Study material - Hard Copy available on request (chargeable extra)
For further clarification or information on the same, please do whatsapp on +91 9674006544
Topic
MODULE 1 - PRIMER
1. Introduction to Machine Learning
a. What is Machine Learning
b. Types of Learning (Supervised, Unsupervised, Reinforced)
c. Structured vs Unstructured Data
d. Machine Learning and the World today!
e. Specific Use cases in Finance
2. Math toolbox for ML
a.Linear Algebra
i. Vector Algebra (Addition, Product, Projections)
ii. Matrix Algebra (Transpose, Multiplication, Inverse, Eigen Values)
b. Optimization
i. Maxima and Minima (calculus based)
ii. Lagrangian Multipliers
iii. Gradient Descent
c. Parameter Estimation
i. Maximum Likelihood Method (MLE)
ii. Maximum a Posteriori (MAP)
3.Getting Started with Python
a.Importing Libraries
b. Data types and Functions
c. Data Preprocessing (Missing Data, Categorical Encoding)
d. Splitting to Training, Validation and Testing sets
e. Feature Scaling
Module 2 – Supervised Learning (Regression)
4. Linear Regression
Introduction and Objective
Cost Function (MSE vs MAD)
Simple vs Multiple Linear Regression
Regression Assumptions (Multicollinearity, Exogeneity, Serial Correlation, Homoscedasticity)
Parameter Estimation (Analytical and Gradient Descent)
5.Stepwise Regression for High Dimensional Data
Forward Selection
Backward Elimination
Least Angle Regression (LARS)
6. Polynomial Regression
7. Support Vector Regression
Linear SVR
Kernel SVR
8. Decision Tree Regression
Splitting, Stopping
Bagging and Boosting
9. Random Forest Regression
10. Regression Model Selection and Performance
9. K - NEAREST NEIGHBOUR
1.K-Nearest neighbour
2.K-means protype
10. Bayes Theorem
Module 3 – Supervised Learning (Classification)
11. Supervised Learning – Classification
Introduction and Objective
Loss Functions (Logistic Loss, Hinge Loss)
Confusion Matrix and ROC
12. Classification – Logistic Regression
Logistic Regression
Multinomial Logit
Multiordinal Logit
13. K-Nearest Neighbor (kNN)
14. Naïve Bayes Classifier
15. Linear and Quadratic Discriminant Analysis (LDA)
16. Support Vector Machines
17. Decision Tree Classification
18. Random Forest Classification
19. Classification Model Selection and Performance
Module 4 – Anomaly Detection
20. One Class SVM
21. Isolation Forest
Module 5 – Unsupervised Learning
22. Dimensionality Reduction
Principal Component Analysis (PCA)
Kernel PCA
23. Clustering
Hierarchical Clustering
K-Means Clustering
Density Based Clustering
Module 6 – Reinforcement Learning
24. Upper Confidence Bound
25. Thompson Sampling
Module 7 – Natural Language Processing (NLP)
26. Processing Unstructured Data
27. Word2Vec
28. Feature Selection (Chi-sq and MI)
Module 8 – Deep Learning
29. Artificial Neural Network (ANN)
30. Recurrent Neural Network (RNN) and Long short term Memory (LSTM)
31. Convolutional Neural Network (CNN)