
This study investigates the use of Recurrent Neural Networks (RNNs) and Long ShortTerm Memory (LSTM) networks to predict crime patterns in Bucaramanga, Colombia. A temporal approach is presented, which starts by splitting the city into 17 communes. Using a dataset of robbery incidents from 2016 to January 2023, we developed individual time series models for each commune. Then, we used the Root Mean Squared Error (RMSE) as the evaluation metric in these regression tasks. The LSTM models consistently outperformed both the RNN and ARIMA models, a classical methodology for time series prediction, achieving lower RMSE scores. The LSTM model yielded an average RMSE of 2.875 (with a standard deviation of 1.657), which is considerably lower than that obtained by the RNN model 3.101 (1.82) and the ARIMA model 3.428 (2.57). These results show that LSTM better captures the complex temporal dependencies in the data. Future work should explore hybrid models and the incorporation of additional data sources to enhance predictive accuracy further.