I am a postdoctoral researcher working currently on two primary areas of research. The first is a continuation of my PhD work, where I develop boosting survival models to predict the lifetimes of rechargeable batteries based on sensor data. This research is aimed at understanding how batteries behave over time and providing insights into their longevity. By using specific boosting models, we can not only make accurate predictions but also extract valuable information from the data itself. I find this work particularly engaging because boosting is a state-of-the-art method in data science, and the subject of batteries is critical for advancements in energy storage and sustainability.
My second research area is more closely tied to my current postdoctoral project and involves the usage of likelihood ratio test statistics in experimental particle physics. In this field, researchers often rely on Wilks' theorem to guide their analysis when searching for new particles, such as dark matter or new types of bosons. Wilks' theorem tells us that, under regularity conditions, the likelihood ratio test statistics follow a chi-squared distribution asymptotically. However, in practice, these ideal conditions are often not met, which can impact the distribution of the test statistics. My research focuses on exploring how these deviations affect the results, particularly in terms of particle discovery. This work combines the theoretical side of statistics with a direct application to one of the most exciting areas of modern physics.