Use data-driven analysis to identify relevant financial trends.
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 with algorithms and statistical techniques and tools.
Designed for financial professionals who want to develop a career in the present-day financial industry or in an organization’s finance department.
Organizations are constantly trying to streamline processes, cut costs, and drive profitability. Data has become a key driver in producing better financial analytics, providing leaders with the insights they need to make strategic decisions.
After completing the course you will be able to:
- Apply basic concepts of statistics to finance, including the random walk model
- Understand what Exploratory Data Analysis is and how to perform it with Python and Pandas
- Engineer new functions using existing data
Financial Analytics curriculum
Understand how to use data to perform advanced financial analysis with algorithms and statistical techniques and tools in order to make strategic financial decisions in your organization.
You will learn to:
- Review statistics and probability and apply basic concepts of statistics to finance
- Understand what linear regression is, when to use it, and how to apply linear regression metrics to a model
- Make models more rigorous by adding train/test split and cross-validation
- Backtest a model and understand why backtesting is important
- Use simulation to solve a portfolio allocation problem
- Converse at a high level about several advanced topics in financial machine learning
Online learning course structure
- Eight weeks in length
- Weekly, self-paced interactive learning modules and assignments are time-sensitive and should be completed by the set deadlines
- Synchronous sessions and live question and answer sessions
- Mentors will provide continuous support and encourage a dynamic and positive learning environment
Weekly course schedule
Gain an introduction to Python, which covers variables, functions, control structures, loops, and Pandas, and learn about probability and statistics, including statistics for finance.
Learn about exploratory data analysis including the univariate and bivariate models, scatterplots, histograms, and boxplots, as well as regression and regression metrics.
Understand how to conduct train-test splits, cross-validation, and overfitting and regularization; learn about feature engineering and selection, more specifically in terms of transforming independent and dependent variables; before delving into its application to finance, such as returns and interest rates.
Define ARIMA modeling, and learn about stationarity for time series models, metrics and tests; and use the statsmodels package in Python to build an ARIMA model.
Discover the different types of testing regimes, such as backtesting a time series-ARIMA model; simple rolling pseudo-out-of-sample backtesting; cross-validation backtesting; and back-testing for linear regression, and learn to monitor and troubleshoot models in production.
Understand logistic regression and metrics, such as accuracy, precision and recall, and confusion matrix. Learn about ensemble methods such as bootstrap aggregation, random forests, and boosting, as well as clustering.
Define “risk” in finance such as no variance in returns; risky and risk-free assets including expected returns and variance. Learn about resampling and efficient portfolios, such as utility functions, and use Monte Carlo simulation for out-of-sample testing.
Become familiar with cloud computing and industry leaders such as Amazon Web Services, Google, and Microsoft. Understand deep learning and neural nets, including back propagation and keras. And, learn about bayesian inference with a focus on beyond frequentist statistics and PyMC3.
Connect with expert instructors
Our course instructor has extensive experience in data analytics and fintech, as well as many years of experience in the world of finance, which she is ready to share with you.
Traditional financial reporting like profit and loss statements, balance sheets, cash flows, and variance analysis are no longer enough. Today’s businesses need data-based financial analysis to gain deeper insights that will allow them to connect business operations to long-term value, model scenarios in real time, and allocate resources efficiently. The increasing demand for advanced finance functions such as connecting operational KPIs to financial metrics, along with technological advancements in cloud-based services, has led to the financial analytics market’s current valuation of 6.32 billion. Experts anticipate it will nearly double in size by 2026, with a projected value of 11.02 billion.
Potential job titles in Financial Analytics
- Asset/Wealth Manager
- Commercial Banker
- Finance Manager
- Financial Advisor
- Financial Analyst
- Investment Banker