ISYS 573: Gen AI and LLMs for Business

Spring 2025

Zoom MeetingTime: T 6:30-9:15 PM

Virtual Office Hours: T 5:30-6:30 PM

Generative AI (Gen AI) and large language models (LLMs) are revolutionizing our personal and professional lives.

From supercharged digital assistants that manage our email to seemingly omniscient chatbots that can communicate with enterprise data across industries, languages, and specialties, these technologies are driving a new era of convenience, productivity, and connectivity. In the business world, Gen AI automates a huge variety of menial tasks, saving time and improving efficiency: it aids in data analysis, automates content creation, and enhances personal experiences. Gen AI models generate entirely new outputs rather than simply making predictions based on prior experience. This shift from prediction to creation opens up new realms for business innovation. For example, while a traditional predictive model can spot excellent investment property opportunities on Zillow (using tools such as Zestimate and Zillow enhanced AI search), a Gen AI app can also determine the likelihood that a property with certain characteristics will become available or what renovations and improvements will enhance the value of a property offering recommendations based on best practices gleaned from thousands of similar cases. Large language models (LLMs) are deep neural network models that have been developed over the past few years. LLMs have remarkable capabilities to understand, generate, and interpret human language. The success behind LLMs can be attributed to the transformer architecture which underpins many LLMs, and the vast amounts of data LLMs are trained on, allowing them to capture a wide variety of linguistic nuances, contexts, and patterns that would be challenging to manually encode. This course provides an in-depth study of business oriented LLMs. It also focuses on the implementation of LLMs in different business contexts with sample business use cases. In addition, it covers topics including working with text data, attention mechanisms, semantic search, prompt engineering, and moving Gen AI and LLMs into production.

The course applies Gen AI and LLMs to practical business problems such as customer service with question answering, sentiment analysis, and visual QA. The course also includes topics on surveying and comparing different Gen AI and LLM offerings as well as how do we create ethically responsible Gen AI and LLMs implementations in a business environment.

By the end of this course student will be able to:

Understand the components of Generative AI and Large Language Models (LLMs)
Understand the use of the Python language and the standard PyData stack: NumPy, SciPy, Pandas, and Scikit-Learn, as well as the use of Keras with TensorFlow for deep learning and Gen AI, and PyTorch for LLMs.
Learn tools for building Gen AI and LLMs including jupyter notebooks.
Understand the application of Gen AI and LLMs to solve business problems such as:
Working with text data for sentiment analysis
Implementing sophisticated question answering
Analyzing visual data to detect aberrations.
Learn how to implement Gen AI and LLM in a business environment.
Understand the best ethical practices for implementing Gen AI and LLMs in a business environment.