Precision
Of all the times a model predicted positive, the fraction it was actually right — a measure of how trustworthy positive predictions are.
When we evaluate an artificial intelligence model, precision answers a simple question: when the model predicts a positive result, how often is it actually correct? For example, if a model has a precision of ninety percent, it means ninety percent of its positive predictions are right, while the remaining ten percent are false alarms.
You want to focus on precision when the cost of a false positive is high. Consider a link spam detector. If it has low precision, it will flag legitimate links as spam, which creates unnecessary work and can hurt search engine optimization. A high-precision detector might miss some spam, but everything it does flag is genuinely problematic. The same goes for detecting AI-generated content. High precision means that when the system flags a piece of text, clients can trust the result without having to manually double-check every single prediction.
Of course, precision doesn't exist in a vacuum. It sits on a scale with recall, which measures how many of the actual positive cases the model managed to find. When you tune a model to be more conservative, precision goes up, but recall goes down. To find the right balance, developers often look at the F-one score, which combines both metrics into a single number. Tracking all three values is the best way to understand exactly how well a model is performing.
What precision is
Precision answers the question: when the model said "yes," how often was it correct? Formally, it is the number of true positives divided by the total number of positive predictions (true positives plus false positives). A precision of 0.90 means that 90% of the model's positive predictions were correct, and 10% were false alarms.
When precision matters most
Precision is the metric to prioritise when false positives are costly. A link spam detector with low precision flags legitimate links as spam — causing unnecessary disavow work and potentially hurting SEO. A high-precision detector may miss some spam (low recall) but everything it does flag is genuinely problematic. The cost of each error type determines which metric to optimise.
For DEJAN's AI content detection model, high precision means that when it flags content as AI-generated, the flag is reliable — clients can act on it without manually reviewing every prediction.
Precision and recall together
Precision and recall trade off against each other. Raising the decision threshold makes the model more conservative — it predicts positive less often, so when it does, it's more likely to be right (higher precision) but it misses more actual positives (lower recall). The F1 score combines both into a single number. DEJAN's training pipelines track all three and select checkpoints by F1, with precision and recall reported alongside for transparency.