Improved Crime Prediction using Hybrid Neural Architecture Search together with Hyper-parameter Tuning

Different parts of the world have recorded an escalating number of criminal incidents, burdened the judicial system, and adversely impacted national security and economic development. Accurate crime prediction is crucial for law enforcement agencies to proactively prevent criminal activity and allocate resources effectively. The existing methods often address architecture design and hyperparameter tuning as separate processes. We present a combination of neural architecture search and hyperparameter tuning for enhanced crime prediction. The study method achieved automation of architecture discovery and fine-tuning of hyperparameters by utilizing Neural Architecture Search (NAS) to explore a vast range of neural network architectures for crime prediction and optimizing the hyperparameters of the discovered architecture for peak performance in binary crime prediction, respectively. The study used three datasets: criminal cases dataset (self-collected dataset), Vancouver crime data, and Austin Crime Data. The criminal cases dataset is extracted from a confidential database from certain countries, focusing on sensitive parts of those countries. The Vancouver crime and Austine Crime datasets were sourced from the Kaggle website. The study considered the robust rank aggregation (RRA) feature selection method to rank and select the best features for predicting crime behavior in some countries. The chosen features using the robust rank aggregation included current position, age range, month, prisoner condition, and identified/unidentified (ide/Unide). The study found that the Neural Architecture Search (NAS+) hyperparameter tuning model is the best approach to predicting crime. The model produced accuracy scores equal to 89.29\% (AUC-ROC=94.82\% and recall=64.54\%), 60.37\% (AUC-ROC=50.00\% and recall=100.00\%), and 86.68\% (AUC_ROC=65.40\% and recall=100.00\%) for the criminal cases data, Vancouver crime data, and Austine crime data, respectively.