Overfitting

What is ML Overfitting?

Model fitting is an important part of machine learning modelling and the accuracy of the particular model.

Overfitting occurs when a machine learning model cannot capture the evaluation data accurately due to memorising the training data. Model overfitting is when the model performs too well on the training data, but poorly on the unseen data. This happens due to a high complexity of the model – in other words, the machine learning model is too complex.

Reasons for model overfitting:

1. High variance in the model performance
2. High model complexity
3. Low data availability
4. Low data preparation

The following is an example of overfitting a machine learning model.

How to tackle model overfitting:

1. Reduction in model complexity
2. Adding more data
3. More efficient data preprocessing
4. Increase in regularisation
5. Reduction in training duration

The following is an example of a balanced machine learning model.

---

Next: Bias/Variance