Systems and methods for automated data set matching services
The present solution provides systems and methods to receive a data set comprising a representation of one or more questions from a survey and provide the data set as input to each of a plurality of machine learning models trained to predict a domain associated with the one or more questions. The systems and methods can receiving as output a first domain prediction for the domain from each of the plurality of machine learning models and determine a second domain prediction for the domain for each question of the one or more questions based on applying a function to each of the first domain predictions. The systems and methods can select, based on the data set and the second domain prediction, an enumerated list of one or more answers from an answer set and cause a display of the enumerated list via a user interface for a selection.
1 . A method comprising,
receiving, by a data processing system, a data set comprising a representation of one or more questions from a survey;
providing, by the data processing system, the data set as input to each instantiation of a plurality of different types of machine learning models trained to predict a domain associated with the one or more questions;
receiving as output, by the data processing system, a first domain prediction for the domain from each instantiation of a plurality of different types of machine learning models;
determining, by the data processing system, a second domain prediction for the domain for each question of the one or more questions based on applying a function to each of the first domain predictions;
selecting, by the data processing system, based on the data set and the second domain prediction, an enumerated list of one or more answers from an answer set;
and
causing, by the data processing system, a display of the enumerated list via a user interface for a selection;
receiving, by the data processing system, an indication of the selection of one of the answers from the enumerated list; and
retraining, by the data processing system, one or more machine learning models of the plurality of different types of machine learning models based on the indication of the selection.
2 . The method of claim 1 , further comprising:
generating, by each of the plurality of machine learning models, a first confidence level for each of the first domain predictions;
determining, by the data processing system, a second confidence level based on each of the first confidence levels; and
causing, by the data processing system, a display of the second confidence level for the selection of each answer of the enumerated list via the user interface.
3 . The method of claim 1 , wherein applying the function to each of the first domain predictions comprises summing a number of the machine learning models sharing a predicted domain for each of the one or more questions.
4 . The method of claim 1 , wherein applying the function to each of the first domain predictions comprises:
receiving a confidence level for the first domain predictions from each of the plurality of machine learning models;
summing the confidence level of the first domain predictions for each of the predicted domains; and
selecting a domain of the predicted domains associated with a highest confidence level summation.
5 . The method of claim 1 , wherein an answer of the answer set includes a time interval for which the answer is valid.
6 . The method of claim 1 , wherein causing the display of the enumerated list comprises:
causing the display of a plurality of domains; and
causing the display of an association between each of the answers of the enumerated list and one of the plurality of domains.
7 . A system comprising:
at least one processor associated with a data processing system;
at least one memory storing computer-readable instructions, wherein the at least one processor is operable to access the at least one memory and execute the computer-readable instructions to:
receive a data set comprising a representation of one or more questions from a survey;
provide the data set as input to each instantiation of a plurality of different types of machine learning models trained to predict a domain associated with the one or more questions;
receive as output a first domain prediction for the domain from each instantiation of a plurality of different types of machine learning models;
determine a second domain prediction for the domain for each question of the one or more questions based on applying a function to each of the first domain predictions;
select, based on the data set and the second domain prediction, an enumerated list of one or more answers from an answer set;
cause a display of the enumerated list via a user interface for a selection;
receive an indication of the selection of one of the answers from the enumerated list; and
retrain a machine learning model of the plurality of different types of machine learning models based on the indication of the selection.
8 . The system of claim 7 , wherein the processors execute computer-readable instructions to:
generate, by each of the plurality of machine learning models, a first confidence level for each of the first domain predictions;
determine a second confidence level based on each of the first confidence levels; and
cause a display of the second confidence level for the selection of each answer of the enumerated list via the user interface.
9 . The system of claim 7 , wherein, to apply the function to each of the first domain predictions, the processors execute computer-readable instructions to sum a number of the machine learning models sharing a predicted domain for each of the one or more questions.
10 . The system of claim 7 , wherein, to apply the function to each of the first domain predictions comprises, the processors execute computer-readable instructions to:
receive a confidence level for the first domain predictions from each of the plurality of machine learning models;
sum the confidence level of the first domain predictions for each of the predicted domains; and
select a domain of the predicted domains associated with a highest confidence level summation.
11 . The system of claim 7 , wherein each answer of the answer set includes a time interval for which the answer is valid.
12 . The system of claim 7 , wherein to cause the display of the enumerated list, the processors execute computer-readable instructions to:
cause the display of a plurality of domains; and
cause the display of an association between each of the answers of the enumerated list and one of the plurality of domains.
13 . A non-transitory computer-readable media comprising computer-readable instructions stored thereon that when executed by one or more processors of a data processing system cause the one or more processors to:
receive a data set comprising a representation of one or more questions from a survey;
provide the data set as input to each instantiation of a plurality of different types of machine learning models trained to predict a domain associated with the one or more questions;
receive as output a first domain prediction for the domain from each instantiation of a plurality of different types of machine learning models;
determine a second domain prediction for the domain for each question of the one or more questions based on applying a function to each of the first domain predictions;
select, based on the data set and the second domain prediction, an enumerated list of one or more answers from an answer set; and
cause a display of the enumerated list via a user interface for a selection;
receive an indication of the selection of one of the answers from the enumerated list; and
retrain one or more machine learning models of the plurality of different types of machine learning models based on the indication of the selection.
14 . The non-transitory computer-readable media of claim 13 , wherein the computer-readable instructions comprise instructions to:
generate, by each of the plurality of machine learning models, a first confidence level for each of the first domain predictions;
determine a second confidence level based on each of the first confidence levels; and
cause a display of the second confidence level for the selection of each answer of the enumerated list via the user interface.
15 . The non-transitory computer-readable media of claim 13 , wherein the computer-readable instructions comprise instructions to sum a number of the machine learning models sharing a predicted domain for each of the one or more questions.
16 . The non-transitory computer-readable media of claim 13 , wherein, to apply the function to each of the first domain predictions comprises, the processors execute computer-readable instructions to:
receive a confidence level for the first domain predictions from each of the plurality of machine learning models;
sum the confidence level of the first domain predictions for each of the predicted domains; and
select a domain of the predicted domains associated with a highest confidence level summation.
17 . The non-transitory computer-readable media of claim 13 , wherein to cause the display of the enumerated list, the processors execute computer-readable instructions to:
cause the display of a plurality of domains; and
cause the display of an association between each of the answers of the enumerated list and one of the plurality of domains.