README.md

---
license: apache-2.0
library_name: numpy
tags:
  - fraud-detection
  - tabular-classification
  - tiny-model
  - edge-ai
  - no-gpu
  - numpy
  - real-time
  - explainable-ai
  - analytic-gradients
datasets:
  - custom
metrics:
  - accuracy
  - latency
model-index:
  - name: KestrelNet Fraud Classifier
    results:
      - task:
          type: tabular-classification
          name: Fraud Detection
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.916
          - name: Inference Latency
            type: latency
            value: 0.005ms
          - name: Parameters
            type: params
            value: 1059
pipeline_tag: tabular-classification
---

# KestrelNet — 1,059-Parameter Fraud Classifier

A fully-connected neural network for real-time transaction fraud detection. Built from scratch with **pure NumPy** — no PyTorch, no TensorFlow, no ONNX runtime. The entire model fits in a single tweet.

## Why This Exists

Most fraud detection models are overbuilt. We wanted to find the floor: what's the smallest model that still works? Turns out, **1,059 parameters** gets you to 91.6% accuracy with sub-microsecond inference on commodity hardware.

## Performance

| Metric | Value |
|---|---|
| Accuracy | 91.6% |
| Parameters | 1,059 |
| Model size | 8.3 KB |
| Inference latency | ~5 μs (CPU) |
| Throughput | ~190,000 inferences/sec |
| Dependencies | NumPy only |

For context, a single GPT-2 attention head has more parameters than this entire model.

## Architecture

```
Input (14 features) → Dense(32, ReLU) → Dense(16, ReLU) → Dense(3, Softmax)
```

Three layers. No batch norm, no attention, no residual connections. Just matrix multiplies and ReLU.

**Training** uses analytic backpropagation — full gradient computation without autograd. Every partial derivative is derived by hand and implemented directly. This makes the training loop ~10x faster than equivalent PyTorch code for models this size.

### GullNet Variant

We also offer a **GullNet** variant that replaces standard dot products with multivector products, giving the network native access to rotations, reflections, and scaling in a single operation — useful when feature interactions have geometric structure. The GullNet variant has more parameters but can capture complex feature relationships that FC nets miss.

## Input Features

The model expects a 14-dimensional normalized feature vector:

| Index | Feature | Normalization |
|---|---|---|
| 0 | `amount_vs_avg` | Transaction amount / 90-day average |
| 1-2 | `hour_sin`, `hour_cos` | Cyclical encoding of transaction hour |
| 3-4 | `day_sin`, `day_cos` | Cyclical encoding of day of week |
| 5 | `location_delta` | Std deviations from usual location |
| 6 | `velocity_1h` | Transactions in past hour / 10, clipped |
| 7 | `velocity_24h` | Transactions in past 24h / 30, clipped |
| 8 | `merchant_risk` | Merchant category risk score [0-1] |
| 9 | `international` | Cross-border transaction (0/1) |
| 10 | `card_present` | Physical card used (0/1) |
| 11 | `device_match` | Known device (0/1) |
| 12 | `account_age_norm` | Account age / 3650 days |
| 13 | `prev_fraud_score` | Historical fraud rate [0-1] |

## Output

Three-class softmax: `[legitimate, review, fraudulent]`

Threshold modes control the decision boundary:
- **Standard** — Balanced precision/recall
- **Conservative** — Flags more transactions (fewer false negatives)
- **Strict** — Flags fewer (fewer false positives)

## Benchmarks — Public Datasets

KestrelNet and GoshawkNet evaluated on public Kaggle datasets. All results independently reproducible.

| Dataset | Task | Accuracy | F1 / AUC | Params | Latency | Source |
|---|---|---|---|---|---|---|
| **ECG Heartbeat** (MIT-BIH) | 5-class arrhythmia | 97.2% | F1 0.853 | 12,756 | 56μs | [shayanfazeli/heartbeat](https://kaggle.com/datasets/shayanfazeli/heartbeat) |
| **EEG Emotions** | 3-class sentiment | 99.1% | F1 0.991 | 163,788 | 1.3ms | [birdy654/eeg-brainwave-dataset-feeling-emotions](https://kaggle.com/datasets/birdy654/eeg-brainwave-dataset-feeling-emotions) |
| **EEG Eye State** | Binary open/closed | 94.2% | AUC 0.986 | 1,576 | 17μs | [robikscube/eye-state-classification-eeg-dataset](https://kaggle.com/datasets/robikscube/eye-state-classification-eeg-dataset) |
| **Seizure Prediction** (Bonn) | Binary seizure | 97.1% | AUC 0.988 | 12,072 | — | [harunshimanto/epileptic-seizure-recognition](https://kaggle.com/datasets/harunshimanto/epileptic-seizure-recognition) |
| **HAR Smartphones** (UCI) | 6-class activity | 94.9% | F1 0.949 | 15,416 | 70μs | [uciml/human-activity-recognition-with-smartphones](https://kaggle.com/datasets/uciml/human-activity-recognition-with-smartphones) |
| **Fraud Detection** | 3-class fraud | 91.6% | — | 1,059 | 5μs | Proprietary |

All benchmarks run on CPU. No GPU required. Pure NumPy inference.

### Parameter Efficiency

For comparison, typical models on these datasets:

| Dataset | Typical CNN/LSTM | KestrelNet/GoshawkNet | Reduction |
|---|---|---|---|
| ECG Heartbeat | 500K–2M params | 12,756 | **40–160x smaller** |
| EEG Emotions | 1M+ params | 163,788 | **6x smaller** |
| EEG Eye State | 100K+ params | 1,576 | **63x smaller** |
| HAR Smartphones | 200K–1M params | 15,416 | **13–65x smaller** |

## Quick Start

```python
import numpy as np
from kestrelnet import KestrelNet

model = KestrelNet.from_pretrained("kestrelnet/fraud-classifier")
scores = model.predict([1.2, 14, 2, 0.1, 1, 3, 0.05, False, True, True, 365, 0.0])
# {'legitimate': 0.983, 'review': 0.017, 'fraudulent': 0.000}
```

## Intended Use

- Real-time fraud screening for payment processors
- Pre-filter before heavier ML models (ensemble first stage)
- Edge deployment where GPU is unavailable
- Educational reference for from-scratch neural networks

## Limitations

- Trained on synthetic/proprietary data — accuracy on your distribution will vary
- 14 fixed features — cannot ingest raw transaction logs directly
- No sequence modeling — treats each transaction independently
- Small capacity means it cannot memorize complex fraud patterns

## How to Cite

```bibtex
@misc{kestrelnet2026,
  title={KestrelNet: Sub-Kilobyte Neural Fraud Classifier},
  author={KestrelNet Team},
  year={2026},
  url={https://huggingface.co/kestrelnet/fraud-classifier}
}
```