popov/gogo2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

wip training

Browse Source
This commit is contained in:
Dobromir Popov
2025-07-24 15:27:32 +03:00
parent b3edd21f1b
commit fa07265a16
4 changed files with 554 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

43
.kiro/specs/multi-modal-trading-system/design.md
View File

@ -140,7 +140,7 @@ Training:
### 4. Orchestrator
The Orchestrator serves as the central coordination hub of the multi-modal trading system, responsible for data subscription management, model inference coordination, output storage, and training pipeline orchestration.
The Orchestrator serves as the central coordination hub of the multi-modal trading system, responsible for data subscription management, model inference coordination, output storage, training pipeline orchestration, and inference-training feedback loop management.
#### Key Classes and Interfaces
@ -245,6 +245,47 @@ The Orchestrator coordinates training for all models by managing the prediction-
- checkpoint manager has capability to ensure only top 5 to 10 best checkpoints are stored for each model deleting the least performant ones. it stores metadata along the CPs to decide the performance
- we automatically load the best CP at startup if we have stored ones
##### 5. Inference Data Validation and Storage
The Orchestrator implements comprehensive inference data validation and persistent storage:
**Input Data Validation**:
- Validates complete OHLCV dataframes for all required timeframes before inference
- Checks input data dimensions against model requirements
- Logs missing components and prevents prediction on incomplete data
- Raises validation errors with specific details about expected vs actual dimensions
**Inference History Storage**:
- Stores complete input data packages with each prediction in persistent storage
- Includes timestamp, symbol, input features, prediction outputs, confidence scores, and model internal states
- Maintains compressed storage to minimize footprint while preserving accessibility
- Implements efficient query mechanisms by symbol, timeframe, and date range
**Storage Management**:
- Applies configurable retention policies to manage storage limits
- Archives or removes oldest entries when limits are reached
- Prioritizes keeping most recent and valuable training examples during storage pressure
- Provides data completeness metrics and validation results in logs
##### 6. Inference-Training Feedback Loop
The Orchestrator manages the continuous learning cycle through inference-training feedback:
**Prediction Outcome Evaluation**:
- Evaluates prediction accuracy against actual price movements after sufficient time has passed
- Creates training examples using stored inference data paired with actual market outcomes
- Feeds prediction-result pairs back to respective models for learning
**Adaptive Learning Signals**:
- Provides positive reinforcement signals for accurate predictions
- Delivers corrective training signals for inaccurate predictions to help models learn from mistakes
- Retrieves last inference data for each model to compare predictions against actual outcomes
**Continuous Improvement Tracking**:
- Tracks and reports accuracy improvements or degradations over time
- Monitors model learning progress through the feedback loop
- Alerts administrators when data flow issues are detected with specific error details and remediation suggestions
##### 5. Decision Making and Trading Actions
Beyond coordination, the Orchestrator makes final trading decisions:

44
.kiro/specs/multi-modal-trading-system/requirements.md
View File

@ -130,4 +130,46 @@ The Multi-Modal Trading System is an advanced algorithmic trading platform that
5. WHEN implementing the system architecture THEN the system SHALL use a unified interface for all data providers.
6. WHEN implementing the system architecture THEN the system SHALL use a unified interface for all trading executors.
7. WHEN implementing the system architecture THEN the system SHALL use a unified interface for all risk management components.
8. WHEN implementing the system architecture THEN the system SHALL use a unified interface for all dashboard components.
8. WHEN implementing the system architecture THEN the system SHALL use a unified interface for all dashboard components.
### Requirement 9: Model Inference Data Validation and Storage
**User Story:** As a trading system developer, I want to ensure that all model predictions include complete input data validation and persistent storage, so that I can verify models receive correct inputs and track their performance over time.
#### Acceptance Criteria
1. WHEN a model makes a prediction THEN the system SHALL validate that the input data contains complete OHLCV dataframes for all required timeframes
2. WHEN input data is incomplete THEN the system SHALL log the missing components and SHALL NOT proceed with prediction
3. WHEN input validation passes THEN the system SHALL store the complete input data package with the prediction in persistent storage
4. IF input data dimensions are incorrect THEN the system SHALL raise a validation error with specific details about expected vs actual dimensions
5. WHEN a model completes inference THEN the system SHALL store the complete input data, model outputs, confidence scores, and metadata in a persistent inference history
6. WHEN storing inference data THEN the system SHALL include timestamp, symbol, input features, prediction outputs, and model internal states
7. IF inference history storage fails THEN the system SHALL log the error and continue operation without breaking the prediction flow
### Requirement 10: Inference-Training Feedback Loop
**User Story:** As a machine learning engineer, I want the system to automatically train models using their previous inference data compared to actual market outcomes, so that models continuously improve their accuracy through real-world feedback.
#### Acceptance Criteria
1. WHEN sufficient time has passed after a prediction THEN the system SHALL evaluate the prediction accuracy against actual price movements
2. WHEN a prediction outcome is determined THEN the system SHALL create a training example using the stored inference data and actual outcome
3. WHEN training examples are created THEN the system SHALL feed them back to the respective models for learning
4. IF the prediction was accurate THEN the system SHALL reinforce the model's decision pathway through positive training signals
5. IF the prediction was inaccurate THEN the system SHALL provide corrective training signals to help the model learn from mistakes
6. WHEN the system needs training data THEN it SHALL retrieve the last inference data for each model to compare predictions against actual market outcomes
7. WHEN models are trained on inference feedback THEN the system SHALL track and report accuracy improvements or degradations over time
### Requirement 11: Inference History Management and Monitoring
**User Story:** As a system administrator, I want comprehensive logging and monitoring of the inference-training feedback loop with configurable retention policies, so that I can track model learning progress and manage storage efficiently.
#### Acceptance Criteria
1. WHEN inference data is stored THEN the system SHALL log the storage operation with data completeness metrics and validation results
2. WHEN training occurs based on previous inference THEN the system SHALL log the training outcome and model performance changes
3. WHEN the system detects data flow issues THEN it SHALL alert administrators with specific error details and suggested remediation
4. WHEN inference history reaches configured limits THEN the system SHALL archive or remove oldest entries based on retention policy
5. WHEN storing inference data THEN the system SHALL compress data to minimize storage footprint while maintaining accessibility
6. WHEN retrieving historical inference data THEN the system SHALL provide efficient query mechanisms by symbol, timeframe, and date range
7. IF storage space is critically low THEN the system SHALL prioritize keeping the most recent and most valuable training examples

81
.kiro/specs/multi-modal-trading-system/tasks.md
View File

@ -135,6 +135,9 @@
- Add thread-safe access to multi-rate data streams
- _Requirements: 4.1, 1.6, 8.5_
- [ ] 4.2. Implement model inference coordination
- Create ModelInferenceCoordinator class
- Trigger model inference based on data availability and requirements
@ -176,6 +179,84 @@
- Provide model performance monitoring and alerting
- _Requirements: 4.6, 8.2, 8.3_
## Model Inference Data Validation and Storage
- [ ] 5. Implement comprehensive inference data validation system
- Create InferenceDataValidator class for input validation
- Validate complete OHLCV dataframes for all required timeframes
- Check input data dimensions against model requirements
- Log missing components and prevent prediction on incomplete data
- _Requirements: 9.1, 9.2, 9.3, 9.4_
- [ ] 5.1. Implement input data validation for all models
- Create validation methods for CNN, RL, and future model inputs
- Validate OHLCV data completeness (300 frames for 1s, 1m, 1h, 1d)
- Validate COB data structure (±20 buckets, MA calculations)
- Raise specific validation errors with expected vs actual dimensions
- Ensure validation occurs before any model inference
- _Requirements: 9.1, 9.4_
- [ ] 5.2. Implement persistent inference history storage
- Create InferenceHistoryStore class for persistent storage
- Store complete input data packages with each prediction
- Include timestamp, symbol, input features, prediction outputs, confidence scores
- Store model internal states for cross-model feeding
- Implement compressed storage to minimize footprint
- _Requirements: 9.5, 9.6_
- [ ] 5.3. Implement inference history query and retrieval system
- Create efficient query mechanisms by symbol, timeframe, and date range
- Implement data retrieval for training pipeline consumption
- Add data completeness metrics and validation results in storage
- Handle storage failures gracefully without breaking prediction flow
- _Requirements: 9.7, 11.6_
## Inference-Training Feedback Loop Implementation
- [ ] 6. Implement prediction outcome evaluation system
- Create PredictionOutcomeEvaluator class
- Evaluate prediction accuracy against actual price movements
- Create training examples using stored inference data and actual outcomes
- Feed prediction-result pairs back to respective models
- _Requirements: 10.1, 10.2, 10.3_
- [ ] 6.1. Implement adaptive learning signal generation
- Create positive reinforcement signals for accurate predictions
- Generate corrective training signals for inaccurate predictions
- Retrieve last inference data for each model for outcome comparison
- Implement model-specific learning signal formats
- _Requirements: 10.4, 10.5, 10.6_
- [ ] 6.2. Implement continuous improvement tracking
- Track and report accuracy improvements/degradations over time
- Monitor model learning progress through feedback loop
- Create performance metrics for inference-training effectiveness
- Generate alerts for learning regression or stagnation
- _Requirements: 10.7_
## Inference History Management and Monitoring
- [ ] 7. Implement comprehensive inference logging and monitoring
- Create InferenceMonitor class for logging and alerting
- Log inference data storage operations with completeness metrics
- Log training outcomes and model performance changes
- Alert administrators on data flow issues with specific error details
- _Requirements: 11.1, 11.2, 11.3_
- [ ] 7.1. Implement configurable retention policies
- Create RetentionPolicyManager class
- Archive or remove oldest entries when limits are reached
- Prioritize keeping most recent and valuable training examples
- Implement storage space monitoring and alerts
- _Requirements: 11.4, 11.7_
- [ ] 7.2. Implement efficient historical data management
- Compress inference data to minimize storage footprint
- Maintain accessibility for training and analysis
- Implement efficient query mechanisms for historical analysis
- Add data archival and restoration capabilities
- _Requirements: 11.5, 11.6_
## Trading Executor Implementation
- [ ] 5. Design and implement the trading executor