Modeling multi-peril catastrophe using a distributed simulation engine
Modeling multi-peril catastrophe using a multidimensional timeseries data server that creates a first dataset by retrieving previously gathered and analyzed data based on a plurality of perils, and create a second dataset by retrieving from memory synthetically generated data based at least on the plurality of perils; and a directed computational graph service configured to retrieve the first dataset and second dataset from the multidimensional time series data server, and perform graph analysis on the first dataset and second dataset to find links amongst the plurality of perils.
1 . A system for modifying an insurance contract based on multi-peril catastrophe modeling using directed graphs and event linking, comprising:
a plurality of computing devices each comprising at least a processor, a memory, and a network interface;
wherein a plurality of programming instructions stored in one or more of the memories and operating on one or more of the processors of the plurality of computing devices causes the plurality of computing devices to:
receive real-world insurance data, the real-world insurance data comprising a potential insurance loss and time series data for a plurality of risks that may lead to the potential insurance loss;
create a first directed graph from the real-world insurance data, wherein the first directed graph comprises nodes representing events and edges representing a probability of one event occurring after another, the nodes and edges comprising a plurality of pathways from the plurality of risks to the insurance loss;
receive a user-specified parameter for generation of simulated insurance data;
generate simulated insurance data from probabilistic analyses of the real-world insurance data based on the user-specified parameter, wherein:
the simulated insurance data comprises the potential insurance loss and time series data for a plurality of simulated risks that may lead to the potential insurance loss; and
the probabilistic analyses used to generate the simulated insurance data comprise a Monte Carlo simulation for each of the plurality of simulated risks based on the potential insurance loss and time series data; and
create a second directed graph comprising nodes representing events and edges representing a probability of one event occurring after another, the nodes and edges comprising a plurality of pathways from the simulated insurance data; and
perform graph analysis on the first directed graph and second directed graph to find a pathway common to both graphs which leads to the potential insurance loss;
determine a risk associated with the common pathway based on the edge probabilities of the common pathway; and
change an insurance premium of an insurance contract based on the risk.
2 . The system of claim 1 , further comprising the step of forecasting a probability of occurrence of the potential insurance loss based at least in part by the first directed graph, the second directed graph, and the common pathway.
3 . The system of claim 1 , wherein the real-world insurance data further comprises geographical information, and the graph analysis further comprises tessellated grid modeling to determine a geographical link between the first directed graph and second directed graph.
4 . The system of claim 1 , wherein the graph analysis further comprises path-dependency modeling to identify a pathway to the potential insurance loss with a specific metric.
5 . The system of claim 1 , the graph analysis further comprises a dimensionality reduction analysis to reduce the complexity of the graph analysis.
6 . The system of claim 1 , wherein the graph analysis further comprises dynamic micro-peril modeling to identify pathways that lead to alternate, less-severe losses than the potential insurance loss.
7 . A method for modifying an insurance contract based on multi-peril catastrophe modeling using directed graphs and event linking, comprising the steps of:
receiving real-world insurance data, the real-world insurance data comprising a potential insurance loss and time series data for a plurality of risks that may lead to the potential insurance loss;
creating a first directed graph from the real-world insurance data, wherein the first directed graph comprises nodes representing events and edges representing a probability of one event occurring after another, the nodes and edges comprising a plurality of pathways from the plurality of risks to the insurance loss;
generating simulated insurance data from probabilistic analyses of the real-world insurance data based on the user-specified parameter, wherein:
the simulated insurance data comprises the potential insurance loss and time series data for a plurality of simulated risks that may lead to the potential insurance loss; and
the probabilistic analyses used to generate the simulated insurance data comprise a Monte Carlo simulation for each of the plurality of simulated risks based on the potential insurance loss and time series data;
creating a second directed graph comprising nodes representing events and edges representing a probability of one event occurring after another, the nodes and edges comprising a plurality of pathways from the simulated insurance data;
performing graph analysis on the first directed graph and second directed graph to find a pathway common to both graphs which leads to the potential insurance loss;
determining a risk associated with the common pathway based on the edge probabilities of the common pathway; and
changing an insurance premium of an insurance contract based on the risk.
8 . The method of claim 7 , further comprising the step of forecasting a probability of occurrence of the potential insurance loss based at least in part by the first directed graph, the second directed graph, and the common pathway.
9 . The method of claim 7 , wherein the real-world insurance data further comprises geographical information, and the graph analysis further comprises tessellated grid modeling to determine a geographical link between the first directed graph and second directed graph.
10 . The method of claim 7 , wherein the graph analysis further comprises path-dependency modeling to identify a pathway to the potential insurance loss with a specific metric.
11 . The method of claim 7 , the graph analysis further comprises a dimensionality reduction analysis to reduce the complexity of the graph analysis.
12 . The method of claim 7 , wherein the graph analysis further comprises dynamic micro-peril modeling to identify pathways that lead to alternate, less-severe losses than the potential insurance loss.
13 . A computer-readable, non-transitory medium comprising a plurality of programming instructions that, when operating on a plurality of computing devices each comprising at least a processor, a memory, and a network interface, cause the plurality of computing devices to carry out the method of claim 7 .