Class 2: Introduction to Machine Learning for Lawyers - in this class we expand both our tactical and theoretical understanding of machine learning.  From a tactical perspective,  students are introduced to Github and RMarkdown.  From a theoretical perspective, we contrast supervised and unsupervised learning using an applied legal example.   We conclude by discussing the bias / variance tradeoff as well as the distinction between precision and recall.


Daniel Martin Katz   <CV> <SSRN> <arXiv>
Michael J. Bommarito  <CV> <SSRN> <arXiv>

Review Modules
I.     Review Materials (Intro to Stats, Regression, etc.)
II.    R Tutorials <Install> <Part1> <Part2> <Bonus>
III.   Github and RMarkdown Tutorial

Course Modules
1.    Introduction to Legal Analytics
2.    Introduction to Machine Learning for Lawyers
3.    Quantitative Legal Prediction + Business of Law
4.    Bias/Variance, Precision/Recall & Dimensionality
5.    Overfitting, Underfitting, & Cross-Validation
6.    Logistic Regression and Maximum Likelihood
7.    K Nearest Neighbors + Naive Bayes Classifiers
8.    Binary Classification w/ Decision Tree Learning
9.    Ensemble Models including Random Forests
10.  Clustering (K-Means & Hierarchical Clustering)
11.  Data Visualization and DataViz in R
12.  Data Preprocessing and Cleaning using dPlyR
13.  Network Analysis and Law
14.  Natural Language Processing (NLP) Overview
15.  Applied Legal Analytics - Contract Analytics
16.  Applied Legal Analytics - Exploring SEC Data
17.  Applied Legal Analytics - Judicial Prediction
18.  Applied Legal Analytics - Regulatory Outcomes
19.  Applied Legal Analytics - Sentiment Analysis
20.  Advanced Topics - Support Vector Machines
21.  Advanced Topics - EM Algorithm  
22.  Advanced Topics - Neural Networks
23.  MLaaS and Shifting Economics of #BigData