Average treatment effect for paired data

1 . A computer-implemented method comprising:

identifying a plurality of data variables within a stream of a multivariate event dataset;

formalizing a causal inference between a first identified data variable associated with historical occurrences and a second identified data variable associated with a different occurrence within the multivariate event dataset by determining a causal connection strength for the first identified data variable and the second identified data variable;

training a data model with the multivariate event dataset based on the causal inference, wherein the data model estimates a plurality of treatment effects between the first identified data variable and the second identified data variable;

calculating an inverse propensity score for the data model based on a type of identified variable, a predetermined time associated with the identified variable, and the causal connection strength between the first identified data variable and the second identified data variable;

validating the inverse propensity score by splitting the multivariate event dataset into a training data set based on an identified optimal time window;

responsive to the inverse propensity score being validated, optimizing the data model by strengthening the causal inference between the first identified data variable and the second identified data variable;

responsive to the inverse propensity score failing validation, optimizing the data model by removing the causal inference between the first identified data variable and the second identified data variable.

2 . The computer-implemented method of claim 1 , wherein identifying the plurality of data variables comprises:

analyzing the multivariate event dataset for a data variable based on a plurality of indicative markers;

identifying at least two analyzed data variables based on an average treatment effect and a propensity value using a plurality of scanning devices; and

retrieving the at least two analyzed data variables based on a positive match percentage that meets or exceeds a predetermined threshold of change associated with the plurality of indicative markers, wherein a retrieved data variable assists in formalizing the causal inference within the multivariate event dataset.

3 . The computer-implemented method of claim 1 , wherein formalizing the causal inference between the first identified data variable and the second identified data variable comprises:

generating a data structure that plots each identified data variable associated with the multivariate event dataset within an estimated data model;

predicting outcomes associated with collected data using the generated data structure by estimating a plurality of treatment effects between a treatment variable associated with historical occurrences and an outcome variable associated with a different occurrence; and

formalizing the causal inference between the first identified data variable and the second identified data variable based on an estimation of the plurality of treatment effects between the treatment variable and the outcome variable.

4 . The computer-implemented method of claim 1 , wherein generating the data model comprises calculating a difference between the first identified data variable and the second identified data variable at a plurality of predetermined times.

5 . The computer-implemented method of claim 1 , wherein calculating the inverse propensity score for the data model comprises modifying the first identified data variable and the second identified data variable, wherein the validating may be changing a type of identified variable, the predetermined time associated with the identified variable, and a causal connection strength between the identified plurality of data variables.

6 . The computer-implemented method of claim 1 , further comprising validating the inverse propensity score based on a derivation of an equivalent propensity score.

7 . The computer-implemented method of claim 6 , further comprising automatically terminating an operation of the data model in response to the inverse propensity score meeting or exceeding a predetermined threshold.

8 . The computer-implemented method of claim 1 , further comprising:

generating a second data model for the multivariate event dataset based on the causal inference of the first identified data variable and the second identified data variable; and

calculating an inverse propensity score for the second data model based on a plurality of factors.

9 . A computer program product comprising:

one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions comprising:

program instructions to identify a plurality of data variables within a stream of a multivariate event dataset;

program instructions to formalize a causal inference between a first identified data variable associated with historical occurrences and a second identified data variable associated with a different occurrence within the multivariate event dataset by determining a causal connection strength for the first identified data variable and the second identified data variable;

program instructions to train a data model with the multivariate event dataset based on the causal inference, wherein the data model estimates a plurality of treatment effects between the first identified data variable and the second identified data variable;

program instructions to calculate an inverse propensity score for the data model based on a type of identified variable, a predetermined time associated with the identified variable, and the causal connection strength between the first identified data variable and the second identified data variable;

program instructions to validate the inverse propensity score by splitting the multivariate event dataset into a training data set based on an identified optimal time window;

program instructions to, responsive to the inverse propensity score being validated, optimize the data model by strengthening the causal inference between the first identified data variable and the second identified data variable; and

program instructions to, responsive to the inverse propensity score failing validation, optimize the data model by removing the causal inference between the first identified data variable and the second identified data variable.

10 . The computer program product of claim 9 , wherein the program instructions to identify the plurality of data variables comprise:

program instructions to analyze the multivariate event dataset for a data variable based on a plurality of indicative markers;

program instructions to identify at least two analyzed data variables based on an average treatment effect and a propensity value using a plurality of scanning devices; and

program instructions to retrieve the at least two analyzed data variables based on a positive match percentage that meets or exceeds a predetermined threshold of change associated with the plurality of indicative markers, wherein a retrieved data variable assists in formalizing the causal inference within the multivariate event dataset.

11 . The computer program product of claim 9 , wherein the program instructions to formalize the causal inference between the first identified data variable and the second identified data variable comprise:

program instructions to generating a data structure that plots each identified data variable associated with the multivariate event dataset within an estimated data model;

program instructions to predict outcomes associated with collected data using the data structure by estimating a plurality of treatment effects between a treatment variable associated with historical occurrences and an outcome variable associated with a different occurrence; and

program instructions to formalize the causal inference between the first identified data variable and the second identified data variable based on an estimation of the plurality of treatment effects between the treatment variable and the outcome variable.

12 . The computer program product of claim 9 , wherein the program instructions to generate the data model comprise:

program instructions to calculate a difference between the first identified data variable and the second identified data variable at a plurality of predetermined times.

13 . The computer program product of claim 9 , wherein the program instructions to calculate the inverse propensity score for the data model comprise:

program instructions to modify the first identified data variable and the second identified data variable, wherein the modifying comprises changing a type of identified variable, the predetermined time associated with the identified variable, and a causal connection strength between the identified plurality of data variables.

14 . The computer program product of claim 9 , wherein the program instructions stored on the one or more computer readable storage media further comprise:

program instructions to validate the inverse propensity score based on a derivation of an equivalent propensity score.

15 . The computer program product of claim 14 , wherein the program instructions stored on the one or more computer readable storage media further comprise:

program instructions to automatically terminate an operation of the data model in response to the inverse propensity score meeting or exceeding a predetermined threshold.

16 . A computer system comprising:

one or more computer processors;

one or more computer readable storage media; and

program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the program instructions comprising:

program instructions to identify a plurality of data variables within a stream of a multivariate event dataset;

program instructions to formalize a causal inference between a first identified data variable associated with historical occurrences and a second identified data variable associated with a different occurrence within the multivariate event dataset by determining a causal connection strength for the first identified data variable and the second identified data variable;

program instructions to train a data model with the multivariate event dataset based on the causal inference, wherein the data model estimates a plurality of treatment effects between the first identified data variable and the second identified data variable;

program instructions to calculate an inverse propensity score for the data model based on a type of identified variable, a predetermined time associated with the identified variable, and the causal connection strength between the first identified data variable and the second identified data variable

program instructions to validate the inverse propensity score by splitting the multivariate event dataset into a training data set based on an identified optimal time window;

program instructions to, responsive to the inverse propensity score being validated, optimize the data model by strengthening the causal inference between the first identified data variable and the second identified data variable; and

program instructions to, responsive to the inverse propensity score failing validation, optimize the data model by removing the causal inference between the first identified data variable and the second identified data variable.

17 . The computer system of claim 16 , wherein the program instructions to identify the plurality of data variables comprise:

program instructions to analyze the multivariate event dataset for a data variable based on a plurality of indicative markers;

program instructions to identify at least two analyzed data variables based on an average treatment effect and a propensity value using a plurality of scanning devices; and

program instructions to retrieve the at least two analyzed data variables based on a positive match percentage that meets or exceeds a predetermined threshold of change associated with the plurality of indicative markers, wherein a retrieved data variable assists in formalizing the causal inference within the multivariate event dataset.

18 . The computer system of claim 16 , wherein the program instructions to formalize the causal inference between the first identified data variable and the second identified data variable comprise:

program instructions to generating a data structure that plots each identified data variable associated with the multivariate event dataset within an estimated data model;

program instructions to predict outcomes associated with collected data using the data structure by estimating a plurality of treatment effects between a treatment variable associated with historical occurrences and an outcome variable associated with a different occurrence; and

program instructions to formalize the causal inference between the first identified data variable and the second identified data variable based on an estimation of the plurality of treatment effects between the treatment variable and the outcome variable.

19 . The computer system of claim 16 , wherein the program instructions to generate the data model comprise:

program instructions to calculate a difference between the first identified data variable and the second identified data variable at a plurality of predetermined times.

20 . The computer system of claim 16 , wherein the program instructions to calculate the inverse propensity score for the data model comprise:

program instructions to modify the at least two identified variables, wherein the modifying comprises changing a type of identified variable, the predetermined time associated with the identified variable, and a causal connection strength between the identified plurality of data variables.