In the ETL stage I carried out:
- Exclusion of null values, duplicates, and outliers;
- Normalization of predictor variables;
- Balancing the target variable;
- Correlation analysis;
I leveraged this data to compare 2 techniques widely used in data science:
- Machine Learning with Random Forest;
- Deep Learning with Neural Networking;
In this case, the accuracy of the Random Forest model was more efficient.
