Go to main content
Back to Courses
MODULE 20

AI for Data Analysis, Data Engineering and AutoML

Use generative AI and AutoML to accelerate analysis, pipelines, features, and decision memos without losing control, quality, and ownership.

Editorial cover of the AI for Data Analysis, Data Engineering, and AutoML module
AI as an accelerator for data work - GinnyTech header image with an editorial cosmic visual
1
Intermediate 22 min

AI as a work accelerator on data

AI as a work accelerator on data at GinnyTech: choosing where to insert AI in the workflow and where to maintain human control with checks, ownership, and revisable outputs.

Prerequisites: 1

Go to lesson
Analytical prompting and question control - GinnyTech header image with an editorial cosmic visual
2
Intermediate 24 min

Analytical prompting and question control

Analytical prompting and question control on GinnyTech: writing prompts that produce reviewable work and not seductive but fragile answers with controls, ownership, and reviewable output.

Prerequisites: 1

Go to lesson
Assisted exploratory analysis - GinnyTech header image with an editorial cosmic visual
3
Intermediate 26 min

Assisted exploratory analysis

Assisted exploratory analysis on GinnyTech: decide which signals deserve further investigation and which are just descriptive noise with controls, ownership, and reviewable outputs.

Prerequisites: 1

Go to lesson
SQL, notebooks, and data storytelling with AI - GinnyTech header image with an editorial cosmic visual
4
Advanced 28 min

SQL, notebooks, and data storytelling with AI

SQL, notebooks and data storytelling with AI on GinnyTech: establishing when AI can propose code and when analytical code review with controls, ownership and reviewable outputs is needed.

Prerequisites: 1

Go to lesson
Data cleaning, data quality, and feature engineering - GinnyTech header image with an editorial cosmic visual
5
Advanced 30 min

Data cleaning, data quality, and feature engineering

Data cleaning, data quality, and feature engineering on GinnyTech: decide which transformations to automate and which require domain owners with controls, ownership, and reviewable outputs.

Prerequisites: 1

Go to lesson
AI for data engineering, mapping, and documentation - GinnyTech header image with an editorial cosmic visual
6
Advanced 27 min

AI for data engineering, mapping, and documentation

AI for data engineering, mapping, and documentation on GinnyTech: deciding what to document with AI and which technical validation blocks release with controls, ownership, and reviewable output.

Prerequisites: 1

Go to lesson
AutoML for classification, regression, and forecasting - GinnyTech header image with an editorial cosmic visual
7
Advanced 32 min

AutoML for classification, regression, and forecasting

AutoML for classification, regression and forecasting on GinnyTech: deciding when AutoML is enough, when custom modeling is needed and when the problem is not modelable with controllable, owned and reviewable outputs.

Prerequisites: 1

Go to lesson
Evaluation: leakage, drift, metrics, and limits - GinnyTech header image with an editorial cosmic visual
8
Advanced 31 min

Evaluation: leakage, drift, metrics, and limits

Evaluation: leakage, drift, metrics, and limits on GinnyTech: decide if a model can enter the process or must remain a controlled experiment with controls, ownership, and reviewable outputs.

Prerequisites: 1

Go to lesson
Case study: end-to-end AI-assisted workflow - GinnyTech header image with an editorial cosmic visual
9
Advanced 34 min

Case Study: AI-Assisted End-to-End Workflow

Case Study: AI-Assisted End-to-End Workflow on GinnyTech: designing an AI-assisted process governed by human review with controls, ownership, and revisable outputs.

Prerequisites: 1

Go to lesson
Cheat sheet: AI for data work - GinnyTech header image with an editorial cosmic visual
10
Intermediate 18 min

Cheat Sheet: AI for Data Work

Cheat Sheet: AI for Data Work on GinnyTech: quickly choosing the correct level of automation for each data task with controls, ownership, and revisable outputs.

Prerequisites: 1

Go to lesson

Module connections

Natural prerequisitePhilosophical Foundations of Data Analysis20 lessons

Give epistemological, causal, and critical depth to data work, linking evidence, models, risk, and responsibility.

Continue hereAgentic AI for Data Analysis, Data Engineering, and AutoML10 lessons

Design agentic workflows for analysis, SQL, pipelines, AutoML, and analytics operations with tools, state, guardrails, evaluation, and approval.

Same stage of the pathDirections in Analytics: Marketing, Product, Finance14 lessons

Connect technical modules to real roles, economic responsibilities, and professional specialization choices.

Previous moduleCourse Overview and Study Method for Data Work8 lessons

Transform the course from catalog to cognitive system, with study method, technical memory, and professional output plan.

Previous moduleData Collection & Tracking Systems8 lessons

Move from isolated tags and tools to reliable, governed, and observable measurement systems.

Previous moduleMetrics, KPI Trees, and Analytical Foundations6 lessons

Learn to read numbers as systems, with KPI trees, unit economics, correct baselines, and causal signal interpretation.