Scribd
Upload
73 views10 pages

Machine Learning For Finance

Uploaded by

Madhavan ADP
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
73 views10 pages

Machine Learning For Finance

Uploaded by

Madhavan ADP
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 10

Machine Learning

for Finance
Leverage data-driven
analysis to identify
relevant financial trends.
Table of Contents

1 About the Course

2 Why Take This Course?

3 Course Takeaways

4 Course Content

5 Meet Your Instructors

6 Next Steps

7 Hear from Our Students

8 Our Strength in Numbers


8 weeks

1. About the Course Online with live,


interactive sessions

4.6 CEUs

Overview
The University of Chicago’s eight-week Machine Learning for Finance course will teach
you to collect, organize, and use data to perform advanced financial analysis using
algorithms, statistical techniques, and more. By the end of the course, you will be
equipped to produce robust financial analytics that enable your organization to carry
out business intelligence and turn insights into action.

2. Why Take This Course?


The course is designed for professionals interested in leveraging data-driven analysis
to identify relevant financial trends. Current and aspiring financial analysts, advisors,
and consultants will benefit from exploring the latest industry knowledge and
tools. Decision-makers across industries—from chief financial officers to business
development and risk managers to fintech entrepreneurs—will also gain valuable
insight to align, support, and execute finance strategy.

Enroll Now

Page 1
3. Course Takeaways

• Apply basic concepts of probability


and statistics to finance.

• Understand what exploratory data


analysis is and how to perform it
with Python and Pandas.

• Engineer new features and functions


from existing data.

• Comprehend how unsupervised


machine-learning models work and
when they can be useful.

• After successful completion of this


course, participants will receive a
credential certified by the University
of Chicago.

Page 2
4. Course Content

Module 1

Statistics Review and Introduction to Python


The ability to analyze large volumes of data is essential, especially in finance.
In this course, you will learn to use different models and tools to perform
data-driven financial analysis and apply what you learn to real-world
scenarios. We will review concepts related to probability and statistics,
as well as learn the basics of Python, to be used throughout the course to
implement machine-learning models. Finally, we will analyze a data sample
and make inferences by applying statistical measures and using basic Python
codes together with the Pandas library.

Module 2

Exploratory Data Analysis and Linear Regression


Here, we will further develop our understanding of Python and Pandas,
focusing on how to use them to analyze large databases and draw up key
statistical measures. We will also introduce the concept of linear regression—
our introduction to machine learning. Based on a working example, you
will take a data sample, generate a model that describes the relationship
between two variables from that data, and then use the model to make
predictions for data outside our sample space. You will use Python, Pandas,
and two of the most popular machine learning libraries for Python, sklearn
and statsmodels.

Module 3

Advanced Linear Regression and Model Building


As our data sets get longer and more complicated, building a robust model
to handle complex data’s intricacies can be challenging. To tackle this, we can
use feature engineering to transform some of our data to fit a linear regression
model better or the train-test split and cross-validation methods. In this
module, we will also learn how to deal with over-fitting, which occurs when
our model-fitting outcome corresponds exactly or too closely to a particular
set of data, rendering it unable to predict out-of-sample data correctly.

Page 3
Module 4

Time Series Modeling


In finance, we often encounter a special kind of data, time series data. As
the name implies, a time series is essentially a data sequence with a time
component, meaning that all data observations are recorded over time. A
straightforward example of this can be measuring the price of a stock over
time, where the time interval between each observation is the same (e.g.,
weekly, monthly, or yearly stock price). In this module, you will learn why we
cannot use linear regression models with time series. Instead, we use AR, MA,
and ARIMA models, and you will learn how to implement in Python.

Module 5

Advanced Time Series


In this module, we will take our time series models to the next level through
backtesting and GARCH/ARCH models. Backtesting a time series model
will allow us to test the model’s performance on past historical data. The
underlying idea is similar to cross-validation in regression models but is
implemented differently. Backtesting is a prevalent technique implemented
in trading analytic scenarios. GARCH/ARCH models are widely used in
financial institutions to estimate the volatility of different assets, such as
stocks, bonds, or market indices.

Module 6

Classification, Unsupervised Learning, and Ensemble Methods


This module covers classification models, which can categorize data into
various classes. We will analyze unsupervised machine learning models
for working with data that do not have a target variable. Unsupervised
models can spot underlying patterns even where our data does not have a
clear dependent variable. You will also examine ensemble methods, where
several models are created for certain data and then combined to improve
the overall model’s performance. By the end of the module, you will have a
broader vision of machine-learning techniques and how to implement them
for data analysis.

Module 7

Risk and Portfolio Selection


In this module, you will be introduced to the concept of simulation as a method
for answering financial questions. Specifically, we will use the Monte Carlo
method to study portfolio risk. To do this, we will first examine the essential
definitions of risk and return, exploring key concepts such as capital allocation,
standard deviation, consumers’ preferences, risk aversion, utility values,
covariance, and correlation.

Page 4
Module 8

Advanced Concepts in Financial Analysis


Our last module explores several advanced concepts in financial analysis,
including deep learning and big data. Data continues to get bigger every
day, so we must understand how financial institutions are tackling today’s
data challenges. We will define big data as the field that offers methods
to extract and analyze information from large datasets that are difficult to
handle with traditional data-processing applications. You will also look at
implementing solutions in Python and learn how to analyze legacy systems
that are considered outdated, which many financial databases still rely on.

5. Meet Your Instructors

Lara Kattan, MPP


Data Science Educator and Curriculum Writer

Lara Kattan is a data science educator and curriculum


writer. She is currently developing curriculum for
• Seasoned data science institutions such as the University of Chicago and
manager. data science learning start-ups. Before embarking
• Specialist in Python, on a career in curriculum development, she was a
R, Tableau, SQL, and consultant in risk practice at McKinsey & Co.
Snowflake.

• Passionate about
Kattan earned an MA in public policy with a
economics, statistics, concentration in econometrics from the University of
and machine learning. Chicago and a BA in economics and political science
from Northwestern University. A lifelong learner, she
is also pursuing master’s degrees in computer science
and mathematics from DePaul University.

Page 5
6. Next Steps

Complete the form on the registration page.

Pay the tuition fee through our secure gateway.

Receive a welcome email with your login


information for the virtual campus.

Gain access to the course content prior to the


course start date.

Enroll Now

7. Hear from Our Students

Derrick Walker
Alumni

“This course enhanced my understanding of application principles


and increased my confidence to make decisions related to
problems that can be solved by applying the concepts covered.”

Page 6
8. Our Strength
in Numbers

130+ years of
history

Since 1890, the University of Chicago has been creating transformative


academic experiences. It is the home of pioneering schools of thought and
the birthplace of initiatives that address the world’s most pressing issues.

99 Nobel
laureates
University of Chicago faculty and affiliated scholars are international leaders
in their fields. As it deepens knowledge and enriches society, their work is
both enduring and ever evolving.

1 global
community
UChicago alumni around the world go on to become world-changing
researchers, CEOs, university presidents, literary giants, and government
leaders. They shape industries, break scientific barriers, create disruptive
technologies, and forge new paths of knowledge. Want to join them?

Page 7
[email protected]
Schedule an appointment

You might also like