CFDS® Produkt Logo

Chartered Financial Data Scientist

Become a professional expert in Data Science


Start date


Start: 24. November 2022
Early Bird: 30. September 2022

Price: from 5.900 € plus VAT

Data is the new oil

Creating value in financial services depends critically on the ability to draw reliable inferences from large quantities of heterogeneous data. Against this background, the Chartered Financial Data Science programme will provide you with essential tools and techniques for processing, analysing, and visualizing such information.  You will learn to analyse time series and cross-sectional data in order to make forecasts, assess risks, perform simulations, and assign probabilities to possible events. Each of the relevant methods and modelling strategies is explained by one or more specific examples using real-world financial data. A comprehensive introduction to Python, one of the most popular programming languages for data science, will enable you to implement, extend and vary the techniques learned in accordance with the individual aims and needs.

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


Financial Statistik
Maschine Learning & AI

1. Introduction: Data Science

2. Exploratory Data Analysis

3. Multiple Linear Regression and Related Topics

4. Models with Binary Dependent Variables

5. Time-Varying Volatility and the Likelihood of Extreme Loss Events

6. Smoothed Bootstrap

7. Statistics with Python

1. Introduction to Machine Learning

2. Introduction to Python and ML Libraries

3. Supervised Learning and Logistic Regression

4. Unsupervised Learning and K-Means

5. Neural Networks and Deep Learning

6. Convolutional Neural Networks

7. Recurrent Neural Networks and Long Short Term Memory

8. Natural Language Processing

9. Reinforcement Learning

10. Data Centric AI

11. AI Canvas

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 program consists of 2 in-class blocks. One Kick off at the beginning and a presentation at the end. In between you will have 15 live webinars as well as video material for your self-study. (Study time: approx. 145 hours).

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


Sikandar Siddiqui

Sikandar Siddiqui is an economist and financial analyst specializing in asset valuation, risk management, and applied econometrics. Having gathered more than twenty years of professional experience in the fields of finance and management consulting, he currently serves as Head of Quantitative Methods at Deloitte Audit Analytics Germany.
Sikandar has authored or co-authored several articles on economic, statistical and financial issues. He holds a doctoral degree in economics from the University of Konstanz and has qualified as a CFA Charterholder.

Natalie Packham

Natalie Packham is Professor of Mathematics and Statistics at Berlin School of Economics and Law and Principal Researcher within the International Research Training Group “High Dimensional Nonstationary Time Series” (IRTG 1792) at Humboldt University Berlin. Natalie has several years of industry experience as a front office software engineer at an investment bank, and is frequently involved in industry-related research and consulting projects. Her research expertise includes Mathematical Finance, Financial Risk Management and Computational Finance, and her academic work has been published in Mathematical Finance, Finance & Stochastics, Quantitative Finance, Journal of Applied Probability and many other academic journals. She is associate editor of “Methodology and Computing in Applied Probability” and “Digital Finance” and co-chair of the GARP Research Fellowship Advisory Board. Natalie holds an M.Sc. in Computer Science from the University of Bonn, a Master’s degree in Banking & Finance from Frankfurt School, and a Ph.D. in Quantitative Finance from Frankfurt School.


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:

Start date


Start: 24. November 2022
Early Bird: 30. September 2022

Price: from 5.900 € plus VAT