Automated machine learning system
An example method may include receiving, via a graphical user interface, credentials for connecting to a data store containing a plurality of datasets and connecting to the data store using the credentials. A selection of a target metric to predict using the machine learning model can be received, via the graphical user interface, and datasets included in the plurality of datasets that correlate to the target metric can be identified by analyzing the datasets to identify an association between the target metric and data contained within the datasets. The datasets can be input to the machine learning model to train the machine learning model to generate predictions of the target metric, and the machine learning model can be deployed to computing resources in a service provider environment to generate predictions associated with the target metric.
1 . A method comprising:
determining, based on a selection of a target metric, one or more data records associated with a prediction driver for the target metric;
causing, based on the selection, a first machine learning model to output a first prediction score for the target metric, wherein the first prediction score is based on the one or more data records and the prediction driver;
receiving an adjustment to an amount of influence for the prediction driver, wherein the adjustment causes at least one value stored in each of the one or more data records to be replaced with a substitute value, and wherein the substitute value for each of the one or more data records is based on the at least one value stored in the corresponding data record and the adjustment to the amount of influence for the prediction driver;
causing, based on the adjustment and the substitute value for each of the one or more data records, a second machine learning model to output a second prediction score for the target metric; and
storing, based on a further selection, the first prediction score or the second prediction score, wherein the further selection is indicative of the first machine learning model or the second machine learning model.
2 . The method of claim 1 , wherein determining the one or more data records associated with the prediction driver for the target metric comprise: determining, based on a selection received via a graphical user interface (GUI), the one or more data records, wherein the GUI comprises at least one input control, and wherein receiving the adjustment to the amount of influence for the prediction driver comprises: receiving, via the at least one input control, the adjustment to the amount of influence for the prediction driver.
3 . The method of claim 2 , wherein the at least one input control of the GUI comprises one or more of: a slider, an increment control, a decrement control, or an input box.
4 . The method of claim 1 , wherein the second machine learning model comprises another version of the first machine learning model that is trained based on the substitute value for each of the one or more data records.
5 . The method of claim 1 , wherein the adjustment to the amount of influence for the prediction driver comprises an adjustment to a weight, or to a degree of influence, associated with the prediction driver.
6 . The method of claim 1 , further comprising modifying, in proportion to the adjustment to the amount of influence for the prediction driver, the at least one value within the one or more data records.
7 . The method of claim 1 , further comprising:
training, based on the one or more data records, the first machine learning model; and
training, based on the substitute value for each of the one or more data records, the second machine learning model.
8 . An apparatus comprising:
one or more processors; and
memory storing processor-executable instructions that, when executed by the one or more processors, cause the apparatus to:
determine, based on a selection of a target metric, one or more data records associated with a prediction driver for the target metric;
cause, based on the selection, a first machine learning model to output a first prediction score for the target metric, wherein the first prediction score is based on the one or more data records and the prediction driver;
receive an adjustment to an amount of influence for the prediction driver, wherein the adjustment causes at least one value stored in each of the one or more data records to be replaced with a substitute value, and wherein the substitute value for each of the one or more data records is based on the at least one value stored in the corresponding data record and the adjustment to the amount of influence for the prediction driver;
cause, based on the adjustment and the substitute value for each of the one or more data records, a second machine learning model to output a second prediction score for the target metric; and
store, based on a further selection received, the first prediction score or the second prediction score, wherein the further selection is indicative of the first machine learning model or the second machine learning model.
9 . The apparatus of claim 8 , wherein the processor-executable instructions that cause the apparatus to determine the one or more data records associated with the prediction driver for the target metric further cause the apparatus to determine, based on a selection received via a graphical user interface (GUI), the one or more data records, wherein the GUI comprises at least one input control, and wherein the processor-executable instructions that cause the apparatus to receive the adjustment to the amount of influence for the prediction driver further cause the apparatus to: receive, via the at least one input control, the adjustment to the amount of influence for the prediction driver.
10 . The apparatus of claim 9 , wherein the at least one input control of the GUI comprises one or more of: a slider, an increment control, a decrement control, or an input box.
11 . The apparatus of claim 8 , wherein the second machine learning model comprises another version of the first machine learning model that is trained based on the substitute value for each of the one or more data records.
12 . The apparatus of claim 8 , wherein the adjustment to the amount of influence for the prediction driver comprises an adjustment to a weight, or to a degree of influence, associated with the prediction driver.
13 . The apparatus of claim 8 , wherein the processor-executable instructions further cause the apparatus to modify, in proportion to the adjustment to the amount of influence for the prediction driver, the at least one value within the one or more data records.
14 . The apparatus of claim 8 , wherein the processor-executable instructions further cause the apparatus to:
train, based on the one or more data records, the first machine learning model; and
train, based on the substitute value for each of the one or more data records, the second machine learning model.
15 . One or more non-transitory computer-readable media storing processor-executable instructions that, when executed by one or more processors of at least one computing device, cause the at least one computing device to:
determine, based on a selection of a target metric, one or more data records associated with a prediction driver for the target metric;
cause, based on the selection, a first machine learning model to output a first prediction score for the target metric, wherein the first prediction score is based on the one or more data records and the prediction driver;
receive an adjustment to an amount of influence for the prediction driver, wherein the adjustment causes at least one value stored in each of the one or more data records to be replaced with a substitute value, and wherein the substitute value for each of the one or more data records is based on the at least one value stored in the corresponding data record and the adjustment to the amount of influence for the prediction driver;
cause, based on the adjustment and the substitute value for each of the one or more data records, a second machine learning model to output a second prediction score for the target metric; and
store, based on a further selection received, the first prediction score or the second prediction score, wherein the further selection is indicative of the first machine learning model or the second machine learning model.
16 . The one or more non-transitory computer-readable media of claim 15 , wherein the processor-executable instructions that cause the at least one computing device to determine the one or more data records associated with the prediction driver for the target metric further cause the at least one computing device to determine, based on a selection received via a graphical user interface (GUI), the one or more data records, wherein the GUI comprises at least one input control, and wherein the processor-executable instructions that cause the at least one computing device to receive the adjustment to the amount of influence for the prediction driver further cause the at least one computing device to: receive, via the at least one input control, the adjustment to the amount of influence for the prediction driver.
17 . The one or more non-transitory computer-readable media of claim 16 , wherein the at least one input control of the GUI comprises one or more of: a slider, an increment control, a decrement control, or an input box.
18 . The one or more non-transitory computer-readable media of claim 15 , wherein the second machine learning model comprises another version of the first machine learning model that is trained based on the substitute value for each of the one or more data records.
19 . The one or more non-transitory computer-readable media of claim 15 , wherein the adjustment to the amount of influence for the prediction driver comprises an adjustment to a weight, or to a degree of influence, associated with the prediction driver.
20 . The one or more non-transitory computer-readable media of claim 15 , wherein the processor-executable instructions further cause the at least one computing device to modify, in proportion to the adjustment to the amount of influence for the prediction driver, the at least one value within the one or more data records.