Creating and Validating Synthetic Financial Data in Python - Part 1

Part 1 of a 2 part video series showing you how to generate, validate, and assess synthetic financial data using Python. You’ll learn how to test for analytical fidelity, apply privacy safeguards, and ultimately identify which model is the best choice for your dataset.

Tutorial Link: https://datasense.to/2025/09/13/synthetic-financial-data-python-guide/
Gitlab Repo: https://gitlab.com/datasense-co/synthetic-financial-data

Timestamps:
0:45 - Reviewing the Data
2:30 - Data Cleaning and Transformation
4:15 - Exploratory Data Analysis (EDA)
5:20 - Prerequisites
5:40 - Discussing Domain Constraints and Gaussian Copula
8:30 - Metadata and Domain Constraints
13:00 - Generating the Synthetic Dataset with Gaussian Copula and Domain Constraints
15:00 - Quick Checks (EDA) of the Synthetic Data
19:25 - Analytical Fidelity Testing (Gaussian Copula -- Synthetic Dataset)
24:25 - Privacy Preservation
29:50 - Model Sweep for Initial Model Selection
38:10 - Analytical Fidelity Testing (CTGAN -- Synthetic Dataset)
Contact Us: https://datasense.to/#contact
#syntheticdata #syntheticfinancialdata #financialservices #datasense #dataprivacy #differentialprivacy #kanonymity #gaussiancopula #pythontutorial #sdvpython #datascience #financialriskmanagement #datavalidation #datasynthesis #regulators #fintech #economics #supervisorytechnology #regtech #dataanalysis #privacypreservingdata

Видео Creating and Validating Synthetic Financial Data in Python - Part 1 канала Data Sense