TID-030/ Data Mining Workshop (R or Python)

3-Day Intensive Course for Technical Professionals

3 Intense Days
7 Hours per Day (Split into two 3.5-hour sessions)

Learning Path Visual

Your hands-on journey from raw data to reliable, actionable patterns:

Day 1: Foundations of Data Mining: Concepts, Methods & Toolkits
Understand core algorithms, workflows, and use cases of data mining. Set up your environment with tools like Python, Jupyter, and Scikit-learn. Learn preprocessing, sampling, and exploratory analysis essentials.

Day 2: Patterns in Practice: Clustering, Classification & Anomaly Detection
Apply key mining techniques including k-means, decision trees, and DBSCAN. Build supervised and unsupervised models, detect outliers, and evaluate performance using metrics and visualizations.

Day 3: Real-World Deployment: Pipelines, Projects & Interpretability
Go beyond modeling to deploy full workflows. Connect mining outputs to dashboards, APIs, and business outcomes. Implement explainability, fairness checks, and scalable deployment patterns.

Course Overview

Raw data holds hidden patterns — this course teaches you how to find and apply them. Through hands-on projects and real datasets, you’ll master the full lifecycle of data mining: from preparation and modeling to deployment and interpretation.

You’ll move beyond theory to build real, usable mining workflows using Python, open-source libraries, and cloud-ready tools.

You’ll learn how to:

• Perform data preprocessing and transformation for mining

• Apply classification, clustering, and association rule mining

• Detect anomalies and outliers with statistical and ML methods

• Build interpretable and reliable models

• Connect mining results to dashboards, APIs, and decision processes

• Address ethics, bias, and data quality in production

Designed for engineers, data scientists, and developers, this course gives you the practical skills to mine value from complexity.

What’s Inside Each Day

Day 1: Foundations of Data Mining: Concepts, Methods & Toolkits

• Understand the data mining lifecycle (CRISP-DM, SEMMA)

• Learn preprocessing techniques: missing values, encoding, normalization

• Explore sampling and feature selection strategies

• Set up your toolkit: Python, Pandas, Scikit-learn, Seaborn

• Visualize data distributions, correlations, and outliers

• Apply basic unsupervised techniques (k-means preview, PCA)

Tools: Python, Pandas, Scikit-learn, Jupyter, Seaborn, NumPy
Focus: Preprocessing • Foundations • Tool Setup

Day 2: Patterns in Practice: Clustering, Classification & Anomaly Detection

• Train classification models: decision trees, k-NN, logistic regression

• Apply clustering: k-means, DBSCAN, hierarchical clustering

• Perform association rule mining (Apriori, FP-Growth)

• Detect anomalies using Isolation Forest, Z-score, and LOF

• Use confusion matrix, ROC-AUC, and silhouette score for evaluation

• Visualize decision boundaries, clusters, and anomaly regions

Tools: Scikit-learn, Matplotlib, Yellowbrick, MLxtend
Focus: Models • Metrics • Pattern Discovery

Day 3: Real-World Deployment: Pipelines, Projects & Interpretability

• Build reusable pipelines with sklearn.pipeline and MLflow

• Automate training and tuning workflows

• Connect models to dashboards and APIs (Flask, Streamlit)

• Apply SHAP and LIME for model explainability

• Conduct bias, fairness, and data drift checks

• Export, document, and present mining outputs for stakeholders

Tools: MLflow, Streamlit, Flask, SHAP, LIME, Scikit-learn
Focus: Deployment • Interpretability • Business Integration

Course Goals

By the end of this course, you’ll be able to:

• Design and execute full-scale data mining workflows

• Apply key classification, clustering, and detection methods

• Evaluate model performance with clarity and depth

• Package and deploy interpretable mining models

• Communicate insights effectively to technical and business audiences

• Address ethical and operational concerns around data use

Who Should Take This Course?

• Data scientists looking to deepen pattern detection and model deployment

• Engineers and developers who want to build and deploy mining models

• Analysts and researchers working with large structured datasets

• ML engineers seeking a mining-centric workflow foundation

• Academic professionals teaching or studying knowledge discovery

• CTOs and tech leads who want to integrate mining into products or platforms

Class Reference: TID/030

Form Updated on: 06/16/2025 (Version 1)
Last Modified on: 06/16/2025

Program Note

This course is updated continuously to reflect the latest methods and open-source frameworks in practical data mining and pattern discovery.

Links to Resources for presentations and summaries

Data Mining Definition

Data Mining: Definitions, 5 Free Tools, and Techniques

What is Data Mining? Definition of Data Mining, Data Mining Meaning

How Data Mining Works: A Guide | Tableau

TOP-10 DATA MINING CASE STUDIES | International Journal of Information Technology & Decision Making

Download Data Mining Case Studies I

What are some data mining case studies that use simple data mining algorithms?

The Age Of Analytics And The Importance Of Data Quality

The Importance of Data Collection: 10 Reasons Why Data Is So Important

Read “Going to Extremes: Meeting the Emerging Demand for Durable Polymer Matrix Composites” at NAP.edu

DATA MINING AND E-COMMERCE: METHODS, APPLICATIONS, AND CHALLENGES DATA MINING AND E-COMMERCE: METHODS, APPLICATIONS, AND CHALLEN

Data mining in ecommerce

The Benefits of Data Mining in CRM

Why Retailers Should Care About Data Mining : Intelligent Enterprise

Data Analysis with R (Coming Soon!) – BDU

Big Data Use Cases – Big Data Analytics News

What Is Data Science, and What Does a Data Scientist Do?

What is association rules (in data mining)? – Definition from WhatIs.com

18 Big Data tools you need to know!! – Data Science Central

Unit Testing in R – DZone Big Data

How Pokemon Go needed a Kubernetes powered Java cloud

A Pocket Guide to Data Science

Data Science and the Imposter Syndrome

Scalable Software and Big Data Architecture – Software Architectural Patterns and Design Patterns

The Ultimate Guide to Basic Data Cleaning

All the Best Big Data Tools and How to Use Them – Import.io

Navigating the Complexity of Big Data Transformation

4 Steps to Moving Big Data to the Cloud

Introductory Data Concepts: Fantastic Video Tutorials from Ronald van Loon

Big Data Storymap Revisited | Grroups

5 Steps to Building a Big Data Business Strategy – Data Science Central

Key tools of Big Data for Transformation: Review & Case Study – Data Science Central

A Beginner’s Guide to Data Engineering – Part II

Brief pédagogique en français

TID-030/ Data Mining Workshop (R or Python) est présenté ici en version synthétique française afin que les équipes pédagogiques puissent évaluer rapidement l'intérêt du module.

Le module s'inscrit dans la famille Analytics et intelligence artificielle. Il peut être adapté au calendrier de l'école, au niveau Tous niveaux, au volume horaire 3 jours et aux modalités d'évaluation prévues.

Objectif d'intervention

Ce module vise à relier les outils data, IA et automatisation à des usages professionnels concrets.

Livrables et activités possibles

• cas d'usage, prompts, scénarios d'automatisation ou analyses data
• évaluation critique des résultats, limites et risques
• communication claire des choix techniques et business

Adaptation école

LC peut ajuster le déroulé, la langue d'enseignement, les supports, les exercices et les critères d'évaluation selon la promotion, le diplôme, le niveau d'autonomie attendu et les contraintes de planning.

Pour une version détaillée du syllabus en français, LC confirme le programme final après cadrage du niveau, des heures, du calendrier et des livrables attendus.