Mapping the Risk Terrain for Crime Using Machine Learning
Mapping the Risk Terrain for Crime Using Machine Learning
复制标题
DOI：
10.1007/s10940-020-09457-7
复制
发表时间：
2020-01
影响因子：
3.6
通讯作者：
A. Wheeler;W. Steenbeek
中科院分区：
文献类型：
--
作者：
A. Wheeler;W. Steenbeek
ObjectivesWe说明了机器学习算法，随机森林，可以提供准确的长期预测犯罪在微观地方相对于其他流行的技术。我们还展示了模型摘要的最新进展如何有助于打开随机森林的“黑匣子”，大大提高其interpretability.MethodsWe生成的抢劫案在达拉斯在200 200英尺的网格单元格，允许犯罪发电机和人口因素在整个研究区域的空间变化的关联的长期犯罪预测。然后，我们将展示如何使用可解释的模型摘要促进理解该模型的内部workings.ResultsWe发现，随机森林大大优于风险地形模型和核密度估计预测未来的犯罪，使用不同的预测精度的措施，但只有轻微优于使用事先计数的犯罪。我们发现不同的因素，预测犯罪是高度非线性的，并随空间而变化。ConclusionsWe展示了如何使用黑盒机器学习模型可以提供准确的基于微放置的犯罪预测，但仍然被解释的方式，促进理解为什么一个地方被预测为有风险。
ObjectivesWe illustrate how a machine learning algorithm, Random Forests, can provide accurate long-term predictions of crime at micro places relative to other popular techniques. We also show how recent advances in model summaries can help to open the ‘black box’ of Random Forests, considerably improving their interpretability.MethodsWe generate long-term crime forecasts for robberies in Dallas at 200 by 200 feet grid cells that allow spatially varying associations of crime generators and demographic factors across the study area. We then show how using interpretable model summaries facilitate understanding the model’s inner workings.ResultsWe find that Random Forests greatly outperform Risk Terrain Models and Kernel Density Estimation in terms of forecasting future crimes using different measures of predictive accuracy, but only slightly outperform using prior counts of crime. We find different factors that predict crime are highly non-linear and vary over space.ConclusionsWe show how using black-box machine learning models can provide accurate micro placed based crime predictions, but still be interpreted in a manner that fosters understanding of why a place is predicted to be risky.