• To give introduction of machine learning techniques to students
• To provide knowledge of Python programming
At the end of the course, students should be able to:
Unit I (4 weeks)
Data Manipulation using Python: Introduction to Python, IDE’s (Jupyter, Spyder), custom environment settings, Data Structure: basic data types (numeric, string, float, date timestamp), aggregate functions, conditions (if-elif-else), looping (for, while), inbuilt functions for data conversion, writing user defined functions. Concepts of packages/libraries – important packages like NumPy, scikit-learn, scipy, sympy, math, Pandas, Matplotlib, etc. importing packages using pip, reading and writing data from/to different formats: Data frame, arrays, list of list, series, sets, dictionaries, plotting, functions, list comprehensions (index comprehension). Application of machine learning algorithm for solving problem in financial markets.
Dive into PYTHON 3 by Mark Pilgrim : Chapters 1, 2, 4
Python Machine Learning by Sebastian Raschka: Chapter 3
Unit II (2 weeks)
Machine learning: Introduction, Definitions, Supervised, unsupervised, python libraries for machine learning, Sci-kit learn, Applications of Machine learning in Financial Technology (FinTech).
Machine Learning by Tom M. Mitchell: Chapter 1, 2, 4
Unit III (2 weeks)
Regression: Linear regression univariate and multivariate, nonlinear regression, over-fitting and regularization, logistic regression, Case studies based on regression techniques (using financial market data)
An Introduction to Statistical Learning by Gareth James: Chapter 3 and Chapter 4
Unit IV (3 weeks)
Classification: K Neighbors, K – means, decision Trees and SVM.
Clustering: Partial based clustering, hierarchical clustering, intensity based clustering, Neural Network: Single layer perceptron, multi-layer perceptron, back propagation algorithm applying neural network on financial market data
Machine Learning by Tom M. Mitchell: Chapter 3, 4, 6, 8