fasttext upload

README.md

@@ -1,3 +1,135 @@
----
-license: apache-2.0
----
+---
+language: en
+license: apache-2.0
+tags:
+  - text-classification
+  - transaction-classification
+  - banking
+  - finance
+  - fasttext
+  - subword-embeddings
+datasets:
+  - mitulshah/transaction-categorization
+pipeline_tag: text-classification
+model-index:
+  - name: transaction-classifier-fasttext
+    results:
+      - task:
+          type: text-classification
+          name: Transaction Classification
+        metrics:
+          - name: Real-World Accuracy (Weighted)
+            type: accuracy
+            value: 0.557
+          - name: FastText-Only Accuracy
+            type: accuracy
+            value: 0.148
+          - name: Validation Accuracy
+            type: accuracy
+            value: 0.99
+---
+
+# Transaction Classifier — FastText (v2)
+
+A [FastText](https://fasttext.cc/) supervised model that classifies bank transaction strings into 10 budget categories using subword embeddings.
+
+This is **version 2** (Phase 2) in a progressive model development series. It introduced direction detection (credit vs debit) and a rules engine, but the FastText ML component itself suffered from severe Income category bias.
+
+## Model Details
+
+| Property | Value |
+|---|---|
+| Architecture | FastText supervised (subword n-grams) |
+| Task | Multi-class text classification (10 categories) |
+| Training samples | 3,597,859 |
+| Epochs | 10 |
+| Learning rate | 0.5 |
+| Word n-grams | 2 |
+| Embedding dim | 100 |
+| Subword range | 3-6 characters |
+| Loss | Softmax |
+| Format | `.bin` (FastText binary) |
+| Trained | 2026-03-28 |
+
+## Categories
+
+| ID | Category |
+|---|---|
+| 0 | Food & Dining |
+| 1 | Transportation |
+| 2 | Shopping & Retail |
+| 3 | Entertainment & Recreation |
+| 4 | Healthcare & Medical |
+| 5 | Utilities & Services |
+| 6 | Financial Services |
+| 7 | Income |
+| 8 | Government & Legal |
+| 9 | Charity & Donations |
+
+## Performance
+
+Evaluated on 505 unique real-world RBC transactions (3,113 weighted, 2019-2026).
+
+| Metric | Score |
+|---|---|
+| Real-world accuracy (weighted) | **55.7%** |
+| FastText-only accuracy | **14.8%** |
+| Direction detection accuracy | 100.0% |
+| Rules accuracy | 91.3% |
+| Validation accuracy | 99.0% |
+
+> **Key finding**: FastText achieves only 14.8% on unknown merchants due to subword n-gram overlap between the Income category in the training data and real merchant names. The model defaults to predicting Income for most inputs.
+
+## Usage
+
+```python
+import fasttext
+
+model = fasttext.load_model("fasttext_model.bin")
+
+result = model.predict("MCDONALD'S #12345 TORONTO ON")
+label = result[0][0].replace("__label__", "")
+confidence = result[1][0]
+
+print(f"Category: {label}, Confidence: {confidence:.3f}")
+```
+
+### Dependencies
+
+```
+fasttext
+```
+
+## Training Data
+
+- **Primary**: [mitulshah/transaction-categorization](https://huggingface.co/datasets/mitulshah/transaction-categorization) - full 3.6M records (gated dataset)
+- **Evaluation**: 505 real-world RBC bank transactions (2019-2026)
+
+## Key Contributions
+
+Despite the weak ML component, Phase 2 introduced two critical pipeline stages:
+1. **Direction Detection**: Rule-based credit/debit detection achieving 100% accuracy
+2. **Rules Engine**: YAML-based pattern matching for structural transaction patterns (91.3% accuracy on matched transactions)
+
+These pipeline stages carried forward into all subsequent versions.
+
+## Part of a Series
+
+See the [Transaction Classifier collection](https://huggingface.co/collections/maaz-zaidi/transaction-classifier) for all 7 model versions.
+
+## Limitations
+
+- Severe Income category bias (14.8% ML-only accuracy)
+- Subword n-gram features from Income training examples overlap with real merchant names
+- Superseded by SetFit (v3) which achieved 66.7% ML-only accuracy using pre-trained embeddings
+
+## Citation
+
+```bibtex
+@misc{zaidi2026txnclassifier,
+  title={Transaction Classifier: Multi-Stage Bank Transaction Categorization},
+  author={Maaz Zaidi},
+  year={2026},
+  url={https://huggingface.co/maaz-zaidi/transaction-classifier-fasttext}
+}
+```

fasttext_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37a4f623d92dbb89ec9bd52c66090839ee1460e028588a46766a957c361b29fe
+size 168572253

metadata.json

@@ -0,0 +1,13 @@
+{
+  "epoch": 10,
+  "lr": 0.5,
+  "word_ngrams": 2,
+  "min_count": 1,
+  "dim": 100,
+  "minn": 3,
+  "maxn": 6,
+  "loss": "softmax",
+  "bucket": 200000,
+  "train_samples": 3597859,
+  "trained_at": "2026-03-28T19:04:32.539634+00:00"
+}