Data Science in Insurance (online certificate)

Why an online data science course with application in insurance?

Data Science is developing at a fast pace in the industry with a lot of use cases and applications being implemented around various topics

Training yourself to these new techniques is essential to be up-to-date and make the most of these new opportunities in your professional career.
A lot of e-learning training or MOOCS are available on-line on the (statistical) techniques themselves but few are oriented towards specific cases studies in insurance

The goals of this online data science certificate are double

Introduce you to the main data sciences techniques from a methodological point of view
But also let your practice data science on specific insurance use cases (including coding in R and Python) so that the knowledge you acquire isn’t just theoretical

Structure of the course

The Online Data Science Certificate is composed of 2 pillars

E-learning modules: presenting basis of machine learning process, advanced machine learning techniques and data culture applications.

The goals of the e-learning modules are the following

a. Creating improved awareness around data culture;
b. Sharing a common vision on data topics and main steps of a machine learning process;
c. Discovering practical applications of data science (in Insurance and Finance);
d. Being introduced to technical aspects in a pedagogical way.

Notebooks: web pages with pedagogical explanations and examples of code. Exercises and case studies are also attached to these notebooks for your practicing.

The goals of the e-learning modules are the following

a. Combining methodological lessons with practical use cases and exercises;
b. Go deeper on methodological aspects of data science;
c. Apply methodologies on real business cases.

A flexible approach

Not all of you have the same interests and we therefore offer you the opportunity to select among two complementary training tracks:

Technical track: designed to strengthen your skills with supervised and unsupervised machine learning techniques
Data collection and visualization track: designed to develop your skills in data collection (scraping, text mining, natural language processing) and data visualization (including dashboarding)

Content of the course

E-learning modules

The e-learning modules are divided in 3 blocks containing each 3 e-learning modules

1. Basis of a machine learning process

(mandatory for both tracks)

Data Preparation and Data Quality
Introduction to Machine Learning
Introduction to Data Visualization

2. Advanced machine learning techniques

(included in technical track)

Supervised machine learning part 1
Supervised machine learning part 2
Unsupervised machine learning

3. Data culture and applications

(included in data collection and visualization track)

Text Mining
Scraping
Advanced data visualization

Certification on the e-learning modules will be organized through quiz you will have to answer at the end of the e-learning modules

Notebooks

The notebooks are divided in 3 blocks containing each 2 notebooks

1. Introduction to data science software

(these 2 notebooks are optional for the participants already familiar with these software)

Introduction to R
Introduction to Python

2. Machine learning process