Downloads · 30 days
0
GoldEgbuonu/ultimate-crime-predictor-rf-nn-xgb-nlp-gnn
ultimate-crime-predictor-rf-nn-xgb-nlp-gnn is a machine learning model from GoldEgbuonu. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This repository contains a final, trained StackingClassifier model for predicting crime categories.
Downloads · 30 days
0
Access
Public
Updated Nov 25, 2025
Repo size
65 MB
Likes
1
Public
Click a slice to open those files.
.skops16.2 MB · 100%
From the Hugging Face model README
This repository contains a final, trained StackingClassifier model for predicting crime categories.
This is a hybrid model with the following structure:
RandomForestClassifierMLPClassifier (Neural Network)XGBClassifierXGBClassifierThe model was trained on a feature set engineered from the Chicago Crime Dataset. This is a state-of-the-art feature set including:
Hour, DayOfWeekLatitude, Longitude, Location_Codeall-MiniLM-L6-v2 BERT model on the crime narrative.All features were scaled using StandardScaler.
Target Variable:
The model was evaluated using 5-fold stratified cross-validation. The final mean accuracy achieved was [99.55].
Load the model using skops.io.load(). IMPORTANT: To use this model for prediction, you must provide input data that has been processed with the exact same, complex feature engineering pipeline (including BERT and GNN embeddings) used during training. This model does not contain the pre-processing steps.