Parts Availability Analytics Using Supervised Machine Learning Algorithms

Share on twitter
Share on facebook
Share on linkedin
Share on whatsapp
Share on email

Anglo-Australian multinational mining, metals and petroleum company

Problem Statement

  • Identification of factors which effect Parts Availability and understand their impact
  • Prediction of parts availability failure and setting up an advance alert mechanism , integrate approaches to improve and manage Parts Ordering and Availability

Solution Approach

  • Data Input

  • Application Features

  • Model Dataset

  • Logistic Regression

  • Logistic Regression

  • MARS Model

Business Impact

  • Identification of business rules defining success and failure of parts availability

  • Part Availability Failure Prediction

  • Theoretical lift which can be achieved by controlling “Planned Delivery Time”

Critical Success Factors

  • Every Stage of process flow modeled separately
  • Part Availability Failure Prediction

    XTechalpha: Launching a “next-in class“ platform of exponential technologies: AI, Blockchain, Cloud, Cybersecurity, IoT & emerging segments: GCCs, Startups and Academic Institutions & Edtech accentuated with an enviable line up of proven and seasoned thought leaders bringing together and ensemble, curated content, networking interventions and learning enhancement. A must visit primer for GIC heads, Technology leaders, Exponential technologies enthusiasts, Academic deans and Entrepreneurs.

    Watch the Launch video:

    XTechalpha: reimagine your THINKING