Certification Course
The AI-Data Program
The AI-Data Program
The AI-Data Program
Exclusive track on AI in data analytics. Learn Prompt Engineering, AI-driven analysis, and predictive insights for next-generation decision-making.
AI-DATA PROGRAM
₦100k
FEATURES:
Introduction to Prompt Engineering
AI for Data Analysis
AI for Predictive Analysis
AI-DATA PROGRAM
₦100k
FEATURES:
Introduction to Prompt Engineering
AI for Data Analysis
AI for Predictive Analysis
AI-DATA PROGRAM
₦100k
FEATURES:
Introduction to Prompt Engineering
AI for Data Analysis
AI for Predictive Analysis
Course Description
Course Description
An exclusive program that explores the intersection of data analytics and artificial intelligence. Participants will gain hands-on experience with Prompt Engineering, AI for Data Analysis, and AI for Predictive Analysis, preparing them to leverage AI-driven tools for next-generation insights and decision-making.
Learning Schema
Week 1: Introduction to Prompt Engineering
Week 1: Introduction to Prompt Engineering
Week 1: Introduction to Prompt Engineering
Session 1
- Introduction to Generative AI and ChatGPT
- What is Prompt Engineering?
- Types of prompts: instructional, comparative, role-based
- Prompt crafting principles: clarity, constraints, context
Session 1
- Introduction to Generative AI and ChatGPT
- What is Prompt Engineering?
- Types of prompts: instructional, comparative, role-based
- Prompt crafting principles: clarity, constraints, context
Session 1
- Introduction to Generative AI and ChatGPT
- What is Prompt Engineering?
- Types of prompts: instructional, comparative, role-based
- Prompt crafting principles: clarity, constraints, context
Session 2
- Use cases in data tasks: exploratory analysis, cleaning, summarisation
- Role-play prompting: Analyst, Engineer, Statistician
- Exercise: Crafting prompts for data summarisation and cleaning
- Assignment: Draft 5 practical prompts for data work
Session 2
- Use cases in data tasks: exploratory analysis, cleaning, summarisation
- Role-play prompting: Analyst, Engineer, Statistician
- Exercise: Crafting prompts for data summarisation and cleaning
- Assignment: Draft 5 practical prompts for data work
Session 2
- Use cases in data tasks: exploratory analysis, cleaning, summarisation
- Role-play prompting: Analyst, Engineer, Statistician
- Exercise: Crafting prompts for data summarisation and cleaning
- Assignment: Draft 5 practical prompts for data work
Week 2: Prompt Engineering for Data Analysis
Week 2: Prompt Engineering for Data Analysis
Week 2: Prompt Engineering for Data Analysis
Session 1
- Structuring prompts for reproducible code
- Naming conventions for datasets, variables, and DataFrames
- Generating modular Python scripts using prompts
- AI-enhanced exploratory data analysis prompts
Session 1
- Structuring prompts for reproducible code
- Naming conventions for datasets, variables, and DataFrames
- Generating modular Python scripts using prompts
- AI-enhanced exploratory data analysis prompts
Session 1
- Structuring prompts for reproducible code
- Naming conventions for datasets, variables, and DataFrames
- Generating modular Python scripts using prompts
- AI-enhanced exploratory data analysis prompts
Session 2
- Hands-on: Prompt-to-code for EDA (using student dataset or sales data)
- Copying and running AI-generated code in Jupyter Notebooks
- Debugging AI-generated code
- Case Study: Analyse dataset using only AI-generated code
Session 2
- Hands-on: Prompt-to-code for EDA (using student dataset or sales data)
- Copying and running AI-generated code in Jupyter Notebooks
- Debugging AI-generated code
- Case Study: Analyse dataset using only AI-generated code
Session 2
- Hands-on: Prompt-to-code for EDA (using student dataset or sales data)
- Copying and running AI-generated code in Jupyter Notebooks
- Debugging AI-generated code
- Case Study: Analyse dataset using only AI-generated code
Week 3: AI for Supervised Learning (Part 1)
Week 3: AI for Supervised Learning (Part 1)
Week 3: AI for Supervised Learning (Part 1)
Session 1
- Introduction to Predictive Modelling & Supervised Learning
- Overview of classification vs regression problems
- Prompting for classification models (e.g. Logistic Regression, Decision Trees)
- Splitting data and model training using AI
Session 1
- Introduction to Predictive Modelling & Supervised Learning
- Overview of classification vs regression problems
- Prompting for classification models (e.g. Logistic Regression, Decision Trees)
- Splitting data and model training using AI
Session 1
- Introduction to Predictive Modelling & Supervised Learning
- Overview of classification vs regression problems
- Prompting for classification models (e.g. Logistic Regression, Decision Trees)
- Splitting data and model training using AI
Session 2
- Prompting for model evaluation: Accuracy, Precision, Recall, F1-score
- Hands-on: Use AI to build and evaluate a classification model
- Interpreting confusion matrix & classification report
- Assignment: Prompt AI to build a classification model for new dataset
Session 2
- Prompting for model evaluation: Accuracy, Precision, Recall, F1-score
- Hands-on: Use AI to build and evaluate a classification model
- Interpreting confusion matrix & classification report
- Assignment: Prompt AI to build a classification model for new dataset
Session 2
- Prompting for model evaluation: Accuracy, Precision, Recall, F1-score
- Hands-on: Use AI to build and evaluate a classification model
- Interpreting confusion matrix & classification report
- Assignment: Prompt AI to build a classification model for new dataset
Week 4: AI for Supervised Learning (Part 2)
Week 4: AI for Supervised Learning (Part 2)
Week 4: AI for Supervised Learning (Part 2)
Session 1
- Prompting for regression models: Linear Regression, Random Forest Regressor
- Evaluation metrics: RMSE, MAE, R²
- Feature selection and engineering prompts
Session 1
- Prompting for regression models: Linear Regression, Random Forest Regressor
- Evaluation metrics: RMSE, MAE, R²
- Feature selection and engineering prompts
Session 1
- Prompting for regression models: Linear Regression, Random Forest Regressor
- Evaluation metrics: RMSE, MAE, R²
- Feature selection and engineering prompts
Session 2
- Hands-on: End-to-end regression model using AI prompts
- Interpreting residual plots and evaluation results
- Case Study: Forecasting revenue or fuel consumption
Session 2
- Hands-on: End-to-end regression model using AI prompts
- Interpreting residual plots and evaluation results
- Case Study: Forecasting revenue or fuel consumption
Session 2
- Hands-on: End-to-end regression model using AI prompts
- Interpreting residual plots and evaluation results
- Case Study: Forecasting revenue or fuel consumption
Week 5: AI for Unsupervised Learning
Week 5: AI for Unsupervised Learning
Week 5: AI for Unsupervised Learning
Session 1
- Introduction to clustering and dimensionality reduction
- Prompting for k-means clustering and visualising clusters
- Using AI for PCA and t-SNE explanations
Session 1
- Introduction to clustering and dimensionality reduction
- Prompting for k-means clustering and visualising clusters
- Using AI for PCA and t-SNE explanations
Session 1
- Introduction to clustering and dimensionality reduction
- Prompting for k-means clustering and visualising clusters
- Using AI for PCA and t-SNE explanations
Session 2
- Hands-on: Segment customer or product data using clustering
- Interpreting silhouette score and visual plots
- Case Study: Customer segmentation for a retail business
- Assignment: Build unsupervised model via AI prompt and interpret output
Session 2
- Hands-on: Segment customer or product data using clustering
- Interpreting silhouette score and visual plots
- Case Study: Customer segmentation for a retail business
- Assignment: Build unsupervised model via AI prompt and interpret output
Session 2
- Hands-on: Segment customer or product data using clustering
- Interpreting silhouette score and visual plots
- Case Study: Customer segmentation for a retail business
- Assignment: Build unsupervised model via AI prompt and interpret output
Week 6: Final Project & Deployment Guidance
Week 6: Final Project & Deployment Guidance
Week 6: Final Project & Deployment Guidance
Session 1
- Final Project Introduction
- Students pick either a classification, regression, or clustering task
- Guidance on structuring prompts for a full workflow
- Summary of evaluation techniques and prompt hygiene
Session 1
- Final Project Introduction
- Students pick either a classification, regression, or clustering task
- Guidance on structuring prompts for a full workflow
- Summary of evaluation techniques and prompt hygiene
Session 1
- Final Project Introduction
- Students pick either a classification, regression, or clustering task
- Guidance on structuring prompts for a full workflow
- Summary of evaluation techniques and prompt hygiene
Session 2
- Project Presentation: Students present prompt-to-code workflow
- Feedback & Improvements
- Intro to deploying Python models using AI-generated Flask code (Pre-recorded)
Session 2
- Project Presentation: Students present prompt-to-code workflow
- Feedback & Improvements
- Intro to deploying Python models using AI-generated Flask code (Pre-recorded)
Session 2
- Project Presentation: Students present prompt-to-code workflow
- Feedback & Improvements
- Intro to deploying Python models using AI-generated Flask code (Pre-recorded)
© 2025. AnalystXcelerate, NG. All rights reserved.
© 2025. AnalystXcelerate, NG. All rights reserved.
© 2024. AnalystXcelerate, NG.
All rights reserved.