Posted by James Wexler, Software Engineer, Google AI Building effective machine learning (ML) systems means asking a lot of questions. It's not enough to train a model and walk away. Instead, good practitioners act as detectives, probing to understand their model better: How would changes to a datapoint affect my model’s prediction? Does it perform differently for various groups–for example, histo
![Google AI Blog: The What-If Tool: Code-Free Probing of Machine Learning Models](https://cdn-ak-scissors.b.st-hatena.com/image/square/5fb14460c430d1851fd383ac8b24b96d32b7f918/height=288;version=1;width=512/https%3A%2F%2F1.bp.blogspot.com%2F-KgKc1scTJHE%2FW5b3SWTpS0I%2FAAAAAAAADUY%2FucVU6ZVlvTcrqgLG9UviU8o9-BLeseR0QCLcBGAs%2Fw1200-h630-p-k-no-nu%2Fimage1.png)