HDLCP: Experimental Analysis and Development of Hybrid Deep Learning Methodology for Crime Scenario Assesment and Prediction

For a variety of reasons, prediction is utilized in nearly every industry. Many societal functions, like as crime prediction, are served by it. Data mining tools abound when it comes to traditional prediction. These approaches lack accuracy when dealing with new kinds of data and are somewhat outdated. They take a lot of time as well. In place of the antiquated data mining methods, Artificial Neural Networks function well. This study employs a Hybrid Deep Learning based Crime Prediction (HDLCP) model to forecast criminal activity; the model is then tested for accuracy using the Decision Tree (DT) technique for cross-validation. Using the current datasets, additional information is anticipated to be extracted. Criminal activity is perilous and pervasive, affecting societies all across the globe. Life expectancy, GDP growth, and national prestige are all impacted by crime rates. New methods and sophisticated technologies are required to enhance crime analytics in order to safeguard communities and ensure the safety of society as a whole. A number of crime probabilities in a certain area may be studied, detected, and predicted by the suggested approach. Using a number of data mining approaches, the author explains the many forms of criminal study and crime prediction.