Abstract: In an approach to provide consistent job descriptions for global entities, computer-implemented methods, computer program products, and computer systems for standardizing global entity job descriptions are described. The computer-implemented method for standardizing global entity job descriptions may include one or more processors configured for receiving first job identifier data corresponding to a job posting having a plurality of job descriptions, generating second job identifier data by removing duplicate job descriptions and outlier job descriptions from the plurality of job descriptions, determining job description intents for the plurality of job descriptions based at least on the second job identifier data, generating third job identifier data corresponding to job description similarity groupings based on the job description intents and the second job identifier data, and generating fourth job identifier data comprising a standard job description based on the third job identifier data.

Abstract: An approach for determining most a qualified employee for a job based on analyzing gap in between skill of the employee and the job description requirement is disclosed. The approach utilizes machine learning to extract key skills like functional skills of an employee profile from an organization and job descriptions with a hierarchy of profiles. The approach builds a multi-dimension vector representation for each employee key skills and job descriptions. The approach calculates the vector distance between the key skills in profile vector and job description vector and maintaining the scores for each node. Finally, the approach generates the skill gap summary for the employee by matching the job description with employee profiles.

Abstract: Techniques for failure prediction are provided. A plurality of event indications is received, where each respective event indication corresponds to a respective failure in a computing system. A plurality of machine learning (ML) models is trained based on combinations of event indications in the plurality of event indications, and the ML models are evaluated to generate a respective quality score for each respective ML model. An ensemble of ML models is defined from the plurality of ML models, based on identifying ML models of the plurality of ML models with corresponding quality scores exceeding a predefined threshold. Current data logs from the computing system are processed using the ensemble of ML models, and upon determining that any ML model of the ensemble of ML models predicted a failure based on the current data logs, an alert is generated.

Abstract: Techniques for failure prediction are provided. A plurality of event indications is received, where each respective event indication corresponds to a respective failure in a computing system. A plurality of machine learning (ML) models is trained based on combinations of event indications in the plurality of event indications, and the ML models are evaluated to generate a respective quality score for each respective ML model. An ensemble of ML models is defined from the plurality of ML models, based on identifying ML models of the plurality of ML models with corresponding quality scores exceeding a predefined threshold. Current data logs from the computing system are processed using the ensemble of ML models, and upon determining that any ML model of the ensemble of ML models predicted a failure based on the current data logs, an alert is generated.