Your Browser is Out of Date

Nytro.ai uses technology that works best in other browsers.
For a full experience use one of the browsers below
DELLQUINN: A Machine Learning-Based, Resource Capacity Optimization Solution
Introduction Methodology
Methodology
DELLQUINN solution components
Key takeaways User feedback Conclusion References

Methodology

Home > AI Solutions > Artificial Intelligence > White Papers > DELLQUINN: A Machine Learning-Based, Resource Capacity Optimization Solution > Methodology

Methodology

  • The Dell HES Field Services APJC Business Operations team aims to efficiently meet the evolving future workload demand by:

    • Ensuring field readiness and availability for dispatches
    • Optimizing the workforce utilization to maximize financial performance

    The Services Operations Data Science (DS) team makes these Field Services goals possible by employing ML algorithms that leverage a time-series demand forecasting model coupled with a collaborative filter and an optimization framework. This combination helps the team prioritize and optimize FSE capacity based on future dispatches at the country, Line of Business (LOB), and week levels.

    To comprehend the field reality of dispatches, resource utilization, and overtime estimation, the DS team performed extensive research before developing the DELLQUINN workload optimization solution.

    As a result, DELLQUINN is scripted on Python and R on a Celonis ML workbench. Reporting, insights visualization, and output metrics such as forecasted utilization, overtime, and staffing levels across APJC countries are rendered on a Power BI dashboard for business decision-making.