Workflow Element Store

  1. Data Generation
  2. Surveys and Questionnaires
  3. Public Datasets
  4. Data Pre-existing
  5. Crowdsourcing
  6. APIs and Data Feeds
  7. Unstructured data (Audio)
  8. Structured Data (Tabular)
  9. WebScraping
  10. Data Logging
  11. Mobile Applications or IoT Applications
  12. Data Collaboration and Partnerships
  13. Unstructured data (Images / Videos)
  1. GCS
  2. RDBMS
  3. S3
  4. GCP BigQuery
  5. PostgreSQL
  6. MS SQL server
  7. MySQL
  8. Azure Data Warehouse
  9. AWS Redshift
  10. Informatica
  11. NoSQL DB
  12. Azure blob storage
  13. Oracle DB
  1. Time-Based Features
  2. Handling Imbalanced Classes
  3. Dealing with Outliers
  4. Dimensionality Reduction
  5. AutoEDA libraries
  6. Handling Categorical Data
  7. Data Scaling and Normalization
  8. Handling Noisy Data
  9. Data Scaling and Normalization
  10. Feature Extraction from Images
  11. Textual Feature Extraction
  12. Auto-Preprocessing libraries
  13. Domain-Specific Feature Engineering
  14. Handling Time-Series Data
  15. Encoding Categorical Variables
  16. Binning
  17. Logarithmic Transform
  18. Handling Missing Data
  19. Interaction Features
  20. Polynomial Features
  21. Dimensionality Reduction
  22. Feature Selection
  1. Supervised Learning-Regression
  2. Ensemble Techniques
  3. Supervised Learning-multiclass classification
  4. Train-Test Split
  5. Time Series Anaysis
  6. Forecasting
  7. Data Partitioning
  8. Unsupervised Learning
  9. Supervised Learning-binary classification
  10. Blackbox Techniques
  1. Cross-Validation
  2. Ensemble Methods
  3. Data Augmentation
  4. Gradient Clipping
  5. Train-Test Split
  6. Early Stopping
  7. Transfer Learning
  8. Regularization
  9. Weight Initialization
  10. Learning Rate Scheduling
  11. Batch Size Selection
  12. Data Partition-sequential
  13. Hyperparameter Tuning
  14. Regular Monitoring and Logging
  15. Batch Normalization
  1. Model Interpretability
  2. Hyperparameter Tuning
  3. Data Partitioning
  4. Performance Visualization
  5. Evaluation Metrics
  6. Regularization Techniques
  7. Model Comparison
  8. External Validation
  9. Cross-Validation
  10. Train-Test Split
  1. Model Drift
  2. Serverless Computing
  3. Edge Deployment
  4. Error Analysis
  5. Model Monitoring and Maintenance
  6. Model Registry
  7. Alerting and Notification
  8. Concept Drift Detection
  9. Web APIs - Flask, FastAPI, etc.
  10. Feedback Collection
  11. Model Health Monitoring
  12. Prediction Logging
  13. Streamlit
  14. Monitoring and Logging
  15. Cloud Deployment
  16. Data Drift Monitoring
  17. Model Retraining and Updating
  18. Performance Metrics
  19. A/B Testing
  20. Model Versioning
  21. Containerization
  22. Bias and Fairness Assessment
  23. Model Serialization
  24. Security Considerations
  25. Continuous Integration and Deployment (CI/CD)
  26. Documentation and Reporting
  27. Documentation and API Documentation
  1. Mobile
  2. End User Machine
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