Deploy and run powerful machine learning algorithms on your data to garner deep insights, take optimal decisions, reduce cost and improve productivity.

Inferneon™ is a machine learning platform developed by IPSG Systems that democratizes the application of machine learning for organizations that want to gain useful insight into their data. It provides a SaaS-based or in-premises platform to help organizations learn useful patterns in their data for useful decision making, reducing cost and improve efficiency.The platform provides users the ability to ingest unstructured data in Big Data platforms like Hadoop, transform them in useful ways, run pre-deployed machine learning algorithms on them and use the results in various applications.

Inferneon provides a SaaS-based platform that allows users to create, deploy and run machine learning algorithms. The platform consists of a core machine learning component, a metadata store to store the results of the machine learning computations and the data store hosting the data on which the algorithms run. The platform can be used by two types of users:

a. The Data Scientist : This type of user typically has expertise in machine learning algorithms and statistics. The UI provides this user with data visualization, the ability to select and run algorithms on the data and to generate machine learning models that can later be used by business analysts for prediction, clustering, classification, etc. Actions like registering new algorithms, ingesting data, running algorithms, etc. is typically performed by this user.

b. The Business analyst : This user is typically a domain expert or someone well-versed with theoperational and business dynamics of the system. The UI for this user is limited to providingthe ability to use the results of the algorithms (called models) generated by the data scientist for specific business purposes. For example, a business analyst in a bank might be interested in determining if a particular transaction is fraudulent; the interface provides a means to run this transaction against the model generated by the data scientist to predict the outcome.