Crime prediction using machine learning project

1. Machine learning in crime prediction

Keywords:
Machine learning, Artificial Intelligence, Feature selection, Crime prediction, Neural networks, Crime Analysis

            In this paper we aim to predict crimes the datasets they used and methods that are applied are numerous. They use a Systematic Literature Review (SLR) to collect and synthesize knowledge regarding ML based crime prediction and help both law enforcement authorities and scientists to mitigate and prevent future crime occurrences.  

2. Edge Assisted Crime Prediction and Evaluation Framework for Machine Learning Algorithms

Keywords:

Edge Computing, Impact Learning, Decision Tree, KNN, MLP

            In this paper we propose a crime prediction and evaluation framework for ML algorithms of the network edge. The analysis of four distinct crimes such as, murder, rapid trial, repression of women and children, and narcotics, validates the efficiency of the proposed framework. The total work is completed by selection, assessment, and implementation of ML and finally the crime prediction.

3. Predicting crime during or after psychiatric care: Evaluating machine learning for risk assessment using the Danish patient registries

Keywords:

Computational psychiatry, Precision psychiatry, Forensic psychiatry, Statistical risk assessment

            In this paper we develop a predictive model designed to identify psychiatric patients at risk of committing lead to a future forensic psychiatric treatment course. Four machine learning models (Logistic Regression, Random Forest, XGBoost and LightGBM) were applied over a range of socio demographic, judicial, and psychiatric variables. LightGBM algorithm gives better result.     

4. Empirical Analysis for Crime Prediction and Forecasting Using Machine Learning and Deep Learning Techniques

Keywords:

LSTM and ARIMA based crime prediction, analysis and forecast.

            This study applied different ML algorithms namely logistic regression, SVM, Naïve Bayes, KNN, decision tree, MLP, random forest, and eXtreme Gradient Boosting (XGBoost), and time series analysis by LSTM and autoregressive integrated moving average (ARIMA) model to better fit the crime data. The performance of LSTM for time series analysis was reasonably adequate.  

5. Design and Implementation of Crime Prediction Using Machine Learning Algorithm

Keywords:

Support vector machines, training, decision support systems, social networking (online), blogs, urban areas

            Predictive analytics based on Twitter can aid decision support systems. All messages are tagged in real time with their location and time of transmission which is completely free. Ml method is used to create intelligent method of effective criminal detection. To find the most accurate classifier, different classification methods were devised. The SVM performed better than other classifiers. 

6. Machine Learning Algorithms for Crime Prediction under Indian Penal Code

Keywords:

Random forest regression (RFR), Decision tree regression (DTR), Indian penal code (IPC), support vector regression (SVR), mean absolute percentage error (MAPE), Natural language processing (NLP)

            In this paper we  propose a data driven approach to draw insightful knowledge from Indian crime data. In this they used different regression models such as random forest regression (RFR), decision tree regression (DTR), multiple linear regression (MLR), simple linear regression (SLR), and support vector regression (SVR). These can predict different Indian Penal Code (IPC) and provide desired model. RFR predicts the best result.

7. An Empirical Analysis of Machine Learning Algorithms for Crime Prediction Using Stacked Generalization: An Ensemble Approach

Keywords:

Predictive models, data models, prediction algorithms, artificial neural networks

            This work proposes an efficient authentic method called assemble-stacking based crime prediction method (SBCPM) based on SVM algorithms for identifying the predictions of crime by implementing learning-based methods. The SVM is used to achieve domain specific configurations. The result implies that a model performs better result.

8. Crime Prediction Using Machine Learning and Deep Learning: A Systematic Review and Future Directions

Keywords:

Crime datasets, deep learning

            In this paper they provide access to the datasets used for crime prediction by researchers and analyzes prominent approaches applied in ML and DL to predict crime offering different trends and factors related tom criminal activities. By gaining a deeper understanding of crime prediction techniques, law enforcement agencies can develop strategies to prevent and respond to criminal activities. 

9. Crime Prediction and Forecasting using Machine Learning Algorithms

Keywords:

AdaBoost, crime forecasting, deep neural network, folium, future crime, random forest.

            In this paper ML will be used for crime forecasting. The Random Forest, K-Nearest-Neighbours, AdaBoost, and Neural Network are the ML models they used. We tested their models on Chicago Police Department’s CLEAR (Citizen Law Enforcement Analysis and Reporting) system. Neural Network gives the better result on accuracy. 

10. Prediction of crime rate in urban neighbourhoods based on machine learning

Keywords:

            In this paper GAN neural networks can be used to build a prediction model of city floor plans and corresponding crime distribution maps. We collect Philadelphia as the research sample and train the model for predicting the crime rate and when the training is completed a floor plan can be fed directly to the model. Using the untrained Philadelphia data as the test set, the model can accurately predict crime concentration.