Technologies: SAS Enterprise Miner, Excel, Machine Learning, Python

Description: This project seeks to demonstrate how it is possible to evaluate, locate and predict possible problems in requests for benefits, considering the issues and studies that lead to these requests and how it is possible to reduce such requests and reduce damage to the public coffers.
Understanding these reasons is to build a predictive, informative model, risks, and implementation.
Applying data mining and data analysis techniques. Creating and using models such as Decision Tree, Logistic Regression and Neural Network, analyzing and comparing with reports and graphs made and extracted from SAS Enterprise Miner.

Chosen dataset: Using datasets provided on government and partner websites.
The dataset and this project are within the laws of the General Data Protection Regulation (GDPR).

Workflow of the process and stages:

• Business and Data Understanding
• Data Preparation and exploration
• Modeling
• Summary of metrics and comparison
• Evaluation and results explanation
• Evaluation of possible benefits ans commercial risks

Where in each of these steps was addressed more deeply in subtopics.

Models used in SAS Enterprise Miner:

• Decision Tree(DT)
• Logistic Regression(LR)
• Neural Network(NN)

Documentation: Complete documentation divided into chapters describing all stages of the process, research, and results.