Applied Data Science

Audience

Data analysts, BI analysts, Data scientists, Insight analysts, Reporting analysts, the applied data science module can also be tailored for business leaders who want understanding how data can help business decisions.

Prerequisites

R or Python programming preferred, at least some data handling and analysis experience, basic understanding of statistics.

Duration

4 days.

Course Objectives

Introduction to data science (1 days)
This module will introduce the field of data science and its importance in the industry. It will also cover the basic concepts of data science, such as data types, visualisation, data project lifecycle.

Machine learning (2 days)
This module will cover the basics of machine learning, including different types of machine learning algorithms, supervised and unsupervised learning, model evaluation, introduction to deep learning.

Applied data science (1 day)
This module will cover the application of data science to real-world problems, including case studies and ethics.

Course Content

Introduction to Data Science - Day 1

Overview of Data Science

• Data science applications
• Data scientist skillset
• Data sources
• Common challenges

Data Science Project Management

• Basics of project management
• Requirements gathering
• Planning
• Execution lifecycle
• Monitoring

Uncovering Insight from Data

• Data cleaning & transformation
• Detecting trends & uncovering insight
• Getting creative: example led
• When it all goes wrong..

Data Visualisation

• Data types and visual design principles
• Tips and best practices for effective visualisations

Machine Learning: Algorithms - Days 2 & 3

Introduction to ML

• Model lifecycle
• Supervised v. unsupervised learning
• Classification v. regression
• Cheat sheet of pros & cons of specific models
• Pros & cons of 'black box' approach

Supervised Learning Algorithms

• Decision trees & random forest
• Logistic regression
• K-nearest neighbours
• Introduction to other supervised learning models

Unsupervised Learning Algorithms

• K-Means clustering
• Principal component analysis
• Introduction to other unsupervised learning models

Model Evaluation: Random Forest Example

• Model evaluation metrics
• Model selection, underfitting & overfitting
• Cross validation and hyperparameter tuning
• Interpretation and feature importance
• Boosting, bagging and ensembles
• Model monitoring

Introduction to Deep Learning

• Introduction to deep learning
• Architecture of neural network
• Types of neural networks
• Applications
• Deep learning v. machine learning - do or don't?