Despite abundant energy use data, few facilities managers have a good benchmark for tracking energy performance in commercial buildings. Building energy self-benchmarking is an effective means of comparing performance to expectations. This paper presents an improved theory for a decision support tool that can self-benchmark building energy performance, identify energy faults, and quantify their severity. Detailed building energy simulation modeling of a big-box retail store with open source software is accessible and economical to industry for generating performance benchmarks. Methods of parametric sampling and uncertainty analysis are enhanced with detailed parameter uncertainty characterization. Uncertainty and sensitivity analysis are used to adjust risk tolerance thresholds for each unique monitored end-use. A dynamic cost function allows utility theory to compute expected costs covering multiple criteria. Improved theory for decision support tool is tested on ten faulted model scenarios placed in three climate zones. Finally, we demonstrate fault response prioritization.
The paper addresses the challenge of accelerating identification of changes in risk drivers in the insurance industry. Specifically, the work presents a method to identify significant news events ("signals") from batches of news data to inform Life & Health insurance decisions. Signals are defined as events that are relevant to a tracked risk driver, widely discussed in multiple news outlets, contain novel information and affect stakeholders. The method converts unstructured data (news articles) into a sequence of keywords by employing a linguistic knowledge graph-based model. Then, for each time window, the method forms a graph with extracted keywords as nodes and draws weighted edges based on keyword co-occurrences in articles. Lastly, events are derived in an unsupervised way as graph communities and scored for the requirements of a signal: relevance, novelty and virality. The methodology is illustrated for a Life & Health topic using news articles from Dow Jones DNA proprietary data set, and assessed against baselines on a publicly available news data set. The method is implemented as an analytics engine in Early Warning System deployed at Swiss Re for the last 1.5 years to extract relevant events from live news data. We present the system's architectural design in production and discuss its use and impact.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.