# michaeldrah/pinn_ewc_dissertation architecture

> Architecture diagram of the GitHub repository michaeldrah/pinn_ewc_dissertation, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-16). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/michaeldrah/pinn_ewc_dissertation
- Repository: https://github.com/michaeldrah/pinn_ewc_dissertation

## Overview

This repository is a financial time-series modeling research project, organized around notebooks and persisted datasets, models, and evaluation outputs. Its visible stages include data acquisition and exploration, preprocessing and feature work, physics-informed modeling, continual-learning experiments, backtesting, and evaluation. The tree identifies these components but no README or source excerpts document calls or data transfers, so the graph does not assert relationships between them.

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_research["Research notebooks"]
  node_download["Data download"]
  node_exploration["Raw data exploration"]
  node_eda["Dissertation EDA"]
  node_preprocessing["Preprocessing"]
  node_features["Feature engineering"]
  node_selection["Feature selection"]
  node_pinn["PINN modeling"]
  node_physics_loss["Physics-informed loss"]
  node_ewc["EWC module"]
  node_adaptive_ewc["Adaptive finance EWC"]
  node_backtesting["Backtesting"]
  node_evaluation["Evaluation"]
end

subgraph group_data["Market data"]
  node_raw_data[("Raw market data")]
  node_processed_data[("Preprocessed data")]
  node_feature_data[("Feature datasets")]
  node_model_ready_data[("Model-ready datasets")]
end

subgraph group_models["Model artifacts"]
  node_model_artifacts[("Trained model artifacts")]
end

subgraph group_results["Evaluation outputs"]
  node_prediction_outputs[("Predictions")]
  node_metric_outputs[("Metrics")]
  node_backtest_outputs[("Backtest results")]
  node_research_tables[("Research tables")]
end

node_researcher(("Researcher"))

click node_download "https://github.com/michaeldrah/pinn_ewc_dissertation/blob/main/notebooks/02_data_download.ipynb"
click node_exploration "https://github.com/michaeldrah/pinn_ewc_dissertation/blob/main/notebooks/03_raw_data_exploration.ipynb"
click node_eda "https://github.com/michaeldrah/pinn_ewc_dissertation/blob/main/notebooks/03a_dissertation_eda.ipynb"
click node_preprocessing "https://github.com/michaeldrah/pinn_ewc_dissertation/blob/main/notebooks/04_preprocessing.ipynb"
click node_features "https://github.com/michaeldrah/pinn_ewc_dissertation/blob/main/notebooks/05_feature_engineering.ipynb"
click node_selection "https://github.com/michaeldrah/pinn_ewc_dissertation/blob/main/notebooks/05a_feature_selection.ipynb"
click node_pinn "https://github.com/michaeldrah/pinn_ewc_dissertation/blob/main/notebooks/06_pinn_model.ipynb"
click node_physics_loss "https://github.com/michaeldrah/pinn_ewc_dissertation/blob/main/notebooks/06a%20%E2%80%93%20Physics-Informed%20Loss.ipynb"
click node_ewc "https://github.com/michaeldrah/pinn_ewc_dissertation/blob/main/notebooks/07_ewc_module.ipynb"
click node_adaptive_ewc "https://github.com/michaeldrah/pinn_ewc_dissertation/blob/main/notebooks/07a_adaptive_finance_informed_ewc.ipynb"
click node_backtesting "https://github.com/michaeldrah/pinn_ewc_dissertation/blob/main/notebooks/08_backtesting.ipynb"
click node_evaluation "https://github.com/michaeldrah/pinn_ewc_dissertation/blob/main/notebooks/09_evaluation.ipynb"
click node_raw_data "https://github.com/michaeldrah/pinn_ewc_dissertation/tree/main/data/raw"
click node_processed_data "https://github.com/michaeldrah/pinn_ewc_dissertation/tree/main/data/processed"
click node_feature_data "https://github.com/michaeldrah/pinn_ewc_dissertation/tree/main/data/features"
click node_model_ready_data "https://github.com/michaeldrah/pinn_ewc_dissertation/tree/main/data/model_ready"
click node_model_artifacts "https://github.com/michaeldrah/pinn_ewc_dissertation/tree/main/models"
click node_prediction_outputs "https://github.com/michaeldrah/pinn_ewc_dissertation/tree/main/outputs/predictions"
click node_metric_outputs "https://github.com/michaeldrah/pinn_ewc_dissertation/tree/main/outputs/metrics"
click node_backtest_outputs "https://github.com/michaeldrah/pinn_ewc_dissertation/tree/main/outputs/backtesting"
click node_research_tables "https://github.com/michaeldrah/pinn_ewc_dissertation/tree/main/tables"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_download,node_exploration,node_eda,node_preprocessing,node_features,node_selection,node_pinn,node_physics_loss,node_ewc,node_adaptive_ewc,node_backtesting,node_evaluation toneBlue
class node_raw_data,node_processed_data,node_feature_data,node_model_ready_data toneAmber
class node_model_artifacts toneMint
class node_prediction_outputs,node_metric_outputs,node_backtest_outputs,node_research_tables toneRose
class node_researcher toneIndigo
```

## Components

### Research notebooks

- [Data download](https://github.com/michaeldrah/pinn_ewc_dissertation/blob/main/notebooks/02_data_download.ipynb): `notebooks/02_data_download.ipynb`
- [Raw data exploration](https://github.com/michaeldrah/pinn_ewc_dissertation/blob/main/notebooks/03_raw_data_exploration.ipynb): `notebooks/03_raw_data_exploration.ipynb`
- [Dissertation EDA](https://github.com/michaeldrah/pinn_ewc_dissertation/blob/main/notebooks/03a_dissertation_eda.ipynb): `notebooks/03a_dissertation_eda.ipynb`
- [Preprocessing](https://github.com/michaeldrah/pinn_ewc_dissertation/blob/main/notebooks/04_preprocessing.ipynb): `notebooks/04_preprocessing.ipynb`
- [Feature engineering](https://github.com/michaeldrah/pinn_ewc_dissertation/blob/main/notebooks/05_feature_engineering.ipynb): `notebooks/05_feature_engineering.ipynb`
- [Feature selection](https://github.com/michaeldrah/pinn_ewc_dissertation/blob/main/notebooks/05a_feature_selection.ipynb): `notebooks/05a_feature_selection.ipynb`
- [PINN modeling](https://github.com/michaeldrah/pinn_ewc_dissertation/blob/main/notebooks/06_pinn_model.ipynb): `notebooks/06_pinn_model.ipynb`
- [Physics-informed loss](https://github.com/michaeldrah/pinn_ewc_dissertation/blob/main/notebooks/06a%20%E2%80%93%20Physics-Informed%20Loss.ipynb): `notebooks/06a – Physics-Informed Loss.ipynb`
- [EWC module](https://github.com/michaeldrah/pinn_ewc_dissertation/blob/main/notebooks/07_ewc_module.ipynb): `notebooks/07_ewc_module.ipynb`
- [Adaptive finance EWC](https://github.com/michaeldrah/pinn_ewc_dissertation/blob/main/notebooks/07a_adaptive_finance_informed_ewc.ipynb): `notebooks/07a_adaptive_finance_informed_ewc.ipynb`
- [Backtesting](https://github.com/michaeldrah/pinn_ewc_dissertation/blob/main/notebooks/08_backtesting.ipynb): `notebooks/08_backtesting.ipynb`
- [Evaluation](https://github.com/michaeldrah/pinn_ewc_dissertation/blob/main/notebooks/09_evaluation.ipynb): `notebooks/09_evaluation.ipynb`

### Market data

- [Raw market data](https://github.com/michaeldrah/pinn_ewc_dissertation/tree/main/data/raw): `data/raw`
- [Preprocessed data](https://github.com/michaeldrah/pinn_ewc_dissertation/tree/main/data/processed): `data/processed`
- [Feature datasets](https://github.com/michaeldrah/pinn_ewc_dissertation/tree/main/data/features): `data/features`
- [Model-ready datasets](https://github.com/michaeldrah/pinn_ewc_dissertation/tree/main/data/model_ready): `data/model_ready`

### Model artifacts

- [Trained model artifacts](https://github.com/michaeldrah/pinn_ewc_dissertation/tree/main/models): `models`

### Evaluation outputs

- [Predictions](https://github.com/michaeldrah/pinn_ewc_dissertation/tree/main/outputs/predictions): `outputs/predictions`
- [Metrics](https://github.com/michaeldrah/pinn_ewc_dissertation/tree/main/outputs/metrics): `outputs/metrics`
- [Backtest results](https://github.com/michaeldrah/pinn_ewc_dissertation/tree/main/outputs/backtesting): `outputs/backtesting`
- [Research tables](https://github.com/michaeldrah/pinn_ewc_dissertation/tree/main/tables): `tables`

### Other components

- **Researcher**
