# Machine Learning for State Model Improvement - Master Internship
## Assignment Overview
ASML uses a standardized State Model (aligned with SEMI E-10 standard) to derive machine performance and availability information from machine-generated data. While the automated State Model provides consistent interpretation, manual reconciliation is still necessary to incorporate business and operational context. This internship focuses on improving the State Model using Machine Learning techniques.
## Objectives
- Improve the quality of automatically generated machine state
- Reduce the number of corrections required during reconciliation
- Increase consistency across machines, sites, and product lines
## Key Responsibilities
- Understanding the Existing Pipeline: Study event logs, task interpretation, State Model logic (states, substates, triggers), and reconciliation process/EPC workflow
- Dataset Preparation: Align original and reconciled states, identify reconciliation changes, extract features from event logs, machine tasks, task transitions, and logbook information
- Machine Learning Model Development: Apply supervised learning using reconciled states as ground truth, predict machine states/state transitions, justify model choice and features
- Evaluation: Compare Current State Model output, ML-based predictions and reconciled states, provide quantitative assessment of potential quality improvements
- Conclusions and Recommendations: Assess feasibility of ML support, possible integration approaches (decision support vs automation), document limitations, risks, and explainability considerations
## Requirements
- Master student in Data Science or related field
- Programming experience (preferably Python)
- Strong analytical skills and structured thinking
- Proactive approach and ability to take ownership
- Enrolled at educational institute for entire internship duration
- Located in the Netherlands (or willing to relocate)
- If non-EU citizen: university must be willing to sign relevant internship documents (Nuffic agreement)
- Must submit cover letter with clear motivation
## Duration and Schedule
- Minimum 6 months
- Minimum 4 days per week (minimum 2 days on-site)
- Start date: September 2026