- 👋 Introduction
- 📝 Course Criteria
- 🗺️ Course progress
- 📄 Midterms, Exams and Projects
- 📚 Resources and Further Reading
Welcome to the Data Mining and Knowledge Recovery Course!
This course provides a comprehensive introduction to the principles, algorithms, and applications of data mining, equipping you with the tools to transform raw data into actionable knowledge. From preprocessing, analyzing and model development for classification or regression to clustering and association rule mining, you’ll learn how to tackle real-world challenges in fields like healthcare, finance, marketing, and beyond.
1. Fundamentals of Data Mining
- The knowledge discovery process (KDD)
- Data types, quality, and preprocessing (cleaning, transformation)
- Exploratory Data Analysis (EDA) for knowledge extraction
2. Core Techniques
- Classification/Regression (kNN, Decision Trees, SVM, Naïve Bayes)
- Clustering (k-Means, Hierarchical, DBSCAN)
- Association Rule Mining
- Anomaly Detection
3. Advanced Methods
- Dimensionality reduction (PCA, t-SNE)
- Text mining and NLP basics
- Deep learning for data mining (introductory)
- Practical Applications
- Case studies in healthcare, e-commerce, and social networks
- Ethical considerations and pitfalls (bias, privacy)
By the end of this course, you’ll have a solid knowledge in Data Mining and its techniques, empowering you to make data-driven decisions and insights. If you are looking to enhance your skills in Data Mining, this course has something for everyone.
| Criteria | Percentage |
|---|---|
| Attendance | 10% |
| Participation & quiz | 30% |
| Midterm Exam | 30% |
| Final Project & Presentation / Practical labs | 30% |
You are free you use your favorite programming language
Python or
.
Visit the course webpage: CSCI 866 001: Data Mining.
In this section, you will find all the information related to the midterms, exams and projects including instructions, starting dates and the deadlines.
- A possible
midtermdate:...Loading.
-
Deadline for the report:
...Loading. -
Where to submit:
Canvas -
Your report should be in (your favorite) PDF format and include the following criteria:
- Objective: Clearly define the problem (e.g., classification, clustering, pattern mining).
- Dataset: Describe the source, size, and features (e.g., UCI Repository, Kaggle).
- Relevance: Why is this problem interesting from a data mining perspective?
- Data Cleaning: Handling missing values, duplicates, noise (e.g., binning, interpolation).
- Feature Transformation: Normalization, discretization, encoding (e.g., one-hot).
- Feature Selection: Techniques used (e.g., PCA, correlation analysis, wrapper methods).
- Descriptive Statistics: Mean, variance, distributions (include tables/visualizations).
- Visualizations: Heatmaps, histograms, scatter plots for feature relationships.
- Insights: Uncover preliminary patterns (e.g., class imbalance, outliers).
(Split into subsections based on your project’s focus)
A. Model Development
- Algorithms: Justify choices (e.g., Decision Trees for interpretability, SVM for high dimensions).
- Training/Testing: Choice, split strategy (e.g., 80/20, cross-validation).
- Hyperparameter Tuning: Methods used (e.g., grid search, random search).
B. Alternative Approaches
- Compare at least 2 techniques (e.g., clustering with k-means vs. DBSCAN).
- Mention ensemble methods (e.g., Random Forest, Boosting) if applicable.
- Metrics: Use domain-appropriate measures:
- Classification: Accuracy, Precision, Recall, ROC-AUC.
- Clustering: Silhouette Score, Dunn Index.
- Association Rules: Support, Confidence, Lift.
- Visual Evidence: Confusion matrices, elbow plots, dendrograms.
- Benchmarking: Compare against baselines (e.g., naive Bayes as a simple model).
- Limitations: Data quality, computational constraints, assumptions.
- Business/Research Implications: How do results translate to real-world solutions?
- Summarize key findings (e.g., “k=3 clusters best segmented our customer data”).
- Suggest improvements (e.g., deeper feature engineering, alternative algorithms).
- Cite datasets, libraries (e.g., scikit-learn, Weka), and papers (e.g., on novel algorithms).
-
Code Snippets: Critical steps (e.g., entropy calculation for decision trees).
-
Extended Results: Additional graphs/tables omitted from the main report.
-
Presentation:
- A possible dates:
...Loading.
- A possible dates:
Here, you will find additional resources, including books, research papers, and online courses, to further your understanding of Data Mining.
-
Data Mining: Concepts and Techniques – Jiawei Han, Micheline Kamber, Jian Pei
-
Data Mining and Analysis: Fundamental Concepts and Algorithms – Mohammed J. Zaki & Wagner Meira Jr.
-
Mining of Massive Datasets” – Jure Leskovec, Anand Rajaraman, Jeff Ullman
-
The Elements of Statistical Learning” – Trevor Hastie, Robert Tibshirani, Jerome Friedman
-
Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow – Aurélien Géron

Rmarkdown/Quarto