Modeling and Evaluation
Dr.A.SENTHILKUMAR
Assistant Professor
Department of Computer Science with Data Analytics
Sri Ramakrishna College of Arts and Science
Coimbatore - 641 006
Tamil Nadu, India
SRCAS
1
23CDAP03– Machine Learning with Lab
Introduction to Machine Learning
• Definition: Machine Learning is the study of algorithms that
improve their performance at a task with experience.
• Key components: Performance PP, Task TT, Experience EE
Importance of Modeling
Purpose of modeling in ML: To represent data relationships.
To make predictions based on input data.
Types of models:
• Supervised Learning (e.g., regression, classification).
• Unsupervised Learning (e.g., clustering).
• Reinforcement Learning
Steps in Model Development
1.Data Collection: Gather relevant data.
2.Data Preprocessing: Clean and prepare data for modeling.
3.Model Selection: Choose appropriate algorithms (e.g., decision trees,
SVMs).
4.Training: Fit the model to the training data.
5.Testing: Evaluate model performance on unseen data
Evaluation Metrics
• Common metrics for assessing model performance:Accuracy:
Proportion of correct predictions.
• Precision and Recall: Useful for imbalanced datasets.
• F1 Score: Harmonic mean of precision and recall.
• ROC-AUC: Area under the Receiver Operating Characteristic
curve
Overfitting vs. Underfitting
• Overfitting: Model learns noise in the training data; performs
poorly on test data.
• Underfitting: Model is too simple to capture underlying patterns;
poor performance on both training and test data.
Cross-Validation Techniques
• Importance of cross-validation in evaluating model
performance:K-Fold Cross-Validation
• Leave-One-Out Cross-Validation (LOOCV)
• Benefits include reducing overfitting and providing a better
estimate of model performance
