Due to the continuous change in operational data, AIOps solutions suffer from performance degradation over time. Although periodic retraining is the state-of-the-art technique to preserve the failure prediction AIOps models' performance over time, this technique requires a considerable amount of labeled data to retrain. In AIOps obtaining label data is expensive since it requires the availability of domain experts to intensively annotate it. In this paper, we present McUDI, a model-centric unsupervised degradation indicator that is capable of detecting the exact moment the AIOps model requires retraining as a result of changes in data. We further show how employing McUDI in the maintenance pipeline of AIOps solutions can reduce the number of samples that require annotations with 30k for job failure prediction and 260k for disk failure prediction while achieving similar performance with periodic retraining.

Small and medium enterprises (SME) are crucial for economy and have a higher exposure rate to default than large corporates. In this work, we address the problem of predicting the default of an SME. Default prediction models typically only consider the previous financial situation of each analysed company. Thus, they do not take into account the interactions between companies, which could be insightful as SMEs live in a supply chain ecosystem in which they constantly do business with each other. Thereby, we present a novel method to improve traditional default prediction models by incorporating information about the insolvency situation of customers and suppliers of a given SME, using a graph-based representation of SME supply chains. We analyze its performance and illustrate how this proposed solution outperforms the traditional default prediction approaches.

Machine learning systems both gained significant interest from the academic side and have seen adoption in the industry. However, one aspect that has received insufficient attention so far is the study of the lifecycle of such systems. This aspect is particularly important due to various ML systems' strong dependency on data, which is constantly evolving-and, therefore, changing-over time. The focus of my PhD research is the study of the implications of these dynamics on the ML systems' performance. Concretely, I propose a method of detecting changes caused by drift in the data early. Furthermore, I discuss possibilities for automating large parts of the ML lifecycle management, to ensure a better and more controllable maintenance process.

Due to the continuous change in operational data, AIOps solutions suffer from performance degradation over time. Although periodic retraining is the state-of-the-art technique to preserve the failure prediction AIOps models' performance over time, this technique requires a considerable amount of labeled data to retrain. In AIOps obtaining label data is expensive since it requires the availability of domain experts to intensively annotate it. In this paper, we present McUDI, a model-centric unsupervised degradation indicator that is capable of detecting the exact moment the AIOps model requires retraining as a result of changes in data. We further show how employing McUDI in the maintenance pipeline of AIOps solutions can reduce the number of samples that require annotations with 30k for job failure prediction and 260k for disk failure prediction while achieving similar performance with periodic retraining.