Artificial Intelligence Models for Crime Prediction in Urban Spaces

This work presents research based on evidence with neural networks for the development of predictive crime models, finding data sets used are focused historical data, classification, types theft at different scales space and time, counting conflict points in urban areas. Among some results, 81% precision is observed prediction Neural Network algorithm ranges occurrence a space-time point between 75% 90% using LSTM (Long-ShortSpace-Time). It also this review, that field justice, systems intelligent technologies have been incorporated, to carry out activities such as legal advice, decisionmaking, national international cooperation fight against crime, police intelligence services, control facial recognition, search processing information, surveillance, definition criminal models under criteria records, history incidents regions city, location force, established businesses, etc., is, they make predictions context public security justice. Finally, ethical considerations principles related developments artificial presented, which seek guarantee aspects privacy, privacy impartiality algorithms, well avoid biases or distinctions. Therefore, it concluded scenario development, research, operation solutions contexts, viable necessary Mexico, representing an innovative effective alternative contributes attention insecurity, since according indices intentional homicides, rates organized violence firearms, statistics from INEGI, Global Peace Index Government remain increase.