Advanced Data Science & Machine Learning in Python

Introductory Statistics and Econometrics

  • Probability Distributions

  • Bell curves

  • Null hypothesis H0

  • P Value

  • Type I & Type II errors

  • Degree of freedom

Linear regression using Python – OLS regression

  • Creating covariance matrix of variables

  • correlation and multicollinearity

  • Assumptions of OLS and its interpretation

  • R-square and goodness of fit

  • Practical Development of a OLS model and its performance evaluation

Logistic Regression using python – Probability distributions and Parametric modeling

  • Introduction to the concept of probability distributions

  • Dummy variables

  • Difference between OLS and a proababilistic model like logistic

  • Hosmer-Lemeshov statistics and KS statistics and concordance

  • Practical Development of a logistic model and its performance evaluation

Intro to Machine learnign and Deep learning concepts – Non-parametric modeling

  • Difference from parametric modeling

  • Classes of machine learning models – supervised learning and unsupervised learning

  • What is the logic behind neural networks

  • What are classification trees

  • Random forests and gradient boosting – an introduction

Random Forest modeling

  • Practical development of a RF model using data

  • Model parameter interpretation

  • Model performance evaluation – AUC and ROC

  • Model tuning

Artificial Neural Networks modeling

  • Practical development of a ANN model using data

  • Model parameter interpretation

  • Model performance evaluation – AUC and ROC

  • Model tuning

Gradient Boosting Models

  • Practical development of a GBM model using data

  • Model parameter interpretation

  • Model performance evaluation – AUC and ROC

  • Model tuning

Extreme Gradient Boosting Models – XGBoost

  • Difference from GBM

  • Model Hyper parameters

  • Model parameter interpretation

  • Model performance evaluation – AUC and ROC

  • Parameter tuning

Light GBM – Leaf Wise Tree Classification

  • Difference from GBM & XGBoost

  • Model Hyper parameters

  • Model parameter interpretation

  • Model performance evaluation – AUC and ROC

  • Parameter tuning

Reinforcement Learning

  • What is it?

  • Why to use it?

  • How to use it

  • Use Case and Example

Image Processing – Convolution Neural Network

  • What is Image processing

  • Basics of CNN

  • Convolution

  • Rectification

  • Pooling

  • Flattening

  • Connection

  • Compiling