business-issue-allocation-classifier

Business Issue Allocation Classifier

A text classifier that maps a natural language business problem description to the most likely data engineering solution category.

<div style="background:#f6f8fa; border-left:5px solid #f5b400; border-radius:8px; padding:16px 20px; margin:16px 0;"> <h3 style="margin:0 0 4px 0; color:#c47f00;">💡 How to state a business issue</h3> <p style="margin:0 0 12px 0; color:#444;">Write 1-2 sentences the model can classify reliably:</p> <ol style="margin:0 0 12px 20px; padding:0; color:#333;"> <li style="margin-bottom:6px;"><strong style="color:#2b6cb0;">Describe the data situation</strong> - what systems and data you have, and why the need is hard to meet. Don't just express frustration ("I have no idea what's happening").</li> <li style="margin-bottom:6px;"><strong style="color:#2b6cb0;">State the desired outcome</strong> - the concrete result or constraint you want ("one consolidated monthly report", "alerts within milliseconds").</li> <li style="margin-bottom:6px;"><strong style="color:#2b6cb0;">Describe the need, not the solution</strong> - don't name or negate a category; "we don't have a data warehouse" leaks the answer and confuses the model. Let it infer the label.</li> <li style="margin-bottom:6px;"><strong style="color:#2b6cb0;">Keep it to one issue</strong> - one problem per description, not several bundled together.</li> </ol> <p style="margin:0 0 6px 0; color:#b00020;"><strong>❌ Weak:</strong> "I have no idea what's happening with our finances. I don't see profits per category. We don't have a data warehouse."</p> <p style="margin:0; color:#1a7f37;"><strong>✅ Strong:</strong> "Our finance data is spread across several systems and we can't get profit broken down by product category. We need one consolidated place with monthly profit-by-category figures for management reporting."</p> </div>

Model Details

• Classifier: SVM (Support Vector Machine)
• Embedding model: sentence-transformers/all-mpnet-base-v2
• Classes: 9 (stream_processing, etl_pipeline, data_warehouse, data_lake, api_integration, ml_feature_store, data_caching, data_governance, data_quality)
• Accuracy: 88.2%
• Macro F1: 88.4%

How to Use

Clone the full project from GitHub and run:

from src.inference import Predictor
predictor = Predictor()
result = predictor.predict("We need to detect fraud before transactions are approved.")
print(result["predicted_label"])

Label distribution in dataset

The dataset contains 465 labeled examples across 9 solution categories (label_it). The classes are fairly balanced, ranging from 39 to 63 examples per category.

NOTES FROM TESTING

The model favoured label "data_governance" in these cases: I have no idea, what is happening with our finances. I don't see anywhere profits per category. We don't have data warehouse.

Dataset

dianamikova/business-issue-allocation

GitHub

github.com/dianamikova/business-issue-allocation