Workflow Element Store

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

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