Predictive Analytics for Project Risk Management Using Machine Learning  

作　　者：Sanjay Ramdas Bauskar Chandrakanth Rao Madhavaram Eswar Prasad Galla Janardhana Rao Sunkara Hemanth Kumar Gollangi Shravan Kumar Rajaram Sanjay Ramdas Bauskar;Chandrakanth Rao Madhavaram;Eswar Prasad Galla;Janardhana Rao Sunkara;Hemanth Kumar Gollangi;Shravan Kumar Rajaram(Pharmavite LLC, Los Angeles, CA, USA;Microsoft, Charlotte, NC, USA;AXS Group LLC, Los Angeles, CA, USA;TCS, Indianapolis, IN, USA)

机构地区：[1]Pharmavite LLC, Los Angeles, CA, USA [2]Microsoft, Charlotte, NC, USA [3]AXS Group LLC, Los Angeles, CA, USA [4]TCS, Indianapolis, IN, USA

出　　处：《Journal of Data Analysis and Information Processing》2024年第4期566-580,共15页数据分析和信息处理（英文）

摘　　要：Risk management is relevant for every project that which seeks to avoid and suppress unanticipated costs, basically calling for pre-emptive action. The current work proposes a new approach for handling risks based on predictive analytics and machine learning (ML) that can work in real-time to help avoid risks and increase project adaptability. The main research aim of the study is to ascertain risk presence in projects by using historical data from previous projects, focusing on important aspects such as time, task time, resources and project results. t-SNE technique applies feature engineering in the reduction of the dimensionality while preserving important structural properties. This process is analysed using measures including recall, F1-score, accuracy and precision measurements. The results demonstrate that the Gradient Boosting Machine (GBM) achieves an impressive 85% accuracy, 82% precision, 85% recall, and 80% F1-score, surpassing previous models. Additionally, predictive analytics achieves a resource utilisation efficiency of 85%, compared to 70% for traditional allocation methods, and a project cost reduction of 10%, double the 5% achieved by traditional approaches. Furthermore, the study indicates that while GBM excels in overall accuracy, Logistic Regression (LR) offers more favourable precision-recall trade-offs, highlighting the importance of model selection in project risk management.Risk management is relevant for every project that which seeks to avoid and suppress unanticipated costs, basically calling for pre-emptive action. The current work proposes a new approach for handling risks based on predictive analytics and machine learning (ML) that can work in real-time to help avoid risks and increase project adaptability. The main research aim of the study is to ascertain risk presence in projects by using historical data from previous projects, focusing on important aspects such as time, task time, resources and project results. t-SNE technique applies feature engineering in the reduction of the dimensionality while preserving important structural properties. This process is analysed using measures including recall, F1-score, accuracy and precision measurements. The results demonstrate that the Gradient Boosting Machine (GBM) achieves an impressive 85% accuracy, 82% precision, 85% recall, and 80% F1-score, surpassing previous models. Additionally, predictive analytics achieves a resource utilisation efficiency of 85%, compared to 70% for traditional allocation methods, and a project cost reduction of 10%, double the 5% achieved by traditional approaches. Furthermore, the study indicates that while GBM excels in overall accuracy, Logistic Regression (LR) offers more favourable precision-recall trade-offs, highlighting the importance of model selection in project risk management.

关 键 词：Predictive Analytics Project Risk Management DECISION-MAKING Data-Driven Strategies Risk Prediction Machine Learning Historical Data 

分 类 号：F42[经济管理—产业经济]