# asebaie/triple-i architecture

> Architecture diagram of the GitHub repository asebaie/triple-i, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-06). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/asebaie/triple-i
- Repository: https://github.com/asebaie/triple-i

## Overview

Triple-I is a collection of independent data-science and machine-learning projects, not one application with a shared runtime workflow. The README documents each project’s goal and, for some, its data or prediction task; no source excerpts are available to confirm internal implementation or calls. The graph therefore shows documented project capabilities and inputs only, without inferring internal stages.

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_bank["Banking AI"]
  node_alfa["Income and recommendations"]
end

subgraph group_recommend["Recommendations"]
  node_netflix["Autoencoder recommender"]
end

subgraph group_molecular["Molecular ML"]
  node_cocrystal["Cocrystal classifier"]
end

subgraph group_spectral["Spectral ML"]
  node_spectral["Hyperspectral classification"]
end

subgraph group_search["Search Analytics"]
  node_nornikel["Hybrid structured search"]
end

subgraph group_matching["Product Matching"]
  node_e_cup["Product-pair classifier"]
end

node_netflix_data[("Netflix Prize data")]
node_smiles["Molecular SMILES pairs"]
node_ozon["Ozon product-card pairs"]

node_netflix_data -->|"trains on"| node_netflix
node_smiles -->|"classifies pairs"| node_cocrystal
node_ozon -->|"classifies pairs"| node_e_cup

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_alfa toneBlue
class node_netflix,node_netflix_data toneAmber
class node_cocrystal toneMint
class node_spectral toneRose
class node_nornikel,node_smiles,node_ozon toneIndigo
class node_e_cup toneTeal
```

## Components

### Banking AI

- **Income and recommendations**

### Recommendations

- **Autoencoder recommender**

### Molecular ML

- **Cocrystal classifier**

### Spectral ML

- **Hyperspectral classification**

### Search Analytics

- **Hybrid structured search**

### Product Matching

- **Product-pair classifier**

### Other components

- **Netflix Prize data**
- **Molecular SMILES pairs**
- **Ozon product-card pairs**

## Connections

- Netflix Prize data → Autoencoder recommender: trains on (evidence: `README.md`)
- Molecular SMILES pairs → Cocrystal classifier: classifies pairs (evidence: `README.md`)
- Ozon product-card pairs → Product-pair classifier: classifies pairs (evidence: `README.md`)
