Statistician
Data Scientist
Artifical Intelligence
What humans find easy but computers find hard
Why Now?
What can we do?
\[ \boldsymbol{Y} \sim N(\boldsymbol{X}\boldsymbol{\beta}, \boldsymbol{\Sigma}) \]
Pass vs Rush
Pass vs Rush by Down
Binary Regression
\[ p(y_i=1) = \text{logit}^{-1}(\boldsymbol{X}_i\boldsymbol{\beta}) \]
\[ \text{logit}^{-1}(x) = \frac{e^x}{1+e^x} = \frac{1}{1+e^{-x}} \]
Decision Tree
\[ \hat{f}(x)=\sum_{m=1}^M\hat{c}_mI(x \in R_m) \]
Gradient Boosted Tree
\[ \hat{y}_i^{t} = \sum_{k=1}^t f_k(x_i) = \hat{y}_i^{(t-1)} + f_t(x_i) \]
Neural Network
What We Saw
with
Linear Models
with
Binary Regression - Boosted Trees - Neural Network
with
Network Analysis - Matrix Factorization
Thank You
Jared P. Lander
- Chief Data Scientist of Lander Analytics
- Author of R for Everyone
- Adjunct Professor at Columbia University
- Organizer of New York Open Statistical Programming (The R) Meetup
- Organizer of New York R Conference
