Log loss (logarithmic loss) measures how well the predicted probabilities of a classification model match the actual outcomes. Confident but wrong predictions are penalised particularly heavily; a value close to zero indicates well-calibrated forecasts. Example: if a model gives a 95% churn probability for a customer who stays, the log loss rises sharply. Mathematically it is the same as binary cross-entropy.
Cross-entropy is a measure from information theory that indicates how far a predicted probability distribution deviates from the actual one. In machine learning, it is the most common loss function for classification tasks and also for language models that predict the next token. It penalises confident wrong predictions especially heavily: assigning 99% to the wrong class yields a much higher loss than assigning 60%.
Logistic regression is a statistical method that predicts the probability of one of two outcomes, such as “buys” or “does not buy”. It weights the input features and converts their sum into a value between 0 and 1 using an S-shaped function. Because the weights are easy to interpret, it is widely used in credit scoring, medicine and marketing, often as a solid baseline for more complex models.
A classifier is a model or method that assigns inputs to one of several predefined categories. Classic variants such as decision trees or naive Bayes are trained on labelled examples; language models can also sort texts based on a description of the categories. Typical uses include spam detection, sorting customer enquiries by topic and categorising receipts. Quality is measured with metrics such as accuracy, precision and recall.
A confusion matrix is a table that compares a classifier's predictions with the actual classes. For two classes, it shows true positives, false positives, true negatives and false negatives. From this, metrics such as precision, recall and F1 score can be calculated, and it becomes clear which errors occur. Example: a spam filter that flags many genuine emails as spam has many false positives, which is often more costly than a missed spam message.
