploratory programs on machine learning

  • A.I. based risk management
  • Dynamic factor analysis using A.I.
  • A.I. reconciling investment decisions

EDS A.I. Approach

Combining several A.I. implementations to make for more understandable solutions

Machine Learning

Human + Machine Insight

Best Trade-offs In A Complex World

Broader, Deeper, More Detailed

Extending research from Stanford our modelling process flexibly incorporates data and checks for robustness

Combining the power of distributed computing, our A.I. solves problems simultaneously  by combining optimization with an approach inspired by genetic algorithms

Our custom built data infrastructure combines many of the latest open source foundations which we have extended to meet today's needs

©2019 Economic Data Sciences

Artificial Intelligence

Big And Fast Data

EDS A.I. Implementation

Software which incorporates more data and simultaneous decision making

Where Does EDS Tech Stack Up?

©2019 Economic Data Sciences

Cutting edge technology with focus on ease of interpretation

How We Work

©2019 Economic Data Sciences

EDS provides 3 possible partner collaborations:

  1. Consulting Services
    • Usually the preferred partner starting point
    • Providing full analysis and reporting
    • Popular areas: portfolio construction, manager selection, scenario analysis
  2. User Interface, Online Web Solution
    • Personalized functionalities based on individual requirements
    • EDS continues to advise as needed
  3. Data Infrastructure
    • EDS helps organize partner data, adding additional sources

EDS Offers a Unique Proposition

©2019 Economic Data Sciences

  • Expanding your current tools

    • Current tools consider only 2-3 dimensions
    • A.I. has unlimited potential to consider multiple dimensions
    • EDS incorporates all other models
  • Simultaneous evaluation of all metrics - A.I. and Machine Learning

    • Holistic perspective
  • Adapts to new information

    • A.I. adjusts the models based on new data
  • Customized preferences

    • Each optimization is adjusted based on client's preferences

Tangible Benefits to Working With EDS

©2019 Economic Data Sciences

EDS analysis has made immediate improvements in 91% of cases

*Past performance is not a reliable indicator of future results, yearly performance breakout in the appendix

Added benefit* across a wide range of situations and client types

Examples

©2019 Economic Data Sciences

Click to learn more

Disclaimers

©2019 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.

Appendix

A.I. in Wealth Management

©2019 Economic Data Sciences

Infrastructure Review

Building on Principals, a New Frontier

The EDS Infrastructure - Big Picture

©2019 Economic Data Sciences

Cloud Resources

We seamlessly combine physical and cloud resources which can be dynamically managed:

EDS Data Center

Combined Computing Power

Client Interface

Our Technology Stack

©2019 Economic Data Sciences

Scala

Zookeeper

The EDS Infrastructure - Components

©2019 Economic Data Sciences

Each component of the technology stack leads towards our infrastructure principals and a more effective solution

Cassandra Database Meets All Puts Data of Any Kind Closer To Analysis For Speed and Flexibility
Hadoop Distributed Disk Meets All Quickly Consumers Any Type of Data
Mesos Scheduler Meets All Coordinates Tools for 'Drop-in' Flexibility
Zookeeper Failover Coordinator Meets All Coordinates Redistribution of 'Duties' During Failures Or When Connections Are Dropped
Spark, Scala, and R Analytics Combined -- Meets All When Combined, Tools Provide Analytics In Ways That Align With Principals
Play Front-End Meets All Visualizes to client and collects client information
Component Purpose Principal What It Does

The EDS Infrastructure - Security

©2019 Economic Data Sciences

  • Point to point encryption over the network
    • Data is never exposed without encryption
  • Client to server encryption
    • In line with best practices at other banks. Each client session is encrypted regardless of where the client is connecting from
  • Cloud compute not cloud storage
    • We use the cloud for compute power not storage, we control the physical location of each data point
  • Multi-tiered security layers
    • Designed with multiple layers of security so each must be compromised separately

Always worth discussing

EDS Infrastructure - Summary

©2019 Economic Data Sciences

  • Scale and speed
    • Add nearly an unlimited number of 'factors' - qualitative/quantitative
    • Can run in seconds/minutes and so could be done 'live' for clients
    • Each analysis is applied for all
  • Data communication - goodbye to silos
    • Each part of the business process can share information
  • More in depth client feedback
    • Better understanding of client interest

These features make possible real advances 'on the ground'

Annual Performance Breakout

©2019 Economic Data Sciences

info@EconomicDataSciences.com

EDS Proposition

By Economic Data Sciences

EDS Proposition

  • 91
Loading comments...

More from Economic Data Sciences