Automobile Monitoring Systems and Methods for Loss Reserving and Financial Reporting

1 . A computer-implemented method of predicting loss reserves, the method comprising receiving, in a computing device, a plurality of historical electronic claim documents, each respectively labeled with a claim loss amount;

normalizing, via one or more processors, each respective claim loss amount;

training an artificial neural network, wherein training the artificial neural network includes applying the plurality of historical electronic claim documents to the artificial neural network;

receiving, in the computing device, a user claim, the user claim comprising free-form text and an image; and

predicting a loss reserve amount, by applying the user claim to the trained artificial neural network, wherein the predicting a loss reserve amount comprises:

determining a first cause of loss by applying the trained artificial neural network to the free-form text of the user claim;

determining a second cause of loss by applying the trained artificial neural network to the image of the user claim; and

predicting the loss reserve amount using the trained artificial neural network based at least in part upon the first cause of loss and the second cause of loss.

2 . The computer-implemented method of claim 1 , wherein the user claim is a first user claim, and the loss reserve amount is a first loss reserve amount, the method further comprising

receiving a second user claim;

predicting a second loss reserve amount, by applying the second user claim to the trained artificial neural network; and

computing an aggregate loss reserve amount by analyzing the first loss reserve amount and the second loss reserve amount.

3 . The computer-implemented method of claim 2 , wherein computing an aggregate loss reserve amount by analyzing the first loss reserve amount and second loss reserve amount includes one or both of (i) summing the first loss reserve amount and the second loss reserve amount, and (ii) summing the absolute value of the first loss reserve amount and the second loss reserve amount.

4 . The computer-implemented method of claim 2 , further comprising:

setting aside funds in the amount of the aggregated loss reserve amount.

5 . The computer-implemented method of claim 2 , wherein training the artificial neural network, wherein training the artificial neural network includes applying the plurality of electronic claim documents to the artificial neural network includes applying a first subset of the plurality of electronic claim documents to the artificial neural network, and iteratively training the artificial neural network until loss of the network is less than a maximum value.

6 . The computer-implemented method of claim 2 , further comprising:

determining one or both of (i) network loss of the trained artificial neural network, and (ii) network accuracy of the trained artificial neural network with respect to the plurality of historical electronic claim documents.

7 . The computer-implemented method of claim 2 , further comprising:

generating, via the one or more processors, at least a portion of a financial report, the at least the portion of the financial report including at least one type of the plurality of historical electronic claim documents, and the loss reserve amount.

8 . The computer-implemented method of claim 7 , wherein the type of the plurality of historical electronic claim documents and the loss reserve amount are displayed in a tabular format.

9 . The computer-implemented method of claim 2 , wherein the loss reserve amount is a first loss reserve amount, the method further comprising:

receiving, in the computing device, a settled claim;

updating the trained artificial neural network, wherein updating the trained artificial neural network includes applying the settled claim to the artificial neural network; and

predicting a second loss reserve amount, by applying the user claim to the trained artificial neural network.

10 . The computer-implemented method of claim 9 , further comprising comparing the first loss reserve amount to the second loss reserve amount to determine an impact of the settled claim.

11 . A loss reserving system comprising:

a computing system having one or more network devices,

one or more processors,

an electronic display device having a plurality of display sections; and

a loss reserving application comprising a set of computer-executable instructions stored on one or more memories, wherein the set of computer-executable instructions, when executed, by the one or more processors, cause the loss reserving system to:

receive, in an application, an indication of a user including one or both of (i) a trained artificial neural network, and (ii) a data set;

transmit, via the one or more network devices, a request including the one or both of (i) the trained artificial neural network, and (ii) the data set, to a remote computing device;

receive, from the remote computing device, an output of the trained artificial neural network, the output including an identification of the data set and a loss reserve amount corresponding to the data set; and

display, in one of the plurality of display sections of the electronic display device, the output of the trained artificial neural network.

12 . The loss reserving system of claim 11 , wherein the computer-executable instructions further cause the loss reserving system to:

receive, in the application, a user query; and

retrieve, from an electronic database, the data set, wherein the data set corresponds to the user query.

13 . A computing system comprising:

one or more processor; and

one or more memories storing instructions that, when executed by the one or more processors, cause the computing system to:

receive, in a computing device, a plurality of historical electronic claim documents, each respectively labeled with a claim loss amount;

normalize, via one or more processors, each respective claim loss amount;

train an artificial neural network, wherein training the artificial neural network includes applying the plurality of historical electronic claim documents to the artificial neural network;

receive, in the computing device, a user claim, the user claim comprising free-form text and an image;

determine a first cause of loss by applying the trained artificial neural network to the free-form text of the user claim;

determine a second cause of loss by applying the trained artificial neural network to the image of the user claim; and

predict a loss reserve amount, by applying the user claim to the trained artificial neural network based at least in part upon the first cause of loss and the second cause of loss.

14 . The computing system of claim 13 , wherein the user claim is a first user claim, and the loss reserve amount is a first loss reserve amount, and the instructions further cause the computing system to:

receive a second user claim;

predict a second loss reserve amount, by applying the second user claim to the trained artificial neural network; and

compute an aggregate loss reserve amount by analyzing the first loss reserve amount and the second loss reserve amount.

15 . The computing system of claim 14 , wherein the instructions further cause the computing system to:

one or both of (i) sum the first loss reserve amount and the second loss reserve amount, and (ii) sum the absolute value of the first loss reserve amount and the second loss reserve amount.

16 . The computing system of claim 14 , wherein the instructions further cause the computing system to:

set aside funds in the amount of the aggregated loss reserve amount.

17 . The computing system of claim 13 , wherein the instructions further cause the computing system to:

apply a first subset of the plurality of electronic claim documents to the artificial neural network; and

train the artificial neural network iteratively until loss of the network is less than a maximum value.

18 . The computing system of claim 13 , wherein the instructions further cause the computing system to:

determine one or both of (i) network loss of the trained artificial neural network, and (ii) network accuracy with respect to the plurality of historical electronic claim documents of the trained artificial neural network.

19 . The computing system of claim 13 , wherein the instructions further cause the computing system to:

generate, via the one or more processors, at least a portion of a financial report, the at least the portion of the financial report including at least one type of the plurality of historical electronic claim documents, and the loss reserve amount.

20 . The computing system of claim 13 , wherein the loss reserve amount is a first loss reserve amount, and wherein the instructions further cause the computing system to:

receive, in the computing device, a settled claim;

update the trained artificial neural network by applying the settled claim to the artificial neural network; and

predict a second loss reserve amount, by applying the user claim to the trained artificial neural network.