Engineering data analytics platforms using machine learning

A system comprising:

• one or more computers;
• and
• one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
• accessing, for each past data analysis provider of one or more past data analysis providers, historical information that includes (i) past characteristics of past data analyzed by the past data analysis provider, (ii) past computing loads during analysis of the past data by the past data analysis provider, (iii) past analysis techniques offered by the past data analysis provider, (iv) past access and security requirements implemented by the past data analysis provider for past users accessing the past data analyzed by the data analysis provider, and (v) past configurations of the respective data analysis provider used to analyze the past data;
• training, using machine learning and using the historical information, a model that receives (i) given characteristics of given data, (ii) given computing loads of each of one or more given data analysis providers, (iii) given analysis techniques offered by each of the one or more given data analysis providers, (iv) given access and security requirements for given users accessing analyzed given data, and outputs data indicating (i) a subset of the one or more given data analysis providers to analyze the given data and (ii) a given configuration for the subset of the one or more given data analysis providers;
• and
• providing the model to a recommendation generator, wherein the recommendation generator recommends based on the model both (i) one or more data analysis providers to analyze data and (ii) a configuration for the one or more data analysis providers.

A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

• accessing, for each past data analysis provider of one or more past data analysis providers, historical information that includes (i) past characteristics of past data analyzed by the past data analysis provider, (ii) past computing loads during analysis of the past data by the past data analysis provider, (iii) past analysis techniques offered by the past data analysis provider, (iv) past access and security requirements implemented by the past data analysis provider for past users accessing the past data analyzed by the data analysis provider, and (v) past configurations of the respective data analysis provider used to analyze the past data;
• training, using machine learning and using the historical information, a model that receives (i) given characteristics of given data, (ii) given computing loads of each of one or more given data analysis providers, (iii) given analysis techniques offered by each of the one or more given data analysis providers, (iv) given access and security requirements for given users accessing analyzed given data, and outputs data indicating (i) a subset of the one or more given data analysis providers to analyze the given data and (ii) a given configuration for the subset of the one or more given data analysis providers;
• and
• providing the model to a recommendation generator, wherein the recommendation generator recommends based on the model both (i) one or more data analysis providers to analyze data and (ii) a configuration for the one or more data analysis providers.