{"id":25840,"date":"2026-09-28T08:09:27","date_gmt":"2026-09-28T08:09:27","guid":{"rendered":"https:\/\/scientificassociation.org\/?post_type=journal-paper&#038;p=25840"},"modified":"2026-09-28T08:09:27","modified_gmt":"2026-09-28T08:09:27","slug":"xgboost-algorithm-for-a-spatial-point-process-intensity-estimation-based-on-logistic-loss","status":"publish","type":"journal-paper","link":"https:\/\/scientificassociation.org\/ar\/journal-paper\/xgboost-algorithm-for-a-spatial-point-process-intensity-estimation-based-on-logistic-loss\/","title":{"rendered":"XGBoost algorithm for a spatial point process intensity estimation based on logistic loss"},"content":{"rendered":"<div class=\"padding_abstract justify ltr\">Spatial point processes provide a framework for modeling the spatial distribution of events. Practice dictates that when the intensity depends on a number of covariates, parametric approaches often play a good role. Alternatively, nonparametric kernel-based estimation is also well established in the literature. However, complex relationships across covariates can make the parametric approaches less efficient, and, in addition, it is known that the performance of the nonparametric ones deteriorates when the number of covariates becomes large. Recently, the machine learning method XGBoost has been adapted for spatial point process intensity modeling, called XGBoostPP. This method, however, relies on a composite Poisson likelihood loss that requires both spatial discretization and generation of many dummy points, leading to high computational cost. In this study, we adapt XGBoostPP by considering a logistic loss to obtain a more computationally efficient algorithm. In addition, we also consider XGBoostPP with Poisson and logistic losses for point processes on linear networks. We demonstrate that XGBoostPP with logistic loss outperforms the one with Poisson loss through simulation studies, as well as applications in ecology, crime research, and traffic accident data.<\/div>\n","protected":false},"featured_media":25859,"template":"","meta":{"_acf_changed":false},"journal-name":[218],"paper-tag":[232,278,269],"class_list":["post-25840","journal-paper","type-journal-paper","status-publish","has-post-thumbnail","hentry","journal-name-cjmss","paper-tag-issue-2","paper-tag-november-2026","paper-tag-volume-5"],"acf":[],"_links":{"self":[{"href":"https:\/\/scientificassociation.org\/ar\/wp-json\/wp\/v2\/journal-paper\/25840","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/scientificassociation.org\/ar\/wp-json\/wp\/v2\/journal-paper"}],"about":[{"href":"https:\/\/scientificassociation.org\/ar\/wp-json\/wp\/v2\/types\/journal-paper"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/scientificassociation.org\/ar\/wp-json\/wp\/v2\/media\/25859"}],"wp:attachment":[{"href":"https:\/\/scientificassociation.org\/ar\/wp-json\/wp\/v2\/media?parent=25840"}],"wp:term":[{"taxonomy":"journal-name","embeddable":true,"href":"https:\/\/scientificassociation.org\/ar\/wp-json\/wp\/v2\/journal-name?post=25840"},{"taxonomy":"paper-tag","embeddable":true,"href":"https:\/\/scientificassociation.org\/ar\/wp-json\/wp\/v2\/paper-tag?post=25840"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}