ROBO ADVISORS & SYSTEMATIC INVESTING - INFO.UB.52.001 Spring 2021 - NYU
←
→
Page content transcription
If your browser does not render page correctly, please read the page content below
ROBO ADVISORS &
SYSTEMATIC INVESTING
INFO.UB.52.001 Spring 2021
Instructor Professor Vasant Dhar
Classroom
Class times
Exam date/time One week after the last class
Grader
Office Hours Preferred communication: Email and telephone;
4:30-6PM on day of class and by appointment
Internet Email: vdhar@stern.nyu.edu
URL: www.stern.nyu.edu/~vdhar
Numbers Office (212) 998-0816, Fax: 995-4228
“Follow the plan, and you'll be surprised how successful you can be. Most people
don't have a plan. That's why it's easy to beat most folks.” Bear Bryant.
The most important requirement in the virtual classroom is complete attention and visible
faces!
Seriously, visual cues are an essential in teaching, so I expect cameras to be always on.
1. COURSE SYNOPSIS
I am a “pracademic” who has been trading professionally for over 25 years. I brought
machine learning to Wall Street in the 90s, when I set up the first systematic machine
learning program at Morgan Stanley in the 90s. My one piece of advice to any aspiring
trader is to find a robust “system” instead of “gut feel” because the vast majority of
humans are terrible investors. You need a machine!My experience is that as financial markets have become more information-rich and
liquid, a higher degree of knowledge about analytics and systems is required in order to
compete. In Bear Bryant’s terms, it means “having a plan.” We think of this as following
a repeatable scientific method to financial decision making.
This course teaches students how modern financial markets function and how to use the
information emanating from these markets for systematic investing, specifically how to
build and implement the analytics associated with designing and implementing
systematic computer-based models for investing.
The course covers the basis, evaluation and execution of trading strategies that are
commonly used by professionals in financial markets. There is increasing interest in
particular, on systematic trading strategies and execution systems because of their
consistency in decision making, transparency, scalability and freedom from emotion. The
central objective of this course is to understand the essence of systematic trading, key
elements of which are the basis for generation of “alpha,” and how to think about and
control the various types of risks associated with systematic trading systems. The
strategies are grounded in data of various forms including prices, fundamentals, as well
as unstructured data from news sources. During the second half of the course, we will
increasingly touch on how to think about Machine Learning in creating trading strategies.
In terms of effort and focus, the first part of the course requires an intensive coverage of
systematic trading through regular hands-on assignments. This provides you with the
tools and thinking you will use in your project which you should focus on during the
second part of the course, but start thinking about as early as possible. A project can be
defined in many ways. For example, it might involve the development of a trading
strategy (i.e. a factor model for predicting returns) or try to answer a general question like
“Is method X better than method Y for predicting returns for asset Z?” The important
thing is that the inquiry be conducted scientifically and rigorously.
2. LEARNING GOALS
There are two main learning goals and a secondary one associated with this course:
I. Critical and Integrative Thinking: specifically, how do you transform a trading
idea into a concrete description that can be described and modeling using a
program or a spreadsheet. The spreadsheets created from the various assignments
are usable as “templates” for developing more advanced strategies. In addition to
translating an idea into a model, students will learn how to draw and assess
conclusions from the model and data provided. You are free to use other software
for testing more sophisticated strategies, especially for your project.II. Effective Oral Communication: Each student shall be able to communicate
verbally in an organized, clear, and persuasive manner, and be a responsive
listener.
III. Interpersonal Awareness and Working in Teams: Students will submit a project
which may entail working in a small group (two people) and must apportion tasks
appropriately and submit a quality product in a timely manner.
The course strikes a balance between theory and practice by grounding the discussion in
the current state of financial markets. The course requires students to do several hands-on
exercises with real market data. The exercises start with a review of simple concepts of
risk and return and progress to realistic trading strategies that students build and evaluate.
The objective is to help you understand how to assess markets in an orderly and scientific
way so as to be able to draw sound inferences from the analysis.
The course should be of interest to students across the financial services industry. It will
not transform you into a trading expert, which takes considerable effort, time, and pain. It
will, however, bring the concepts of risk and return alive by working with real data and
exercises, and through industry experts describing their approach to fund management
and administration. More generally, the course should give you a clearer appreciation on
the fact that understanding markets is a theory building exercise, where professionals
spend a lot of time in understanding emerging market phenomena with the objective of
translating their insights into profitable strategies. These concepts are useful regardless of
your specific interest in the financial industry, i.e. whether you intend to be a trader, risk
manager, controller, salesperson, or analyst.
Self-learning is a particularly important part of this course. You will get the best value
from this course if you experiment actively with ideas and actively construct and test
trading strategies instead of just coming to class and expecting to be told what works and
what doesn’t. There’s nothing like learning by doing. Accordingly, 50% of the grade is
assigned to your project. So, start early. Exploratory work always takes longer than you
think. Indeed, your very first assignment is to write a 1-2 page summary of what you
might do as your project. Even if you end up changing topics, the exercise will help you
get started in thinking about it seriously, before you get into the nitty-gritty of the
quantitative exercises.
3. COURSE MATERIALS
There is no required textbook for this course since none of the available books in this area
satisfy the majority of the objectives of this course. The following book, for example,
describes at a high level the basis for quantitative trading strategies used by portfolio
managers but doesn’t provide enough detail or hands-on examples for how to build
strategies:
Inside the Glass Box: The Simple Truth About Quantitative Trading, Rishi Narang,
2013In contrast, for those students wanting details on market indicators and measurement, a
useful textbook is:
New Trading Systems and Methods, Perry Kaufman, Wiley 2014
The above textbook is biased towards practice at the expense of theory and it has detailed
descriptions of market indicators and methods, which makes it a good reference. It is not
mathematically rigorous, but useful in helping you think about measurement issues with
time series data, commonly used types of indicators to describe states of markets, and
vanilla models from which portfolio managers build more elaborate strategies.
The following textbook provides some of the latest research with real-world examples
and interviews with top hedge fund managers to show how certain trading strategies
make money and why they sometimes don't:
Efficiently Inefficient: How Smart Money Invests and Market Prices are
Determined, Lasse Pedersen, Princeton University Press, 2015.
The book is a great source of ideas for your term project.
A set of current readings for each session will be posted on the website that you must
read prior to each class. In addition to these readings, the course will provide datasets that
will be used for the assignments. The assignments are simple, and intended to serve as a
foundation for thinking about more sophisticated trading strategies you might build going
forward. In order to keep the material accessible, all examples are illustrated in Excel.
Since one of the main objectives of the course is to provide you with hands-on skills in
developing and understanding trading strategies, several datasets are provided including
the following:
1. Daily S&P500 cash data 1960-2005
2. Daily data for selected currency, fixed income, equity futures, and commodity
futures
3. Intraday (minute level bars) for select futures contracts
4. Fundamentals (Trade Balance) data for currencies (aligned with the dollar index)
5. Yield curve dynamics data for currency trading
6. Fundamentals-based aggregated equities data
7. Equities data for spread-based (pairs) trading
8. News-based sentiment data for equities
9. High frequency data on select futures contracts including equity, bond, currency,
and commodity indices
All materials (except for late breaking articles and non-electronic information) are posted
on the class website. Students are also encouraged to explore the Internet for materials
relevant to the course.4. EVALUATION
Assignments
Since this is a hands-on course, there are several small assignments involving data
analysis. You must have reasonable Excel skills to do these assignments. There are up to
six such assignments. You must also participate in class discussion and come prepared to
present your analyses to the class. Each class where an assignment is due will begin with
several students at random being chosen to present their results. All assignments due on
a particular date must be submitted prior to the beginning of class. Late
submissions will not be accepted.
Project
In addition, you must hand in a term project describing a complete trading strategy. It is
preferable if this strategy is demonstrated using data and analysis, but conceptual
analyses are also acceptable. Examples of things you could explore are:
Has COVID resulted in a “paradigm shift” in trading, and if so, how? Does it
impact how we think about systematic investing?
Are there newer “alternative data” sources (social media, cargo patterns etc.) that
provide value in their ability to predict certain markets or securities?
Is there any relationship between current volatility and future returns in equity or
currency markets in the US or other markets?
Which macroeconomic indicators have exhibited a consistent influence on
financial markets and what could explain this? Is it possible to blend such “lower
frequency” data with higher frequency data like prices?
(How) and when does spread-based trading work and why?
Are currencies driven by short-rates or the longer end of the yield curve?
Which fundamentals or technicals spread-based or directional trading strategy
works on indices, individual/pairs, ETFs, etc.?
Engineer a system where you can describe the market conditions under which it
would make and lose money. How would you position such a system for
investors?
Does technical analysis work? I.e. Doji based systems, Bollinger bands, etc.
How could one design a news-driven sentiment analysis system for trading
individual equities or equity/currency/commodity indices?
Can you predict the inclusion or exclusion of stocks from indices?
How does inclusion in ETFs impact the behavior and performance of stocks?
Is it possible to predict or capitalize on a “short squeeze” in stocks?In the past, students have turned in interesting projects in a number of areas that typically
“expand” on an assignment, such as testing pairs trading “on scale” across all equities in
a sector or market index or commodities (such as related energy futures contracts),
extending pairs trading to “baskets,” exploring and integrating currency strategies across
multiple timeframes, behavior of markets around options expiration, and so on. Creativity
and exploration is highly encouraged.
Start early on your project. The assignments are “front loaded” and largely done midway
through the course which should give you time to focus on your term project.
There is no final exam. The grade breakdown is as follows.
i. Assignments: 50 points
ii. Term paper on a trading strategy: 40 points
iii. Class participation and attendance: 10 points
iv. Final Quiz (perhaps): 10 points
5. ATTENDANCE AND PUNCTUALITY
Every session covers a specific type of trading strategy and each session builds on the previous
ones. Sessions also discuss “tips and tricks” you will not find in readings or books. Complete
attendance is therefore critical. Class participation is an equally important part of the learning
process. Absence is only appropriate in cases of extreme personal illness, injury, or close family
bereavement. Voluntary activities such as job interviews, business school competitions, travel
plans, joyous family occasions, etc. are never valid reasons for missing any class. Students who
miss two or more sessions without notice will get a zero on attendance.
Late arrival is disruptive to the learning environment; so please arrive before the scheduled time. \
6. PRE-REQUISITES
There are no pre-requisites for this course, except reasonable Excel skills and an enthusiasm to
work with data. However, knowledge about financial markets and financial instruments never hurts!
7. ACADEMIC INTEGRITY/EXPECTATIONS
Integrity is critical to the learning process and to all that we do here at NYU Stern. As
members of our community, all students agree to abide by the NYU Stern Student Code
of Conduct, which includes a commitment to:
Exercise integrity in all aspects of one's academic work including, but not limited
to, the preparation and completion of exams, papers and all other course
requirements by not engaging in any method or means that provides an unfair
advantage.
Clearly acknowledge the work and efforts of others when submitting written
work as one’s own. Ideas, data, direct quotations (which should be designatedwith quotation marks), paraphrasing, creative expression, or any other
incorporation of the work of others should be fully referenced.
Refrain from behaving in ways that knowingly support, assist, or in any way
attempt to enable another person to engage in any violation of the Code of
Conduct. Our support also includes reporting any observed violations of this
Code of Conduct or other School and University policies that are deemed to
adversely affect the NYU Stern community.
The entire Stern Student Code of Conduct applies to all students enrolled in Stern courses
and can be found here: www.stern.nyu.edu/uc/codeofconduct
To help ensure the integrity of our learning community, prose assignments you submit to
NYU Classes will be submitted to Turnitin. Turnitin will compare your submission to a
database of prior submissions to Turnitin, current and archived Web pages, periodicals,
journals, and publications. Additionally, your document will become part of the Turnitin
database.
GENERAL CONDUCT & BEHAVIOR
Students are also expected to maintain and abide by the highest standards of professional
conduct and behavior. Please familiarize yourself with Stern's Policy in Regard to In-
Class Behavior & Expectations (http://www.stern.nyu.edu/portal-partners/current-
students/undergraduate/resources-policies/academic-policies/index.htm) and the NYU
Student Conduct Policy (https://www.nyu.edu/about/policies-guidelines-
compliance/policies-and-guidelines/university-student-conduct-policy.html).
STUDENTS WITH DISABILITIES
If you have a qualified disability and will require academic accommodation of any kind
during this course, you must notify me at the beginning of the course and provide a letter
from the Henry and Lucy Moses Center for Students with Disabilities (CSD, 998-4980,
www.nyu.edu/csd) verifying your registration and outlining the accommodations they
recommend. If you will need to take an exam at the CSD, you must submit a completed
Exam Accommodations Form to them at least one week prior to the scheduled exam time
to be guaranteed accommodation.8. TIMETABLE (subject to slight revision):
Session Topic Reading/Preparation (posted on BB) Submission/Handout
1 Introduction and Should You Trust Your Money to a Robot?
Course Objectives https://www.liebertpub.com/doi/10.1089/big.2015.28999.vda
2 Measurement Basics: Life at Sharpe’s End Assignment RISK
I handed out
Measurement https://www.bloomberg.com/opinion/articles/2019-03-06/a- Assignment RISK due
3 Basics:II money-manager-s-past-performance-does-matter Assignment ETF
Comparing strategies handed out
ETFs and Volatility Link to paper on website Assignment ETF due
4 Assignment VOL
handed out
Trend Following Reading: Kauffman Assignment VOL due
5 Systems & Futures Chapter 8 Assignment TREND
Markets handed out
Trend and Counter- Reading: Riding the Wave Assignment TREND
6 trend systems Reading: website link due
Assignment CT
handed out
Spreads and pairs Kauffman Chap13: Spreads and Arbitrage; Assignment TREND
trading in Equities Dickey-Fuller test handout due
7 Markets Assignment SPRD
Trading “neutral” handed out
portfolios
MIDTERM BREAK
Pairs trading review; Readings: TBD
8 Basket and
ETF/Passive
Investing
Currencies: Technical FX Guide Assignment SPRD due
9 Strategies, Flow- Battle of the Dollar Assignment CUR
based Strategies and handed out
Carry trades
Machine Learning TBD
10 and Artificial
Intelligence in
Financial Prediction
News-based Trading Chapter 15 from High Frequency and Algorithmic Trading
11 Systems: interpreting Late breaking articles on BB
“big” unstructured
data
High frequency High Frequency Trading Assignment CUR due
12 trading: reading
Interpreting “big”
structured data
13 Student Projects
14 Student Projects Projects are due within
one week
15 Final Quiz (perhaps)You can also read
