Getting Started

Course Description

What This Course is Not About

• This is not a computer science class (we're not going to be talking about compliers!)

• This is not a finance class (we're not going to be covering options, bonds, etc)

What This Course is About

• This class is about "learning from data"

• How do we physically analyze data (load & code)

• How do we interpret statistical results

• How do we present results and uncertainty to others

Immediate Aim: Learn how to perform data analysis

Long Term Aim: How to improve a business via data analytics

Prerequisites

• We're more or less going to teach everything from scratch

Start

How to create a variable in Python

Start

How to create a variable in Python

Start

How to use language models to analyze data

End

Keys to Success

• Don't confuse inexperience with inability

• Work a consistent amount each week 

• Lean into your interests

Grading

Homework (20 %)

• Weekly homework (one or two problems related to each lecture)

• Graded for completion not accuracy

Participation (5%)

• Do you enhance the learning experience for those around you

Exams: Midterm & Final (25% each)

• Open Note

• Python Based

• Not Cummulative

Final Project

• Develop a project of interest that leverages the tools and skills developed during the course of the semester

Final Project (25%)

Examples

• Conduct a market feasibility report for a eduction startup

• Develop a model that can predict the Supreme Court Rulings

• Construct a model than can predict lead paint or mold issues in NYC Housing Authority Units

Motivation

Why Business Analytics

Why Business Analytics (BA)?

Motivation

How has Generative AI impacted this class?

Andrej Karpathy

Jensen Huang

Sal Khan

"The Two Sigma Opportunity: Using AI to Provide a One-to-One Tutor for Every Student and Teaching Assistant for Every Teacher"

Case Studies for Data Science Jobs

During this interview I’ll go over your qualifications, discuss the role in general and the specific research projects and spend 10-15 minutes on a case study. It will be high-level; I’ll introduce a problem and have you discuss your thought process and how you would proceed to solve the question. There won’t be any on-the-spot coding.

The fundamentals

The Essence of Programming

(1) Data Storage

(2) Functions

The Essence of Causal Inference

Local Variation of Treatement

The Curse of Dimensionality

The Essence of Statistics

(1) Defining some notion of similarity

(2) Defining a relative notion of "simple"