DISTRIBUTABLE MODEL WITH BIASES CONTAINED WITHIN DISTRIBUTED DATA
A system for improving a distributable model with biases contained in distributed data is provided, comprising a network-connected distributable model configured to serve instances of a plurality of distributable models; and a directed computation graph module configured to receive at least an instance of at least one of the distributable models from the network-connected computing system, create a cleansed dataset from data stored in the memory based at least in part by biases contained within the data stored in memory, train the instance of the distributable model with the cleansed dataset, and generate an update report based at least in part by updates to the instance of the distributable model.
1 . A computing system for improving a distributable model with biases contained in distributed data employing a distributable model platform, the computing system comprising:
one or more hardware processors configured for:
receiving a first distributable model comprising data;
removing a plurality of data biases from the first distributable model using a plurality of data transformation nodes configured to process the data by removing biases, wherein the biases comprise trends exhibited within the data;
creating a generalized dataset based on an instance of the first distributable model and the removed data biases for use in a second distributable model, wherein the generalized dataset is created in part by automatically weighting and correcting the biases using the plurality of data transformation nodes;
assigning a sector classification to the generalized dataset;
training the second distributable model with the generalized dataset;
uploading the second distributable model to a distributable model source; and
generating an update report based at least in part on changes made to the first distributable model to train the second distributable model.
2 . The computing system of claim 1 , wherein at least a portion of the generalized dataset is data that has had sensitive information removed.
3 . The computing system of claim 1 , wherein the at least a portion of the update report is used by the distributable model source to improve the first distributable model.
4 . The computing system of claim 1 , wherein at least a portion of the biases contained within the first distributable model is based on geography.
5 . The computing system of claim 1 , wherein at least a portion of the biases contained within the first distributable model is based on age.
6 . The computing system of claim 1 , wherein at least a portion of the biases contained within the first distributable model is based on gender.
7 . A computer-implemented method executed on a distributable model platform for improving a distributable model with biases contained in distributed data, the computer-implemented method comprising:
receiving a first distributable model comprising data;
removing a plurality of data biases within the first distributable model using a plurality of data transformation nodes configured to process the data by removing biases, wherein the biases comprise trends exhibited within the data;
creating a generalized dataset based on an instance of the first distributable model and the removed data biases for use in a second distributable model, wherein the generalized dataset is created in part by automatically weighting and correcting the biases using the plurality of data transformation nodes;
assigning a sector classification to the generalized dataset;
training the second distributable model with the generalized dataset using the directed computation graph module;
uploading the second distributable model to the distributable model source; and
generating an update report based at least in part by updates to the instance of the distributable model with the directed computation graph module.
8 . The computer-implemented method of claim 7 , wherein at least a portion of the generalized dataset is data that has had sensitive information removed.
9 . The computer-implemented method of claim 7 , wherein the at least a portion of the update report is used by the distributable model source to improve the first distributable model.
10 . The computer-implemented method of claim 7 , wherein at least a portion of the biases contained within the first distributable model is based on geography.
11 . The computer-implemented method of claim 7 , wherein at least a portion of the biases contained within the first distributable model is based on age.
12 . The computer-implemented method of claim 7 , wherein at least a portion of the biases contained within the first distributable model is based on gender.
13 . A system for improving a distributable model with biases contained in distributed data employing a distributable model platform, comprising one or more computers with executable instructions that, when executed, cause the system to:
receive a first distributable model comprising data;
remove a plurality of data biases from the first distributable model using a plurality of data transformation nodes configured to process the data by removing biases, wherein the biases comprise trends exhibited within the data;
create a generalized dataset based on an instance of the first distributable model and the removed data biases for use in a second distributable model, wherein the generalized dataset is created in part by automatically weighting and correcting the biases using the plurality of data transformation nodes;
assign a sector classification to the generalized dataset;
train the second distributable model with the generalized dataset;
upload the second distributable model to a distributable model source; and
generate an update report based at least in part on changes made to the first distributable model to train the second distributable model.
14 . The system of claim 13 , wherein at least a portion of the generalized dataset is data that has had sensitive information removed.
15 . The system of claim 13 , wherein the at least a portion of the update report is used by the distributable model source to improve the first distributable model.
16 . The system of claim 13 , wherein at least a portion of the biases contained within the first distributable model is based on geography.
17 . The system of claim 13 , wherein at least a portion of the biases contained within the first distributable model is based on age.
18 . The system of claim 13 , wherein at least a portion of the biases contained within the first distributable model is based on gender.
19 . Non-transitory computer-readable storage media having computer-executable instructions embodied thereon that, when executed by one or more processors of a computing system employing a distributable model platform, cause the computing system to:
receive a first distributable model comprising data;
remove a plurality of data biases from the first distributable model using a plurality of data transformation nodes configured to process the data by removing biases, wherein the biases comprise trends exhibited within the data;
create a generalized dataset based on an instance of the first distributable model and the removed data biases for use in a second distributable model, wherein the generalized dataset is created in part by automatically weighting and correcting the biases using the plurality of data transformation nodes;
assign a sector classification to the generalized dataset;
train the second distributable model with the generalized dataset;
upload the second distributable model to a distributable model source; and
generate an update report based at least in part on changes made to the first distributable model to train the second distributable model.
20 . The non-transitory computer-readable storage media of claim 19 , wherein at least a portion of the generalized dataset is data that has had sensitive information removed.
21 . The non-transitory computer-readable storage media of claim 19 , wherein the at least a portion of the update report is used by the distributable model source to improve the first distributable model.
22 . The non-transitory computer-readable storage media of claim 19 , wherein at least a portion of the biases contained within the first distributable model is based on geography.
23 . The non-transitory computer-readable storage media of claim 19 , wherein at least a portion of the biases contained within the first distributable model is based on age.
24 . The non-transitory computer-readable storage media of claim 19 , wherein at least a portion of the biases contained within the first distributable model is based on gender.