机构名称：
¥ 2.0
Dimension Code Count % Example Computational Inferential Statistics Statistical tests (ST) 6 10.3% [131] Method Generalized Linear Models (GLM) 35 60.3% [80] Machine Learning Supervised Learning (SUP) 19 32.8% [21] Unsupervised Learning (USUP) 2 3.4% [48] Natural Language Processing (NLP) 1 1.7% [28] Deep Learning Neural Network (NN) 5 8.6% [79]优化混合整数编程（MIP）7 12.1％[103]网络分析（NA）8 13.8％[144]系统仿真（SS）7 12.1％[39]启发式算法（HA）2 3.4％[60]预测者人口统计学个人人口统计学37 63.8％63.8％[45]差异[45]量化家庭构图最新的房屋构成11 199.0.11 199.11 [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118] [118） Housing 22 37.9% [132] Housing History 22 37.9% [17] Service usage history 25 43.1% [43] Housing/service needs 11 19.0% [59] Services Service provider information 20 34.5% [58] Health Health 36 62.1% [14] Person Needs/Risks Prior victimization/trauma 20 34.5% [6] Involvement with criminal justice 16 27.6% [33] Risk assessment 11 19.0% [83]行为特征2 3.4％[143]关系强度7 12.1％[120]社交网络分析8 13.8％[142]结果结果资源分配（RES）15 25.9％[66]变量变量的风险经历无家可归的危害的风险（危害）8 13.8％[127] [127] [127] [127]影响识别（ID）7 12.1 12.12.1 124 [124] [124] [124] [124] [124] [124] [124] [102]无家可归的风险（风险）23 39.7％[64]表2。通过研究问题组织的代码手册（我们的57篇论文中的n = 58算法显示的百分比）
无家可归研究中以人为中心的算法回顾
主要关键词
相关文件推荐
