1. Concepts & Definitions
1.1. Regression versus Classification
1.3. Parameter versus Hyperparameter
1.4. Training, Validation, and Test
2. Problem & Solution
2.1. Gaussian Mixture x K-means on HS6 Weight
2.2. Evaluation of classification method using ROC curve
2.3. Comparing logistic regression, neural network, and ensemble
2.4. Fruits or not, split or encode and scale first?
The next references provide some ideias on the application of previous ideas on customs context
Harmonized System Code Classification using transfer learning with pre-trained weights:
Risk management systems: using data mining in developing countries’ customs administrations:
https://worldcustomsjournal.org/Archives/Volume%205%2C%20Number%201%20(Mar%202011)/03%20Laporte.pdf
Databased employed in article "Risk management systems: using data mining in developing countries’ customs administrations":
https://tools.sars.gov.za/tradestatsportal/data_download.aspx
https://www.sars.gov.za/customs-and-excise/trade-statistics/
An explorative study into the effectiveness of a customs operation and its impact on trade:
Designing a new methodology for customs risk models:
Establishing risk and targeting profiles using data mining: Decision trees:
Managing Risk for Safe, Efficient Trade GUIDE FOR BORDER REGULATORS: