E. Sampling Strategy และ Model Evaluation

The Sampling Strategy and Model Evaluation course offers foundational knowledge and techniques related to data sampling and model evaluation. It covers various sampling methods such as Simple Random, Stratified, Systematic, and Cluster sampling. The course also delves into advanced sampling techniques for handling imbalanced datasets, including methods like SMOTE (Synthetic Minority Over-sampling Technique) and Cluster-based Oversampling to enhance sampling efficiency.

Additionally, the course addresses model evaluation metrics for classification models, including Confusion Matrix, Accuracy, Precision, Recall, and F1-Score. Learners will gain an in-depth understanding of using ROC (Receiver Operating Characteristic) curves and AUC (Area Under the Curve) to assess model performance.

Students will acquire essential skills in data preparation, sampling, and model evaluation, which are crucial for data analysis and deep learning in the field of Data Science. By the end of the course, learners will be equipped to effectively apply these techniques in real-world data science scenarios.