基于蒙特卡洛模擬和掙值分析的項(xiàng)目完工預(yù)測(cè)優(yōu)化

摘要： 基于掙值分析和風(fēng)險(xiǎn)管理,通過(guò)蒙特卡洛模擬獲取項(xiàng)目數(shù)據(jù),使用二次判別分析、隨機(jī)森林和支持向量機(jī)進(jìn)行模型學(xué)習(xí)和完工預(yù)測(cè)是項(xiàng)目控制的有效方法之一。在現(xiàn)有研究基礎(chǔ)上,考慮項(xiàng)目執(zhí)行過(guò)程中的剩余工作時(shí)間、剩余工作費(fèi)用和風(fēng)險(xiǎn),分別應(yīng)用現(xiàn)有研究方法、梯度提升樹和人工神經(jīng)網(wǎng)絡(luò)進(jìn)行模型學(xué)習(xí),利用嵌套交叉驗(yàn)證進(jìn)行模型選擇和模型評(píng)估。研究結(jié)果表明,優(yōu)化后的方法顯著提升項(xiàng)目完工預(yù)測(cè)的準(zhǔn)確率。
Based on the analysis of the earned value and the risk management, the project data is acquired through the Monte Carlo simulation, and the model learning and the completion prediction by using the quadratic discriminant analysis, the random forest and the support vector machine are one of the effective methods of the project control. On the basis of existing research, this paper takes into account the residual working time, the remaining work cost and the risk in the execution of the project, and applies the existing research methods, the gradient lifting tree and the artificial neural network to study the model, and makes model selection and model evaluation by using the nested cross validation. The results show that the optimized method can improve the accuracy of project completion prediction.