SVM Used its Innovative Machine Learning Tool to Improve Vetting Inspection Outcomes

SVM Analytics, used its innovative machine learning and predictive modeling tool SEDGE to mine Teekay Tankers' Ship Management vetting inspection data.

Whilst Teekay Tankers OCIMF SIRE Vetting inspection results are amongst the best in the industry, to continue to be a leader in this business critical metric, a project was undertaken to establish the main criteria that will significantly move the needle to further improve fleetwide inspection results .

SEDGE identified key attributes and their correlation (Linear & Non Linear) that influence vetting inspection outcomes. SEDGE automatically mined the order of importance, cluster and hierarchy of each attribute. These findings are instrumental in shaping up initiatives taken to achieve 2016 vetting inspections goals. Solverminds is a great partner to work with. Entire project was executed promptly and to full satisfaction of Teekay Tankers Ship Management

IDENTIFYING RISK TO IMPROVE VETTING RESULTS

SEDGE churned customer vetting operation data, ran advanced machine learning

algorithms and

• Identified key attributes

• Determined the order of importance,

• Established the hierarchy of attribute

• Determined the influence on vetting inspection outcomes

• Customer Ship Management

These findings were instrumental in decisive initiatives taken by customer to

achieve vetting inspections goals.

These initiatives are predicted to reduce risk and contribute to huge operational

savings.

Whilst our Vetting inspection results are amongst the best in the industry, to continue to be a leader in this business critical metric, a project was undertaken to establish the main

criteria that will significantly move the needle to further improve fleet-wide inspection results.

SEDGE automatically mined the order of importance, cluster and hierarchy of each attribute. These findings are instrumental in shaping up initiatives taken to achieve 2016 vetting inspections goals.