Machine Learning-Based Bug Handling in Large-Scale Software Development

The random forest algorithm belongs to the class of ensemble learning methods that are embarassingly parallel, i.e., the learning task can be straightforwardly divided into

Although our results did not support H2, the fact that the members of the studied teams were involved in different work items at the same time, and every next task

This paper reports the findings of a case study conducted at Ericsson AB, Sweden on the challenges associated with technical dependencies, and communicating technical

As discussed in the Introduction, the efficient operation of a data center requires planning and coordinating the use of resources across a variety technologies and

2) Experiments with the non-smooth cost: We observed good performance on the non-smooth cost function too (Figure 6), though it was not as remarkable as the smooth cost. BO with

Configuration files and configuration switches directly in the source code provide the means to derive specific products from the product line of Sony Ericsson.. To

Is it feasible to replace human bug assignment and fault localization with machine learning techniques in large scale industry SW development projects.. RQ2: Which machine

Each unique input created a representation in the Latent Space (dense layers) which we treated as clusters. Next, we fed in call stack from the testing set and observed where in