Applied Data Science

Applied Data Science program was designed specifically for individuals who want to go in depth in advance topics in the Data Science field. This program is optimized to be the continuation for students who have gone through our Data Science Essential program in the past.

At the end of the program, students will be able to perform data scraping, analyze and deploy the model in the form of a web application such as a shopping recommendation engine similar to what's being implemented in modern marketplace like Amazon, Lazada and Shopee.

Learning Objectives:

• Able to implement standard regression and classification methods, as well as to understand concepts including, overfitting, underfitting, bias, optimization, regularisation and parameter tuning.
• Able to dissect the mathematics behind standard machine learning models, train, validate and test models and evaluate said models for accuracy.

Target Audience:

• Engineers, Business Development, Finance, Marketing Professionals, Software, and IT professionals

Training Outline:

• 1. Data Preparation & Exploration (Part 1)
• Writing and running Python scripts for data manipulation and mathematical computations.
• Learn how to navigate through projects and edit scripts using the command line.
• Learn about and use Git to make changes to projects.
• Review the basics of statistical testing and implement statistical hypothesis tests based on prepared datasets
• Mini Project #1: Data Scraping, Django Web App and Visualisation
• 2. Machine Learning Methods (Part 2)
• Model Evaluation Metrics
• Decision Trees & Random Forests.
• Principal Component Analysis and Functional Discrimination Analysis.
• Bayesian Modeling.
• Gradient Descent
• Naives Bayes
• MarketBasket
• Unsupervised Learning
• Neural Network
• Keras
• Big Data Introduction
• Cloud Computing Overview
• Hadoop
• Introduction to Deep Learning
• Mini Project #2 :Shopping Recommendation Engine.
• Data Science for Image Processing and Computer Vision
• Regression (Curve Fitting)
• CRISP-DM, Pickle, Pipeline