What is a common result of a model that has high bias?

A model that has high bias typically makes strong assumptions about the data which can lead to oversimplified representations of the underlying patterns. This often results in the model failing to capture the complexities and variances present in the training data. Therefore, it may underfit the training set, meaning that the model is not adequately capturing the trends or relationships within the data, leading to poor performance not just on unseen data but also on the training data itself.

High bias is often associated with models that are too simplistic, characterized by limited flexibility to fit the intricacies of the data. Consequently, underfitting indicates a lack of learning from the complexities of the training set, which further contributes to a model that does not generalize well to new, unseen data. Understanding this concept is crucial in the context of model selection and refinement in the field of machine learning and artificial intelligence.