Methodology

Data Analytics

  1. Statistical Analysis
  2. Quantitative Technical Analysis
  3. Trend Trading
  4. Momentum Trading
  5. Support and Resistance
  6. Breakout Analysis
  7. Feature Extraction
  8. Regression Analysis
  9. Decision Tree
  10. Multilayer Perceptron (MLP)
  11. Gradient Boosted Decision Tree
  12. Ensemble Learning
  13. Long Short-term Memory (LSTM)
  14. Reinforcement Learning

Project Roadmap

  1. Use Case Requirements
    • Use Case Requirements
    • Data Requirements
    • Input Feature Requirements
    • Inference Requirements
  2. DevOps for Machine Learning (MLOps)
    • Data Repository
    • Software Repository
    • Machine Learning Artifacts Repository
    • Continuous Integration Automation
      • Build, Train, Test, Tune, Deploy
      • Measure, Optimize, Monitor
  3. Data Pipeline
    • Acquire, Extract, Combine, Persist
    • Analyze, Filter, Format, Convert, Transform
    • Scale, Normalize, Standardize, Validate
    • Engineer and Store Features
  4. Modeling
    • Statistical Models
    • Regression Analysis
    • Input Feature Extraction and Engineering
    • Framework and Algorithm Selection
    • Machine Learning Platforms
    • Machine Learning Models
    • Artificial Neural Networks
    • Hyperparameter Optimization
  5. Deployment
    • Infrastructure
    • Framework
    • Platform
  6. Integration
    • Decoupled Abstraction
    • REST API
    • Inference Microservice
    • ML Software as a Service
    • Service and Dependency Injection
    • User Interfaces

Input Feature Selection