WeAreDevelopers LIVE • Sep 22, 2021

Data Fabric in Action - How to enhance a Stock Trading App with ML and Data Virtualization

Andreas Christian

Tired of complex ETL pipelines stalling your ML projects? Discover how data virtualization within a data fabric architecture predicts customer churn without duplicating a single record.

Pause
Mute Enter Fullscreen
#1 about 3 min

Defining data fabric for modern data integration

Industry definitions shape data fabric as an emerging architecture for orchestrating disparate data sources across various platforms.

#2 about 3 min

Obstacles in developing machine learning applications

Key hurdles include discovering available enterprise data, understanding content semantics, ensuring quality, and addressing model degradation over time.

#3 about 5 min

Connecting data and modern AI with data fabric architecture

The underlying architecture relies on an organized framework to centralize data governance, visualization, and lifecycle analytics.

#4 about 4 min

Segregating platform roles in the machine learning lifecycle

Distinct organizational structures separate raw data engineering and catalog stewardship from specialized operational model development workflows.

#5 about 2 min

Leveraging Red Hat OpenShift for underlying container orchestration

Kubernetes-backed compute clusters dynamically scale host infrastructure resources and manage automated containerized database deployments.

#6 about 6 min

Preventing customer churn with predictive machine learning models

A reference stock trading platform dashboard evaluates retention risk indicators against embedded customer profiles to surface contextual capabilities.

#7 about 6 min

Exploring internal services and the Watson data catalog

A centralized interface exposes data properties, auto-matches context schemas, and records peer application reviews for distributed operational tables.

#8 about 6 min

Selecting and deploying models with automated AI validation

Algorithmic profiling tools compare predictive hyperparameter limits to automatically generate optimum Python notebook scripts or production-ready REST endpoints.

#9 about 3 min

Integrating cloud databases directly into Python application code

Developers natively query logically linked remote tables using uniform SQL connection structures instead of maintaining multiple runtime data adapters.

#10 about 7 min

Mapping external MongoDB collections into queryable visual tables

Complex architectures like nested JSON documents flatten safely into scalable table views mapping directly to downstream visual join conditions.

#11 about 2 min

Sharing refined analytical data assets with collaborative teams

Role-based permissions allow technical operators to persist transformed information layouts directly back into organizational service catalogs.

#12 about 2 min

Dataset sizing thresholds for automated machine learning utilities

The accuracy of automated prediction frameworks directly correlates with adequate statistical density across representative training sets rather than explicit capacity boundaries.

#13 about 3 min

Exposing generated model endpoints to native mobile platforms

Auto-generated REST structures securely process asynchronous prediction requests from decoupled client networks like mobile or frontend interfaces.

Matching moments

3:38 min

Architecting a unified data and machine learning workbench

Kapil Gupta Kapil Gupta · World Congress 2025

4:18 min

Exploring the big data and machine learning portfolio

Qiyang Duan · LIVE

1:46 min

Traditional data architecture before Microsoft Fabric

Dr. Alexander Wachtel Dr. Alexander Wachtel +1 · World Congress 2025

3:03 min

Career evolution in data engineering and AI platforms

Maria Apazoglou · Coffee With Developers

2:47 min

Bringing machine learning into application DevOps

Ignacio Riesgo Ignacio Riesgo +1 · World Congress 2024

1:10 min

Introduction to Microsoft Fabric and data agents

Dr. Alexander Wachtel Dr. Alexander Wachtel +1 · World Congress 2025