Learning Inter-Annual Flood Loss Risk Models from Historical Flood Insurance Claims

This research evaluates different regression models to predict #flood-induced #insuranceclaims, using the #us #national #floodinsurance Program (#nfip) dataset from 2000 to 2020. The models studied include #neuralnetworks (Conditional Generative Adversarial Networks), #decisiontrees (Extreme Gradient Boosting), and #kernel-based regressors (#gaussian Process). The study identifies key predictors for regression, highlighting factors that influence flood-related financial damages.

LIRE

Posts récents

Voir tout

Keep Calm and Bank on: Panic-Driven Bank Runs and the Role of Public Communication

Information about #fdic #insurance and communication about #bank #stability by the #federalreserve can reassure depositors and mitigate #bankruns, while communication from political leaders only influ

Natural Disaster Risk and Firm Performance: Text Mining and Machine Learning Approach

Advanced #machinelearning models were found to be more effective than #linearregression in predicting firm performance under #naturaldisaster #risks. The study suggests that textual data in #financial

Evolution of Cybersecurity Disclosure

#regulators recently issued #cybersecurity #disclosure guidelines to enhance #transparency and #accountability among firms. A study analyzed cybersecurity disclosure practices among a sample of Toront