Workflow Element Store

  1. WebScraping
  2. Data Collaboration and Partnerships
  3. Data Logging
  4. Data Pre-existing
  5. Unstructured data (Audio)
  6. Surveys and Questionnaires
  7. Crowdsourcing
  8. Structured Data (Tabular)
  9. Mobile Applications or IoT Applications
  10. Public Datasets
  11. APIs and Data Feeds
  12. Data Generation
  13. Unstructured data (Images / Videos)
  1. NoSQL DB
  2. MySQL
  3. S3
  4. GCS
  5. GCP BigQuery
  6. RDBMS
  7. Oracle DB
  8. PostgreSQL
  9. AWS Redshift
  10. Azure blob storage
  11. Azure Data Warehouse
  12. MS SQL server
  13. Informatica
  1. Binning
  2. Auto-Preprocessing libraries
  3. Textual Feature Extraction
  4. Handling Categorical Data
  5. Handling Missing Data
  6. Feature Selection
  7. Handling Time-Series Data
  8. Interaction Features
  9. Logarithmic Transform
  10. Feature Extraction from Images
  11. Dimensionality Reduction
  12. Polynomial Features
  13. Dimensionality Reduction
  14. Time-Based Features
  15. Data Scaling and Normalization
  16. Handling Noisy Data
  17. AutoEDA libraries
  18. Data Scaling and Normalization
  19. Handling Imbalanced Classes
  20. Encoding Categorical Variables
  21. Dealing with Outliers
  22. Domain-Specific Feature Engineering
  1. Supervised Learning-multiclass classification
  2. Unsupervised Learning
  3. Supervised Learning-binary classification
  4. Time Series Anaysis
  5. Ensemble Techniques
  6. Blackbox Techniques
  7. Supervised Learning-Regression
  8. Train-Test Split
  9. Data Partitioning
  10. Forecasting
  1. Hyperparameter Tuning
  2. Train-Test Split
  3. Regular Monitoring and Logging
  4. Gradient Clipping
  5. Data Partition-sequential
  6. Data Augmentation
  7. Cross-Validation
  8. Early Stopping
  9. Batch Size Selection
  10. Weight Initialization
  11. Regularization
  12. Ensemble Methods
  13. Batch Normalization
  14. Learning Rate Scheduling
  15. Transfer Learning
  1. Evaluation Metrics
  2. Model Interpretability
  3. Hyperparameter Tuning
  4. Performance Visualization
  5. Data Partitioning
  6. External Validation
  7. Cross-Validation
  8. Regularization Techniques
  9. Train-Test Split
  10. Model Comparison
  1. Data Drift Monitoring
  2. Model Retraining and Updating
  3. Model Registry
  4. Monitoring and Logging
  5. Cloud Deployment
  6. Model Health Monitoring
  7. Web APIs - Flask, FastAPI, etc.
  8. Prediction Logging
  9. Concept Drift Detection
  10. Alerting and Notification
  11. Bias and Fairness Assessment
  12. Model Serialization
  13. Documentation and Reporting
  14. Documentation and API Documentation
  15. Edge Deployment
  16. Model Drift
  17. Streamlit
  18. Error Analysis
  19. Continuous Integration and Deployment (CI/CD)
  20. Security Considerations
  21. Serverless Computing
  22. Feedback Collection
  23. Model Monitoring and Maintenance
  24. Performance Metrics
  25. Containerization
  26. A/B Testing
  27. Model Versioning
  1. End User Machine
  2. Mobile
ML Workflow - Architecture
  • Element belongs to model
  • Element not belongs to model

Feature Store
(Online / Offline)

Data Sources

Data Warehouse/ Data Lake

EDA, Data Pre Processing & Feature Engineering

Model Selection

Model Training & Hyper Parameter Tuning

Model Evaluation

Model Deployment

End User Device

Model Registry