Constructing machine learning models

A non-transitory computer-readable medium storing instructions which, when executed by a processing system in a communications network, cause the processing system to perform operations, the operations comprising:

• initializing a configuration file for a machine learning model, wherein the initializing is performed in response to receiving a request from a user, and wherein the configuration file comprises a plurality of sections that is configurable by the user;
• configuring at least one parameter of a feature engineering rules section of the configuration file, wherein the feature engineering rules section comprises a plurality of logic blocks, wherein each logic block of the plurality of logic blocks defines a feature to be extracted by the machine learning model from an input dataset, wherein the configuring the at least one parameter of the feature engineering rules section is based on a first value provided by the user, and wherein the feature engineering rules section is one of the plurality of sections;
• configuring at least one parameter of an algorithm definitions section of the configuration file, wherein the configuring the at least one parameter of the algorithm definitions section is based on a second value provided by the user, and wherein the algorithm definitions section is one of the plurality of sections;
• and
• populating the configuration file using the feature engineering rules section as configured and the algorithm definitions section as configured, to generate the machine learning model.

A device comprising:

• a processing system including at least one processor;
• and
• a non-transitory computer-readable medium storing instructions which, when executed by the processing system, cause the processing system to perform operations, the operations comprising:
• initializing a configuration file for a machine learning model, wherein the initializing is performed in response to receiving a request from a user, and wherein the configuration file comprises a plurality of sections that is configurable by the user;
• configuring at least one parameter of a feature engineering rules section of the configuration file, wherein the feature engineering rules section comprises a plurality of logic blocks, wherein each logic block of the plurality of logic blocks defines a feature to be extracted by the machine learning model from an input dataset, wherein the configuring the at least one parameter of the feature engineering rules section is based on a first value provided by the user, and wherein the feature engineering rules section is one of the plurality of sections;
• configuring at least one parameter of an algorithm definitions section of the configuration file, wherein the configuring the at least one parameter of the algorithm definitions section is based on a second value provided by the user, and wherein the algorithm definitions section is one of the plurality of sections;
• and
• populating the configuration file using the feature engineering rules section as configured and the algorithm definitions section as configured, to generate the machine learning model.