#acl BusinessIntelligenceAndAnalytics2/ReadWriteGroup:read,write,admin,delete,revert All:read

== Business Intelligence And Analytics (Data Mining) ==

<<TableOfContents(3,3)>>
=== Course Information ===

'''Professor''': Pasquale Rullo. 

'''Office hours''': by appointment.

'''Assistant professor''': Ettore Ritacco

'''Office hours''': by appointment.

'''[[http://www.unical.it/portale/portaltemplates/view/view_scheda_insegnamento.cfm?44772|Course Details]]'''


<<BR>>
===  News ===
* '''7-th June'''
 * Project teams are building up: please, if you are not already registered, let me know which is your group, if you want to create a new group or if you are willing to join a group 

* '''12-th June - Exam deadlines'''
 * The CRISP-DM documentation deadlines are: 27-th of June (first session), 19-th of July (second session)
 * Project presentation and oral proof will take place on: 2-nd of July (first session), 24-th of July (second session)
 * After these dates, we must agree on a new project
 * The project evaluation expires on March 2020 or if you are willing to do a new project

* '''27-th June - Exam deadline change'''
 * The first session date of the exam (project presentation and oral proof) was changed to the 3rd of July, 14:30 at the prof. Rullo's office

* '''3-rd July - Exam deadline change'''
 * The second session date of the exam (project presentation and oral proof) was changed to the 25th of July, 14:30 at the prof. Rullo's office


<<BR>>
=== Teaching material ===

==== Slides ====
 

==== Lab Activities ====
* Lesson 1  [ [[attachment:Lab-01 Introduction.pdf]] ]
  * Introduction to the Data Mining
  * DIKW model
  * CRISP-DM Methodology

* Lesson 2 [ [[attachment:Lab-02 Data Understanding.pdf]] ]
 * Data Exploratory Analysis
 * Data Visualization

* Lesson 3 [ [[attachment:Lab-03 Data Preparation.pdf]] ]
 * Data Manipulation
 * Data Transformation
 * Data Cleaning

* Lesson 4 [ [[attachment:Lab-04 Estimation Theory.pdf]] ]
 * Probability theory overview
 * Probability distributions
 * Estimation and optimization

* Lesson 5 [ [[attachment:Lab-05 Case study - Drug.pdf]] ], [ [[attachment:drug.csv]] ], [ [[attachment:CaseStudy1_Drug.ipynb]] ], [ [[attachment:CaseStudy1_Drug.py]] ], [ [[attachment:plot_utility.py]] ]
 * Software: Python (SciPy, NumPy, Pandas, Matplotlib, SKLearn), PyCharm, Jupyter Notebook
 * A case study for CRISP-DM Methodology - Drug

* Lesson 6 [ [[attachment:Lab-06 Case study - Churn Analysis.pdf]] ], [ [[attachment:churn.cvs]] ], [ [[attachment:CaseStudy2_Mobile.ipynb]] ]
 * A case study about the attrition problem of a mobile company
 * Note: [ [[attachment:plot_utility.py]] ] has been updated

* Lesson 7 [ [[attachment:segment.csv]] ], [ [[attachment:Lab-07 Case study - Image Segmentation.pdf]] ]
 * Guided exercise in class about image classification

* Lesson 8 [ [[attachment:Lab-08 Evaluation.pdf]] ]
 * Model evaluation

* Lesson 9 [ [[attachment:Lab-09 Project.pdf]] ]
 * Project specifications
 * Roc curve
 * Note: [ [[attachment:plot_utility.py]] ] and [ [[attachment:CaseStudy2_Mobile.ipynb]] ] have been updated

* Lesson 10
 * Project
 *  Note [ [[attachment:CaseStudy2_Mobile.ipynb]] ] has been updated
 * Recommender Systems [[https://towardsdatascience.com/prototyping-a-recommender-system-step-by-step-part-1-knn-item-based-collaborative-filtering-637969614ea|KNN approach]],  [[https://towardsdatascience.com/prototyping-a-recommender-system-step-by-step-part-2-alternating-least-square-als-matrix-4a76c58714a1|Matrix factorization approach]]