Pinned Repositories
Efficient-Risk-Estimation-via-Nested-Sequential-Simulation
Insurance-reports-through-deep-neural-networks
Insurance reports through deep neural networks
isaaccs.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
Prediction-of-the-outcome-of-insurance-claims-with-deep-neural-networks
In this paper, we develop a methodology to perform the predic- tion on an open insurance claim (RBNS, Reported But Not Settled) from a set of complex covariates with various structures (structured and unstructured data). The technique combines different deep neu- ral networks architectures (such as Long Short Term Memory for text data) with survival analysis prediction methods (to predict the time of settlement of the claim). The deep learning methods are used to extract features from our complex data, hence to perform dimension reduction. These features may be plugged in a final neural network predictor, or combined with more intelligible models like a General- ized Linear Model, if the need for interpretation is more important than the quality of the prediction. A real data analysis illustrates the technique.
sentiment-analysis-for-financial-news
sentiment analysis for financial news
Stackoverflow-Generate-Answer
recofilm
isaaccs's Repositories
isaaccs/sentiment-analysis-for-financial-news
sentiment analysis for financial news
isaaccs/Insurance-reports-through-deep-neural-networks
Insurance reports through deep neural networks
isaaccs/isaaccs.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
isaaccs/Dog-Breed-Classifier
isaaccs/Efficient-Risk-Estimation-via-Nested-Sequential-Simulation
isaaccs/Prediction-of-the-outcome-of-insurance-claims-with-deep-neural-networks
In this paper, we develop a methodology to perform the predic- tion on an open insurance claim (RBNS, Reported But Not Settled) from a set of complex covariates with various structures (structured and unstructured data). The technique combines different deep neu- ral networks architectures (such as Long Short Term Memory for text data) with survival analysis prediction methods (to predict the time of settlement of the claim). The deep learning methods are used to extract features from our complex data, hence to perform dimension reduction. These features may be plugged in a final neural network predictor, or combined with more intelligible models like a General- ized Linear Model, if the need for interpretation is more important than the quality of the prediction. A real data analysis illustrates the technique.
isaaccs/Stackoverflow-Generate-Answer
isaaccs/disaster_response_pipeline
isaaccs/Log2Vec
A distributed representation method for online logs.
isaaccs/loglizer
A log analysis toolkit for automated anomaly detection [ISSRE'16]
isaaccs/pipeline-calculatrice-Jenkins
isaaccs/SmartThingsPublic
SmartThings open-source DeviceTypeHandlers and SmartApps code