OER·harvester

← Back to the library
Zenodo PDF resource

Foundations of Artificial Intelligence & Machine Learning

Licence
OPEN CC-BY-4.0
Authors
Nidhi Sharma, Honey Singh, Ajay Sharma, Deepak Dagar
Published
2026-07-28 · Zenodo
Language
eng
Length
37166 words
Type
narrative text
Open ↗ Download Open original ↗
Accuracy

Accuracy measures how many predictions were correct out of the total predictions made by the model. It is one of the simplest and most commonly used evaluation metrics. For example, if a model correctly predicts 90 out of 100 cases, the accuracy becomes 90%. Although accuracy is useful, it may become misleading in imbalanced datasets. Precision Precision measures how many positive predictions were actually correct. This metric becomes important in applications such as:

  • fraud detection
  • disease diagnosis
  • cybersecurity systems where false positive predictions may create serious problems. Recall Recall measures how many actual positive cases were correctly identified by the model. In healthcare applications, high recall is important because missing a disease case may be dangerous. F1-Score F1-Score combines precision and recall into a single evaluation metric.

It is especially useful when datasets are imbalanced and accuracy alone becomes insufficient. Machine Learning practitioners often use F1-Score in:

  • spam detection

  • fraud analysis

  • medical classification systems where balanced performance is important. Overfitting and Underfitting Model evaluation also helps identify overfitting and underfitting problems. Overfitting Overfitting occurs when a model performs extremely well on training data but poorly on new unseen data. The model memorizes patterns instead of learning general relationships. Underfitting Underfitting occurs when the model fails to learn meaningful patterns from data. Such models produce poor performance on both training and testing datasets. Proper evaluation helps balance learning and generalization. Importance of Evaluation in AI Systems Modern AI applications require highly reliable Machine Learning models. Poor evaluation may lead to inaccurate predictions and weak system performance. Evaluation metrics help ensure that models:

  • perform accurately

  • generalize properly

  • make reliable decisions

  • handle real-world situations effectively As Artificial Intelligence systems continue growing in complexity, model evaluation will remain an essential part of Machine Learning development and deployment.

CHAPTER 6

UNSUPERVISED LEARNING TECHNIQUES