Google’s machine learning data analyze service called Google Prediction API added a new training feature. The performance of the Google Prediction API improved its ability to provide better prediction results.
According to a post on Blogpost by Google, “Training can take up to 10 minutes, depending on the complexity and size of the data, but will typically take less time.”
Travis Green, a Product Manager of Google announced to Google Prediction API developers the latest upgrades for the program.
“Over the last year, the Prediction API has given you more and more tools to make your apps smarter and teach them to adapt and learn. Today we're adding a frequently requested feature: the ability to adjust models to get better performance,” said Green.
According to Green, historically, getting the right predictive model has required detailed knowledge of algorithmic behavior and experience with similar datasets, and a lot of guess-and-check. With the Prediction API, users need to input what behavior that need to be seen, and the system in Google will automatically search across many algorithms in search of locating the best-match.