Página substituída por '* Link: ** http://intranet/wiki/index.php/Telco_Analytics'
 
(173 revisões intermediárias por 6 usuários não estão sendo mostradas)
Linha 1: Linha 1:
= Step I - Project Presentation  =
* Link:
 
** http://intranet/wiki/index.php/Telco_Analytics
<br>
 
 
Telco Analytics
 
<br>
 
== Purpose  ==
 
Investment optimization and generation of new revenues to support Digital Transformation based on Data
 
<br>
 
== Project Keys  ==
 
<br>
 
  1- Semantic Data Integration
  2- Analytics - Correlação de Dados
  3- Advanced Anomaly Detection
  4- Embedded IoT Analytics to the Edge
  5- Machine Learning
  6- Open Data - For Peoples (PL 53/2018)
  7- Decision Management
  8- Immersive User Experience
  9- Geospatial And Location Intelligence
10- Digital Twins
 
<br>
 
== Presentation  ==
 
<br>
 
Link to the presentation [https://docs.google.com/presentation/d/1MU4oSvaPymDCDg-cJnSJU7Fuh_kVGYKxWfm_zBhrjFo/edit?ts=5bd1ce1a#slide=id.g465dc625f9_1_153]
<br>
 
<br>
 
= Step 2 - Studies  =
 
<br>
 
== Usable Books  ==
Open this Drive Link to find 3 books [https://drive.google.com/drive/folders/1EzfmV4nbfNedVVHPzLsXsEFqtvOVoLi9?usp=sharing] :
    * Data Mining for the masses 2nd edition
    * Python for data Analysis
    * Data Mining concepts and techniques
<br>
 
==Methodology==
<br>
 
CRISP-DM stands for cross-industry process for data mining.
 
The CRISP-DM methodology provides a structured approach to planning a data mining project.
Phase of the process:
      1- Business understanding
      2- Data understanding
      3- Data preparation
      4- Modeling
      5- Evaluation
      6- Deployment
<br>
 
= Step 3 - Business Case Example<br>  =
 
<br>
 
== Benefits to anyone who offers this solution  ==
 
    Offer a machine learning Template for data mining in order to:
      * Improve the broadband customer experience
      * Remote data management and processing with IoT optimizing investments
      * Network scanning for monitoring, testing and predicting events.
<br>
 
<br>
 
== Benefits to the user  ==
 
    Make Intelligent predictions more faster.
 
<br><br>
 
== Business Models  ==
 
    We can use some Classification models Like:
        - Random Forest
        - Decision Tree
        - XGBoost
<br>
 
= Step 4 - Business-oriented prototype  =
 
<br>
 
== Scoop  ==
 
<br>
 
  Join Statistics and programming to better understand huge Data and make decisions in order to improve the company.
<br>
 
== Technical details  ==
 
<br>
 
Tools for Studing Steps:
  * Knime
  * Anaconda / Jupyter notebook : Python users
  * R studio : R users
 
Tools for Collaborative Work:
  * Data Lake / DW : data extraction
  * Google Data Studio : Data visualization
  * Google Colab: Python users
  * Rstudio Cloud : R users
 
<br>
 
<br>
 
<br>
 
<br>
 
= Cronograma Macro  =
 
<br>
 
= Histórico  =
 
<br>
 
<br>
 
= Pesquisadores  =
 
*<br>

Edição atual tal como às 18h28min de 23 de janeiro de 2021