Search

Knowledge management and predictive analytics are considered to be unusual partners in today's technology. However, they can be very good tools that would solve current problems in valuing data. Predictive analytics has now become one of the forecasting tools that is of huge help in information management. Its application in IT project development risk management is very important, where a lot of raw data is involved with risk analysis and prediction. The use of IT project risk management as supported by knowledge management KM will help increase the success rate of IT projects. Knowledge management will bring about additional value to the data needed. This paper presents the usage of KM and predictive analytics to increase the success ratings of projects by predicting the risks that might happen during project development. It explores how KM and predictive analytics can identify risks in IT project development and give recommendations in evaluating the risks that could affect successful completion of IT projects. Mia Torres-Dela Cruz | Subashini A/P Ganapathy | Noor Zuhaili Binti Mohd Yasin "Knowledge Management and Predictive Analytics in IT Project Risks" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Special Issue | International Conference on Advanced Engineering and Information Technology , November 2018, URL: https://www.ijtsrd.com/papers/ijtsrd19142.pdf

International audience; In many optimal design searches, the function to optimise is a simulator that is computationally expensive. While current High Performance Computing (HPC) methods are not able to solve such problems efficiently, parallelism can be coupled with approximate models (surrogates or meta-models) that imitate the simulator in timely fashion to achieve better results. This combined approach reduces the number of simulations thanks to surrogate use whereas the remaining evaluations are handled by supercomputers. While the surrogates' ability to limit computational times is very attractive, integrating them into the over-arching optimization process can be challenging. Indeed, it is critical to address the major trade-off between the quality (precision) and the efficiency (execution time) of the resolution. In this article, we investigate Evolution Controls (ECs) which are strategies that define the alternation between the simulator and the surrogate within the optimization process. We propose a new EC based on the prediction uncertainty obtained from Monte Carlo Dropout (MCDropout), a technique originally dedicated to quantifying uncertainty in deep learning. Investigations of such uncertainty-aware ECs remain uncommon in surrogate-assisted evolutionary optimization. In addition, we use parallel computing in a complementary way to address the high computational burden. Our new strategy is implemented in the context of a pioneering application to Tuberculosis Transmission Control. The reported results show that the MCDropout-based EC coupled with massively parallel computing outperforms strategies previously proposed in the field of surrogate-assisted optimization.