The CRISP-ML(Q) has six individual phases:

  1. Business and Data Understanding
    • Scope: what we want to achieve by using a machine
      learning process. Is it to retain customers or reduce the cost of
      operation by automation.
    • Success Criteria: we have to define clear and measurable business, machine learning (statistical metric), and economic (KPI) success metrics.
    • Feasibility: we need to ensure data availability,
      the applicability of ML application, legal constraints, robustness,
      scalability, explainability, and resource demand.
    • Data Collection: gathering the data, versioning it for reproducibility, and ensuring a constant stream of real-life and generated data.
    • Data Quality Verification: ensuring the quality by maintaining data description, requirements, and verification.
  2. Data Preparation
    1. Data selection, feature selection, data cleaning
    2. handling missing values, noise reduction
    3. feature engineering, data augmentations, one-hot encoding, and clustering
    4. Normalizing and scaling the data
  3. Model Engineering
    1. Research in model architecture and similar business problems
    2. Defining model performance metrics
    3. Model selection
    4. Understanding domain knowledge by incorporating experts.
    5. Model training
    6. Model compression and Ensemble
  4. Model Evaluation
  5. Model Deployment
    • Defining hardware inference
    • Model evaluation in production
    • Ensuring user acceptance and usability
    • Providing fall back plan and minimizing losses
    • Deployment strategy.
  6. Monitoring and Maintenance.