Goto

Collaborating Authors

automl app


How to Build an AutoML App in Python

#artificialintelligence

Automated machine learning (AutoML) helps to lower the barrier to entry for machine learning model building by streamlining the process thereby allowing non-technical users to harness the power of machine learning. On the other hand, the availability of AutoML also helps to free up the time of data scientists (that they would have otherwise spent doing redundant and repetitive pre-processing tasks or model building tasks) by allowing them to explore other areas of the data analytics pipeline. In a nutshell, users can supply an input dataset to the AutoML system that it uses for model building (feature transformation, feature selection, hyperparameter optimization, etc.) and finally it returns the predictions as the output. Wouldn't it be great if you can build your very own AutoML App that you can custom tailor to your heart's content? The development of this AutoML App is 2 folds: (1) Model deployment helps to complete the data life cycle and (2) AutoML helps to make ML accessible to non-technical users.