CFDS® Produkt Logo

Chartered Financial Data Scientist

Become a professional expert in Data Science and learn from the best



Programmstart: 6. Oktober 2021

Early Bird: 06. August 2021

Preis ab: 8.190 €
plus VAT

Data is the new oil

There is no way around it: big data just keeps getting bigger. The numbers are staggering and they are not slowing down. By 2020, there will be 40x more bytes of data than there are stars in the observable universe. But how can we effectively use this amount of data for our purposes? Especially the financial sector is thoroughly observing “Big Data” for benefits. This Program aims to introduce finance professionals into “Machine Learning” and its potentially endless opportunities which arise when insights scientifically extracted from big data are empowering financial market participants. 
You will significally enhance your abilities and career prospects in six distinct ways:
After passing the exam and conducting a three month project work, successful candidates are granted the title
CFDS® – Chartered Financial Data Scientist


a) Introduction to Financial Data Science

b) Exploring and Analysing Data

c) Data & Asset Management: does the asset create data or is independent data the asset?

d) The Science of Data

e) Understanding Asset Management from a financial data science perspective

f) Statistical Analysis of asset price variation

g) Python for Financial Data Science

h) Big Data Storage and Retrieval

i) Machine Learning

j) Deep Learning

k) Data Visualization and Communication of Outcomes


The CFDS programme consists of 3 in-class blocks of two days each. The first two blocks are workshops addressing the main topics of financial data science and will give an introduction to data analysis using Python. Each of these blocks will be followed by weeks of self study with providedreadings.

This knowledge in financial data science will be subject to a two hour multiple choice exam.
All students passing that exam will then start a three months project work, that means analysing a real or fictive data set using Python. The results of the project work will be presented in a two-day closing session.

Target group

Managers and employees from the following segments
  • Data Analytics
  • Data Management
  • Risk Management
  • Marketing/Sales
  • Trading
  • Compliance/Regulation
  • IT
  • interface product management/ project management and IT

Our Experts

Professor Andreas Hoepner

Professor Damian Borth

Play Video


Scroll to Top

Module 1

Introduction to Financial Data Science

  • What is Financial Data Science?
  • Building Block 1: Computer Science & Big Data
  • Building Block 2: Math & Stats
  • Building Block 3: Financial Markets & Asset Management
  • Financial Data Science in the context of previous industrial revolutions
  • FinTech vs. Financial Data Science
  • Financial Data Science vs. Financial Economics
  • The Data Value Chain
Exploring and Analysing Data

  • Scientific Research Design & Question formulation
  • Data and Decision Making
  • Understanding Cognitive Bias
  • Statistical Analysis: a refresher
  • Basic Distributions
  • Parametric and Non-Parametric Tests
  • Regression Analysis
  • Integrating data and domain knowledge
Data & Asset Management: does the asset create data or is independent data the asset?

  • Corporate self-reported data: accounting and/or disclosing
  • Corporate self-funded data: issuer paid ratings
  • Third party promotional data: sell-side research
  • Independent buy-side assessments of assets: ratings & news analytics
  • Macroeconomic data: accounting and/or disclosing by nation states
  • Environmental data: measuring physical constraints
  • Sociodemographic data: more than intergenerational shifts
  • Big Data & Sociolytics: real-time tracking of societies
  • Financial Market data: the most valuable information sponge of all
The Science of Data

  • Independence of data
  • Understanding variation
  • Levels of Measurement
  • The Data Generation Process & its characteristics
  • Upper Partial Moment
  • Lower Partial Moment
  • Tracking Error vs. Trailing Error
  • Machine Readability
  • Data Integrity & Documentation
Understanding Asset Management from a financial data science perspective

  • Data flows through asset management: Data-Analysis-Decision-Data
  • Market Segment Inefficiencies & Porter’s competitive forces
  • Outcome variables: Risk adjusted return (Alpha) vs. Return/Risk ratio
  • Control variables: Market variability (Beta) & Style Factors
  • Diversification: much more non-diversifiable, firm specific risk than expected
  • A data flow model Equity Investments
  • Fixed Income Investments: towards a laboratory infrastructure
  • Financial Data Science of Activism & Alternatives
  • Business Development empowered by Data Science
Statistical Analysis of asset price variation

  • Explaining variation with variables
  • Statistical power & explanatory power
  • OLS and alternative algorithms
  • Point estimates & confidence intervals
  • Cross-sectional vs. time series approaches
  • Single vs. multi step methods
  • Predictability vs. causality
  • Equity Investment explained by Carhart’s model
  • Fixed Income Investment explained by Elton & Gruber’s model

Module 2

Python for Financial Data Science
  • Introduction to Python
  • Basic Operations & Statistical plotting
  • Pandas
  • Quandl & Python
  • Basic statistical analysis with Python
Big Data Storage and Retrieval
  • Data at Scale: Concerns and Tradeoffs
  • Distributed Data Processing
  • Relational Databases
  • Graph Databases
  • Streaming Data Applications
  • Cloud Computing
Machine Learning
  • Machine Learning Pipeline Setup
  • Experimental Design
  • Feature Engineering & Dimensionality Reduction
  • Supervised Learning & Classification
  • Unsupervised Learning & Clustering
Deep Learning
  • Foundation of Deep Learning
  • Convolutional Neural Networks
  • Recurrent Neural Networks
  • Long-Short Term Memory Networks
  • Frameworks & Tools
Data Visualization and Communication of Outcomes
  • Design for Human Perception
  • Effective Visual Presentation of Data
  • Tools (Mathplotlib, D3, Javascript)

Information about Python

Python is an interpreted, object-oriented, high-level programming language with dynamic semantics. Its highlevel built in data structures, combined with dynamic typing and dynamic binding, make it very attractive for Rapid Application Development, as well as for use as a scripting or glue language to connect existing components together. Python‘s simple, easy to learn syntax emphasizes readability and therefore reduces the cost of program maintenance. Python supports modules and packages, which encourages program modularity and code reuse. The Python interpreter and the extensive standard library are available in source or binary form without charge for all major platforms, and can be freely distributed. (Source:


Programmstart: 6. Oktober 2021

Early Bird: 06. August 2021

Preis ab: 8.190 €
plus VAT