Allocation of Shared Computing Resources Using Source Code Feature Extraction and Clustering-Based Training of Machine Learning Models

A computer program product, comprising a tangible machine-readable storage medium having encoded therein executable code of one or more software programs, wherein the one or more software programs when executed by at least one processing device perform the following steps:

• obtaining a source code corpus with a plurality of source code segments for execution in a shared computing environment;
• extracting a plurality of discriminative features from the plurality of source code segments in the source code corpus;
• obtaining at least one trained machine learning model, wherein the at least one trained machine learning model is trained using samples of source code segments from clusters derived from clustering the source code corpus based on one or more of (i) a term frequency metric, and (ii) observed values of execution metrics;
• and
• generating, using the at least one trained model, a prediction of an allocation of one or more resources of the shared computing environment needed to satisfy one or more service level agreement requirements for one or more source code segments to be executed in the shared computing environment.

An apparatus, comprising:

• a memory;
• and
• at least one processing device, coupled to the memory, operative to implement the following steps:
• obtaining a source code corpus with a plurality of source code segments for execution in a shared computing environment;
• extracting a plurality of discriminative features from the plurality of source code segments in the source code corpus;
• obtaining at least one trained machine learning model, wherein the at least one trained machine learning model is trained using samples of source code segments from clusters derived from clustering the source code corpus based on one or more of (i) a term frequency metric, and (ii) observed values of execution metrics;
• and
• generating, using the at least one trained model, a prediction of an allocation of one or more resources of the shared computing environment needed to satisfy one or more service level agreement requirements for one or more source code segments to be executed in the shared computing environment.